No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Understanding the impact of animated gesture performance on personality perceptions
Abstract
Applications such as virtual tutors, games, and natural interfaces increasingly require animated characters to take on social roles while interacting with humans. The effectiveness of these applications depends on our ability to control the social presence of characters, including their personality. Understanding how movement impacts the perception of personality allows us to generate characters more capable of fulfilling this social role. The two studies described herein focus on gesture as a key component of social communication and examine how a set of gesture edits, similar to the types of changes that occur during motion warping, impact the perceived personality of the character. Surprisingly, when based on thin-slice gesture data, people's judgments of character personality mainly fall in a 2D subspace rather than independently impacting the full set of traits in the standard Big Five model of personality. These two dimensions are plasticity, which includes extraversion and openness, and stability, which includes emotional stability, agreeableness, and conscientiousness. A set of motion properties is experimentally determined that impacts each of these two traits. We show that when these properties are systematically edited in new gesture sequences, we can independently influence the character's perceived stability and plasticity (and the corresponding Big Five traits), to generate distinctive personalities. We identify motion adjustments salient to each judgment and, in a series of perceptual studies, repeatedly generate four distinctly perceived personalities. The effects extend to novel gesture sequences and character meshes, and even largely persist in the presence of accompanying speech. This paper furthers our understanding of how gesture can be used to control the perception of personality and suggests both the potential and possible limits of motion editing approaches.
... One important focus in VR and AR research is to develop effective virtual characters for applications like computer gaming, social interaction, virtual story systems, online education, etc. To represent real humans that exist in the physical world, avatars in digital environments must be able to convey personality, mood, and emotions [1][2][3][4][5][6][7]. Even though research remains active in the area of constructing computational frameworks for designing expressive virtual characters, most efforts have been dedicated to modalities like language, gestures, body motion, eye movement, and facial expression. ...
... The great majority of our experiments yielded significant results, and the detailed findings are reported in Section 4. These results suggest that people do reliably associate what virtual characters are wearing with their personality traits. Factor analysis on the three experiments' ratings (in Section 4.4) indicates that outfit manipulation offers finer-grained influence on the five traits than motion adjustment in modalities such as gestures [1]. We propose outfit guidelines for creating avatars with specific personalities in Section 5.1. ...
... In addition to visual appearance, a considerable body of work has focused on investigating the impact of verbal and nonverbal behaviors on perceived personality in the psychology and virtual agent communities. Linguistic variations [3,[25][26][27] and nonverbal behaviors, including body shape [19,28], body posture [29][30][31][32][33][34], interaction distance [32,35,36], gaze [37], facial expression [19], gesture [1,2,38], hand motion [39], and rendering style [40], have been confirmed to have significant influence on personality perception. Further, the effects of detailed verbal and nonverbal features like linguistic verbosity, content polarity [3], gesture rate [2], motion fluency [31,41,42], velocity [31,34,42,43], tension [44], rhythm [41], posture expansiveness, facial hair and attractiveness [19], and body height, weight, and surface [19,28] have been systematically investigated. ...
Designing virtual characters that are capable of reflecting a sense of personality is a key goal in research and applications in virtual reality and computer graphics. More and more research efforts are dedicated to investigating approaches to construct a diverse, equitable, and inclusive metaverse by infusing expressive personalities and styles into virtual avatars. While most previous work focused on exploring variations in virtual characters’ dynamic behaviors, characters’ visual appearance plays a crucial role in affecting their perceived personalities. This paper presents a series of experiments evaluating the effect of virtual characters’ outfits on their perceived personality. Based on the related psychology research conducted in the real world, we determined a set of outfit factors likely to reflect personality in virtual characters: color, design, and type. As a framework for our study, we used the “Big Five” personality model for evaluating personality traits. To test our hypothesis, we conducted three perceptual experiments to evaluate the outfit parameters’ contributions to the characters’ personality. In our first experiment, we studied the color factor by varying color hue, saturation, and value; in the second experiment, we evaluated the impact of different neckline, waistline, and sleeve designs; and in our third experiment, we examined the personality perception of five outfit types: professional, casual, fashionable, outdoor, and indoor. Significant results offer guidance to avatar designers on how to create virtual characters with specific personality profiles. We further conducted a verification test to extend the application of our findings to animated virtual characters in augmented reality (AR) and virtual reality (VR) settings. Results confirmed that our findings can be broadly applied to both static and animated virtual characters in VR and AR environments that are commonly used in games, entertainment, and social networking scenarios.
... For example, Manuscript submitted to ACM spreaded fingers are perceived as conveying extraversion and openness whereas a resting hand pose conveys high emotional stability and agreeableness. Smith and Neff [2017] showed that it is possible to influence the perception of the personality of a virtual character (measured with the Big Five personality model based on the traits extraversion, openness, emotional stability, agreeableness, and conscientiousness) by editing the timing and poses of gestures. While most of the changes apply to the arm motions, they showed that extending the fingers increased extraversion and a slight disfluency -which could be compared to a slight jitter or popping -reduced conscientiousness, agreeableness, and emotional stability. ...
... with the assumption that not too many responses from an individual should deviate greatly compared to the other responses in that condition. We followed Smith and Neff's [2017] example and, after extensive testing, used the same small threshold of 0.15 in order to preserve as many responses as possible. Spot checks revealed that this method correctly excluded participants whose ratings did not seem thought through, e.g., when the same rating was given to every question, or who did not answer our attention check motions correctly. ...
... Further details can be found in the Appendix in Table 2. The impact of jitter on personality is in line with results from Wang et al. [2016] and Smith and Neff [2017], who found that a resting hand pose conveys high emotional stability (jitter would be the most opposite to a resting hand pose) and disfluency in the arm motions reduces conscientiousness and emotional stability. There were no main effects of Motion Intensity for Popping or Smooth, which again is surprising considering the large errors that are being introduced. ...
Detailed hand motions play an important role in face-to-face communication to emphasize points, describe objects, clarify concepts, or replace words altogether. While shared virtual reality (VR) spaces are becoming more popular, these spaces do not, in most cases, capture and display accurate hand motions. In this paper, we investigate the consequences of such errors in hand and finger motions on comprehension, character perception, social presence, and user comfort. We conduct three perceptual experiments where participants guess words and movie titles based on motion captured movements. We introduce errors and alterations to the hand movements and apply techniques to synthesize or correct hand motions. We collect data from more than 1000 Amazon Mechanical Turk participants in two large experiments, and conduct a third experiment in VR. As results might differ depending on the virtual character used, we investigate all effects on two virtual characters of different levels of realism. We furthermore investigate the effects of clip length in our experiments.
Amongst other results, we show that the absence of finger motion significantly reduces comprehension and negatively affects people’s perception of a virtual character and their social presence. Adding some hand motions, even random ones, does attenuate some of these effects when it comes to the perception of the virtual character or social presence, but it does not necessarily improve comprehension. Slightly inaccurate or erroneous hand motions are sufficient to achieve the same level of comprehension as with accurate hand motions. They might however still affect the viewers’ impression of a character. Finally, jittering hand motions should be avoided as they significantly decrease user comfort.
... They found that injecting personality can create more powerful expression, but at the cost of animations appearing cartoonish. Smith and Neff [56] investigated how modifying gesture motion affects perceived personality, finding that perceptions of personality could be modelled through two rather than impacting five dimensions, "plasticity" and "stability". They found perceptions of extraversion and openness to be captured by plasticity, and agreeableness, conscientiousness and emotional stability by stability. ...
... Based on previous research, we hypothesized that audio would be more influential on perceived agreeableness and conscientiousness, whereas motion would strongly influence extraversion [56,57]. For emotional stability and openness to experience, previous research suggest the interplay of both speech and motion would be important [56,57]. ...
... Based on previous research, we hypothesized that audio would be more influential on perceived agreeableness and conscientiousness, whereas motion would strongly influence extraversion [56,57]. For emotional stability and openness to experience, previous research suggest the interplay of both speech and motion would be important [56,57]. Furthermore, we hypothesized that lower-realism motion and voice conditions would have a dampening effect on the perceived personality of each character. ...
The portrayed personality of virtual characters and agents is understood to influence how we perceive and engage with digital applications. Understanding how the features of speech and animation drive portrayed personality allows us to intentionally design characters to be more personalized and engaging. In this study, we use performance capture data of unscripted conversations from a variety of actors to explore the perceptual outcomes associated with the modalities of speech and motion. Specifically, we contrast full performance-driven characters to those portrayed by generated gestures and synthesized speech, analysing how the features of each influence portrayed personality according to the Big Five personality traits. We find that processing speech and motion can have mixed effects on such traits, with our results highlighting motion as the dominant modality for portraying extraversion and speech as dominant for communicating agreeableness and emotional stability. Our results can support the Extended Reality (XR) community in development of virtual characters, social agents and 3D User Interface (3DUI) agents portraying a range of targeted personalities.
... The concept of personality is primarily of interest for CA designers because of the ways in which it affects actual behavior, and precisely since those behaviors are communicative, they establish a channel of social interaction crucial to the smoothness and effectiveness of a conversation [19,20]. The domain of verbal and non-verbal language in which information indicative of personality traits can be expressed is large and diverse and contains modalities such as joking, speaking in a deep/high-pitched voice, holding a gaze and gesturing [21,22], all of which can be further divided into numerous features [23]. Research has shown, that people not only prefer CAs that align with human behavior, such as by speech style or mimicking head movements [24], but are also increasingly attracted to CAs that adapt their personality to the human over time rather than maintaining a static or consistently similar personality [24]. ...
... ABS(("conversational agent" OR "virtual agent" OR "digital agent" OR "conversational assistant" OR "virtual assistant" OR "digital assistant" OR chatbot* OR chatterbot* OR chatterbox*) AND (personality OR "big 5" OR "big five" OR "openness to experience" OR "conscientiousness" OR "extraversion" OR "agreeableness" OR "neuroticism")). Reviewing full text controlled body movements [22] reflect a high score in openness when it comes to an ECA's body language, the studies did not contain any further information on the trait's opposite pole. In the category paraverbal language, research showed that disfluencies in speech [46] is characteristic for low openness, while high emotionality in female voice [47] is considered a personality cue for high openness. ...
... However, assertions, projective statements and terse expressions [49] let a CA appear less agreeable. When it comes to body language, cues such as a tilted head [48] and exhibiting less of a vertical arm [22] reflect high agreeableness, whereas average velocity, less arm swivels, body disfluency, less clavicle use, velocity warp and less controlled body movements [22] are found to be cues representing a low agreeable body language. ...
Conversational agents (CAs)—software systems emulating conversations with humans through natural language—reshape our communication environment. As CAs have been widely used for applications requiring human-like interactions, a key goal in information systems (IS) research and practice is to be able to create CAs that exhibit a particular personality. However, existing research on CA personality is scattered across different fields and researchers and practitioners face difficulty in understanding the current state of the art on the design of CA personality. To address this gap, we systematically analyze existing studies and develop a framework on how to imbue CAs with personality cues and how to organize the underlying range of expressive variation regarding the Big Five personality traits. Our framework contributes to IS research by providing an overview of CA personality cues in verbal and non-verbal language and supports practitioners in designing CAs with a particular personality.
... [6] [19] [23] [32] Big-5 Big-5 [3] [29] [35] Big-5 ...
... Human-Agent Interaction HAI 1 *1 *2 NTT *1 Faculty of Science and Technology, Seikei University *2 NTT Media Intelligence Laboratories, NTT Corporation [30] [ 35] 3 • Big-5 [14], [15] Big-5 10 (Expressivity) Pelachaud [30] 1 6 Table 1 6-dimensional gesture expressivity parameters 6 1 Pelachaud [30] 6 Rehm [33] Pelachaud [30] 4. 1 [30] 4. 1. 1 ...
In this study, first, we analyze the relationship between personality traits and the expressivity of hand gestures in dyad interaction. Second, based on the analysis results, we propose a method for agents’ gesture generation that can express their personality traits. Our user study reveals that expected personality traits can be perceived from the agent’s animation generated by our proposed method. Especially for extroversion and emotional instability, agent gestures generated based on our method successfully gave the expected impression to the human subjects.
... This can include pointing or deictic gesture that establish reference; emblems that replace words, and imagistic metaphoric and iconic gestures that illustrate concepts and artifacts. Third, gesture communicates social information, including personality [SN17,NWAW10,NTB * 11,DKD * 16], emotion [VMD * 14, XBHN13, GFD * 15, NLK * 13, DGS13, FP16, CN19] and subtext. ...
... It is important to be able to drive these emotions in a way that is consis-tent with a character's personality and to be able to shift mood and emotion over time. One way forward might be to leverage findings from the literature of gesture and motion perception, which has identified many useful properties of gesture motion that correlate with the perception of personality [Lip98,KG10,SN17] and emotion [NLK * 13,CN19]. By changing these properties in synthesized gestures, we may exert some control over the perceived speaker personality and emotion [AHKB20, HES * 22]. ...
Gestures that accompany speech are an essential part of natural and efficient embodied human communication. The automatic generation of such co‐speech gestures is a long‐standing problem in computer animation and is considered an enabling technology for creating believable characters in film, games, and virtual social spaces, as well as for interaction with social robots. The problem is made challenging by the idiosyncratic and non‐periodic nature of human co‐speech gesture motion, and by the great diversity of communicative functions that gestures encompass. The field of gesture generation has seen surging interest in the last few years, owing to the emergence of more and larger datasets of human gesture motion, combined with strides in deep‐learning‐based generative models that benefit from the growing availability of data. This review article summarizes co‐speech gesture generation research, with a particular focus on deep generative models. First, we articulate the theory describing human gesticulation and how it complements speech. Next, we briefly discuss rule‐based and classical statistical gesture synthesis, before delving into deep learning approaches. We employ the choice of input modalities as an organizing principle, examining systems that generate gestures from audio, text and non‐linguistic input. Concurrent with the exposition of deep learning approaches, we chronicle the evolution of the related training data sets in terms of size, diversity, motion quality, and collection method (e.g., optical motion capture or pose estimation from video). Finally, we identify key research challenges in gesture generation, including data availability and quality; producing human‐like motion; grounding the gesture in the co‐occurring speech in interaction with other speakers, and in the environment; performing gesture evaluation; and integration of gesture synthesis into applications. We highlight recent approaches to tackling the various key challenges, as well as the limitations of these approaches, and point toward areas of future development.
... Their gestures are fast, frequent, energetic, and broad [23,24]. According to Laban Movement Analysis, a well established technique to systematically evaluate human motion, the time component in extrovert movements is rather sudden, which is reflected by more spacious [37] and faster movements [8]. The findings of Smith and Neff [37] illustrate that the perception of extroversion could be enhanced by the following alterations: spread fingers, increased velocity/stroke size, moving the gesture upwards. ...
... According to Laban Movement Analysis, a well established technique to systematically evaluate human motion, the time component in extrovert movements is rather sudden, which is reflected by more spacious [37] and faster movements [8]. The findings of Smith and Neff [37] illustrate that the perception of extroversion could be enhanced by the following alterations: spread fingers, increased velocity/stroke size, moving the gesture upwards. The mood concept denotes a medium-term affect state that occurs independently of specific objects or events. ...
Movement Energy – physical activeness in performing actions and Affect Priming – prior exposure to information about someone’s mood and personality might be two crucial factors that influence how we perceive someone. It is unclear if these factors influence the perception of virtual characters in a way that is similar to what is observed during in-person interactions. This paper presents different configurations of Movement Energy for virtual characters and two studies about how these influence the perception of the characters’ personality, extroversion in particular, and mood. Moreover, the studies investigate how Affect Priming (Personality and Mood), as one form of contextual priming, influences this perception. The results indicate that characters with high Movement Energy are perceived as more extrovert and in a better mood, which corroborates existing research. Moreover, the results indicate that Personality and Mood Priming influence perception in different ways. Characters that were primed as being in a positive mood are perceived as more extrovert, whereas characters that were primed as being introverted are perceived in a more positive mood.
... Thus, we here propose a system-construction method for making such a dream possible in a realistic way. The definition of per- 1 NTT Media Intelligence Laboratories, NTT Corporation, Yokosuka, Kanagawa 239-08474, Japan 2 NTT Communication Science Laboratories, NTT Corporation, "Keihanna Science City", Kyoto 619-0237, Japan 3 DWANGO Co., Ltd., Chuo, Tokyo 104-0061, Japan a) ryo.ishii.ct@hco.ntt.co.jp sonality in this study means a character's behavioral tendency to respond to an input stimulus, typically an utterance from a conversational partner which is one of the aspects of personality. ...
... We tackled these two research problems to allow generating utterances and body motions of an existing character with the system. Some previous studies used the Big-5 personality traits to represent the personality of conversational agents with utterance and body motion [1], [2], [3]. Although certain aspects of personality can be converted on the basis of the Big-5, such dimensions are too broad and rough when agents need to generate fine-grained answers related to their personality. ...
Starting from their early years, many persons dream of being able to chat with their favorite anime characters. To make such a dream possible, we propose an efficient method for constructing a system that enables users to text chat with existing anime characters. We tackled two research problems to generate verbal and nonverbal behaviors for a text-chat agent system utilizing an existing character. A major issue in creating verbal behavior is generating utterance text that reflects the personality of existing characters in response to any user questions. To cope with this problem we propose use of role play-based question-answering to efficiently collect high-quality paired data of user questions and system answers reflecting the personality of an anime character. We also propose a new utterance generation method that uses a neural translation model with the collected data. Rich and natural expressions of nonverbal behavior greatly enhance the appeal of agent systems. However, not all existing anime characters move as naturally and as diversely as humans. Therefore, we propose a method that can automatically generate whole-body motion from spoken text in order to give the anime characters natural, human-like movements. In addition to these movements, we try to add a small amount of characteristic movement on a rule basis to reflect personality. We created a text-dialogue agent system of a popular existing anime character using our proposed generation methods. As a result of a subjective evaluation of the implemented system, our methods for generating verbal and nonverbal behavior improved the impression of the agent's responsiveness and reflected the personality of the character. Since generating characteristic motions with a small amount of characteristic movement on the basis of heuristic rules was not effective, our proposed motion generation method which can generate the average motion of many people, is useful for generating motion for existing anime characters. Therefore, our proposed methods for generating verbal and nonverbal behaviors and the system-construction method are likely to prove a powerful tool for achieving text-dialogue agent systems for existing characters.
... In fact, the model of Openness to experience, Conscientiousness, Extraversion, Agreeableness, and Neuroticism was conceived to describe behavioral, cognitive, and emotional patterns, rather than visual aspects. Rather, Smith and Neff [8] have concluded that judgments on non interactive characters would better fit to the two-dimension model of plasticity and stability. For judgements of personality based on aesthetics of static stimuli (i.e., static pictures in neutral poses, aka, zero-acquaintance first encounters), Oosterhof and Todorov found that the couple Dominance + Thustworthiness is a more appropriate model of perceived personality [9]. ...
... Reversing the goal, there is work which instead consider a personality profile as input and produce a virtual character who would elicit the given profile when judged. Examples are in the field of behaviour control [8], [12], movement style [13], and generation of body shape [14]; all using the OCEAN model. Concerning models for zero-acquaitance, a generation of pictures from dominance and trustworthiness is proposed by Vernon et al. [15] and by Nunnari and Heloir [4], [5]. ...
This paper presents a contest between the rating and the paired comparison voting in judging the perceived dominance of virtual characters, the aim being to select the voting mode that is the most convenient for voters while staying reliable. The comparison consists of an experiment where human subjects vote on a set of virtual characters generated by randomly altering a set of physical attributes. The minimum number of participants has been determined via numerical simulation. The result of the experiment is a set of stereotypes for the perception of submissiveness or dominance. Results show that the two voting modes result in equivalently expressive models of dominance. Further analysis of the voting procedure shows that, despite an initial slower learning phase, after about 30 votes the judging speed matches between the two modes. Finally, a subjective questionnaire reports a higher (63.8%) preference for the paired comparison mode.
... [29] uses a similar set of parameters including gesture rate, scale, and position, and find they can significantly influence perceptions of extraversion by modifying these parameters in gestures. [33] extends this work by using a set of parameter modifications to target perceptions of all Big Five personality traits. [5] defines a set of 11 motion parameters and shows that they can manipulate the perceived emotional content, defined by valence and arousal, of a gesture. ...
... Arm swivel (4) describes the rotation around an axis between the shoulder and the wrist, bringing the elbow in or away from the body. This angle modifies the amount of space taken up by the gesture and can change the perceived personality [33] and has been postulated to relate to humility and arrogance [32]. ...
Gesture behavior is a natural part of human conversation. Much work has focused on removing the need for tedious hand-animation to create embodied conversational agents by designing speech-driven gesture generators. However, these generators often work in a black-box manner, assuming a general relationship between input speech and output motion. As their success remains limited, we investigate in more detail how speech may relate to different aspects of gesture motion. We determine a number of parameters characterizing gesture, such as speed and gesture size, and explore their relationship to the speech signal in a two-fold manner. First, we train multiple recurrent networks to predict the gesture parameters from speech to understand how well gesture attributes can be modeled from speech alone. We find that gesture parameters can be partially predicted from speech, and some parameters, such as path length, being predicted more accurately than others, like velocity. Second, we design a perceptual study to assess the importance of each gesture parameter for producing motion that people perceive as appropriate for the speech. Results show that a degradation in any parameter was viewed negatively, but some changes, such as hand shape, are more impactful than others. A video summarization can be found at https://youtu.be/aw6-_5kmLjY.
... Virtual characters can adopt these cues to express different personalities [7]; using different modalities expressively contributes to different personality factors [8]. Among different communication elements, body movement is essential in controlling perceived personality [9,10]. The traditional way of adding personality to human motion is through carefully inspected procedural animation modifications. ...
Personality is the individual's interrelated behavioral and emotional patterns that form the unique self. Personality-enriched animations benefit digital characters, which helps improve realism and communication. Body movements, among other modalities, can include strong cues for personality expression. We focus on altering the body movements of human animation to express the desired personality traits following two approaches: (i) a traditional approach that utilizes handcrafted motion adjustments following heuristic rules and (ii) a data-driven approach that separates content and personality into different latent spaces to reconstruct the same motion with altered personality. While the sample size does not affect the traditional approach, the scarcity of personality-labeled animation datasets prevents using sophisticated data-driven models; to this end, we utilize Neural Motion Fields (NeMF) in our data-driven personality transfer architecture. We evaluate the performance of the two approaches through a three-part user study; different models stand out for altering specific personality factors.
... McDonnell et al. [46] investigated the influence of body shape on emotion identification, finding it to be largely unaffected by variations in body shape. Smith and Neff [77] examined how editing gestures in ways similar to motion warping affects the perceived personality of a character, revealing that altering the properties of plasticity and stability in gestures can independently influence perceptions of the character's stability and adaptability. ...
... Although several works exist e.g. [67][68][69] that talk about the process of mapping these animations based on psychological rules like nodding on agreement [70] or sad emotion for apology [71], only a few studies [72] have focused on automatically mapping these animations to their corresponding intent. ...
Virtual human heads are digital representations of existing or synthetic human heads, capable of exhibiting realistic behavior. They are generated, modelled, animated and rendered using a combination of computer vision, computer graphics, and AI methodologies. Virtual human heads are a crucial component in applications and research on fields such as healthcare, human-computer interactions, gaming, VFX, AR & VR,social studies and data privacy. Recent advancements in generative vision models have progressed the generation and manipulation of realistic and effective virtual human heads. Despite the growing interest in these topics, there are limitations and research gaps in the current body of work, that require innovative and effective solutions.
In our work, we address some of the relevant research questions in the realm of virtual human heads, leveraging the capabilities of some of the latest generative vision models. First, we perform an extensive review of some of the traditional and modern approaches in generating realistic behavior and appearance in virtual humans, and perform a comparative study among them. We address the challenges and open research questions in the domain of virtual human heads, and thus lay the foundation for our subsequent contributions. One such contribution involves proposing a method to perform manipulation of semantic features on albedo UV map of 3D virtual heads. We discuss the effectivity of this approach and show its potential significance in creating and editing diverse appearances of virtual humans in fields such as gaming, and AR/VR. Finally, we address the critical task of face de-identification in videos. We investigate some of v the key requirements of successful privacy preserving de-identified videos, and propose a novel pipeline to achieve the results, and also evaluate them on suitable quantified metrics.
Through this thesis, we investigate, discuss and address some of the relevant and important problem statements persisting in the realm of virtual human heads using generative vision models. We aim to advance the understanding and practical applications in this area, and pave the way for future research work for safe, realistic and diverse digital human representations and interactions.
... To address the ambiguity of the generated motions, many studies have attempted to control the style of the generated motions. Research has shown that the statistical properties of movement, such as gesture height, velocity, and spatial extent, are significantly correlated with perceptions of the "big five" personality traits [24,25] and emotions [26]. Some studies have considered transferring style attributes from existing records to a target motion to modify the motion expression [27][28][29]. ...
Body language is a method for communicating across languages and cultures. Making good use of body motions in speech can enhance persuasiveness, improve personal charisma, and make speech more effective. Generating matching body motions for digital avatars and social robots based on content has become an important topic. In this paper, we propose a transformer-based network model to generate body motions from input speech. Our model includes an audio transformer encoder, motion transformer encoder, template variational autoencoder, cross-modal transformer encoder, and motion decoder. Additionally, we propose a novel evaluation metric for describing motion change trends in terms of distance. The experimental results show that the proposed model provides higher-quality motion generation results than state-of-the-art models. As indicated by visual skeleton motions, our results are more natural and realistic than those of other methods. Additionally, the generated motions yield superior results in terms of multiple evaluation metrics.
... Literature [13] created a boundary volume hierarchy optimized for all frames of the corresponding animated scene that can handle highly complex inputs with large deformations and significant topology changes, and the results show that this architecture runs much better than the traditional ones. Literature [14] identifies gestures as a key component of social communication and analyzes how gesture editing affects a character's perceived personality, deepening the understanding of gesture control on personality perception and suggesting the potential of motion editing methods. Literature [15] captures movements in the form of motion recording data to synchronize them with the animated character, uses Kinect to capture the actor's movements, adapts the articulated body character points to the body frame, and gives them visual effects. ...
The development of artificial intelligence technology has become an important trend today and also provides rich means for the development of the animation industry. In this paper, a three-dimensional skeleton extraction model is first proposed through skeletal coordinate transformation, and then a skin deformation technique based on LBS linear hybrid skinning technology is introduced to complete the construction of the character animation generation algorithm. On this basis, a statistical-based scene layout template generation algorithm is proposed to extract spatial relationships in the corpus using the spatial semantic information extraction method and calculate the occurrence probability of objects so as to realize the generation of animated scenes. The PSNR and SSIM scores of the new model have improved by 6.3 and 0.53 points, respectively, when compared to the old model. The recognition accuracy of the latest model reaches 99.6% at a 15° rotation angle and 97.9% at a 30° rotation angle. The average score of the audience for the AIGC-enabled animation scenes is 7.5, which is satisfactory in general. The AIGC-enabled animation character characterization and narrative scene generation have been found to have acceptable results.
... Previous research suggests that personality expression in motion is related to the interaction between different joints rather than the movements of individual joints [27]. For example, the linear distance between the hands can better reflect extraversion than the individual rotations of both hands, arms, and shoulders. ...
... Kiiski et al. [35] examined that visual information of human body motion has relation with social traits and intention perception, and also the human motion features can be used for social intention prediction. Akin to these works, many researchers [36][37][38] have also investigated the connection between motion style and personality perceptions. To conduct motion style transfer, i.e., transferring the motion style from one motion sequence to another, while holding the motion content of the latter, many researchers have exploited many tools, like linear time-invariant model [39] and Gaussian process model [40], to proceed with this problem. ...
Motion style transfer, which aims to transfer the style from a source motion to the target while keeping its content, has recently gained considerable attention. Some existing works have shown promising results but required labeled data for supervised training, limiting their applicability. In this paper, we present a novel self-supervised learning method for motion style transfer. Specifically, we cast the problem into a contrastive learning framework, which disentangles the human motion representation into a content code and a style code, and the result can be generated by compositing the style code of source motion and the content code of target motion. To encourage better code disentanglement and composition, we investigate InfoNCE loss and Triplet loss in a self-supervised manner. This framework aims at generating reasonable motions while guaranteeing the disentanglement of the latent codes. Comprehensive experiments have been conducted over the benchmark datasets and demonstrated our superior performance over state-of-the-art methods.
... The results indicate that the digital human with co-speech gestures generated by the proposed method was perceived more natural, more human-like, more temporally and semantically consistent, and more socially present than the digital human without co-speech gestures or with co-speech gestures generated by the previous counterpart [3]. The fact that the existence of co-speech gestures helps digital human to look more alive and engaging has been supported by numerous studies [41][42][43][44]. Our results align with existing studies, emphasizing the significance of naturalness and human-likeness in perceptions of digital humans. ...
In this study, we explore the effects of co-speech gesture generation on user experience in 3D digital human interaction by testing two key hypotheses. The first hypothesis posits that increasing the number of gestures enhances the user experience across criteria such as naturalness, human-likeness, temporal consistency, semantic consistency, and social presence. The second hypothesis suggests that language translation does not degrade the user experience across these criteria. To explore these hypotheses, we investigated three conditions using a digital human: voice only with no gestures, limited(56 gestures) co-speech gestures, and full system functionality with over 2000 unique gestures. For the second hypothesis, we used language translation to provide multilingual support, retrieving gestures from an English rule base. We obtained text and pose from English videos and matched the pose with gesture units derived from Korean speakers' motion-capture sequences, enhancing a comprehensive rule base that we used for gesture retrieval for given text input. We used translation of non-English input language to English for text matching. Our novel method utilizes an improved pipeline to extract text, 2D pose data, and 3D gesture units. Incorporating a cutting-edge gesture-pose matching model with deep contrastive learning, we retrieved gestures from a comprehensive rule base containing 210,000 rules. This approach optimizes alignment and generates realistic, semantically consistent co-speech gestures adaptable to various languages. A comprehensive user study evaluated our hypotheses. The results underscored the positive impact of diverse gestures, supporting the first hypothesis. Additionally, multilingual capabilities did not degrade the user experience, confirming the second hypothesis. Highlighting the scalability and flexibility of our method, this study provides valuable insights into cross-lingual data and expert systems for gesture generation, contributing significantly to more engaging and immersive digital human interactions and the broader field of human-computer interaction.
... 5 Consequently, motion capture animation datasets are more suitable for movement analysis. 27 To this end, a common approach is to label atomic animations with apparent personality traits via crowd sourcing. 8 While we can observe human-like traits in animals and apply human personality theories to other species using modifications, 12 a standard questionnaire for measuring animal personality is lacking. ...
The movement style is an adequate descriptor of different personalities. While many studies investigate the relationship between apparent personality and high‐level motion qualities in humans, similar research for animal characters still needs to be done. The variety in animals' skeletal configurations and texture complicates their pose estimation process. Our affect analysis framework includes a workflow for pose extraction in animal characters and a parameterization of the high‐level animal motion descriptors inspired by Laban movement analysis. Using a data set of quadruped walk cycles, we prove the display of typologies in cartoon animal characters, reporting the point‐biserial correlation between our motion parameters and the Sasang categories that reflect different personalities.
... The gesture synthesis method [DKD * 16] generates animations by embedding a gesture personality feature into a fivedimensional space, called OCEAN [CM92], and 39 variables were introduced to control styles whose values were determined using multivariate regressions. Smith and Neff [SN17] compressed this five-dimensional space into two dimensions by reflecting a cognitive aspect, thus enabling a more efficient classification of gestural styles. These model-based approaches can control time-dependent features using a timing control function with key poses. ...
Gestural animations in the amusement or entertainment field often require rich expressions; however, it is still challenging to synthesize characteristic gestures automatically. Although style transfer based on a neural network model is a potential solution, existing methods mainly focus on cyclic motions such as gaits and require re‐training in adding new motion styles. Moreover, their per‐pose transformation cannot consider the time‐dependent features, and therefore motion styles of different periods and timings are difficult to be transferred. This limitation is fatal for the gestural motions requiring complicated time alignment due to the variety of exaggerated or intentionally performed behaviors.
This study introduces a context‐based style transfer of gestural motions with neural networks to ensure stable conversion even for exaggerated, dynamically complicated gestures. We present a model based on a vision transformer for transferring gestures' content and style features by time‐segmenting them to compose tokens in a latent space. We extend this model to yield the probability of swapping gestures' tokens for style‐transferring. A transformer model is suited to semantically consistent matching among gesture tokens, owing to the correlation with spoken words. The compact architecture of our network model requires only a small number of parameters and computational costs, which is suitable for real‐time applications with an ordinary device.
We introduce loss functions provided by the restoration error of identically and cyclically transferred gesture tokens and the similarity losses of content and style evaluated by splicing features inside the transformer. This design of losses allows unsupervised and zero‐shot learning, by which the scalability for motion data is obtained.
We comparatively evaluated our style transfer method, mainly focusing on expressive gestures using our dataset captured for various scenarios and styles by introducing new error metrics tailored for gestures. Our experiment showed the superiority of our method in numerical accuracy and stability of style transfer against the existing methods.
... It is important to be able to drive these emotions in a way that is consistent with a character's personality and to be able to shift mood and emotion over time. One way forward might be to leverage findings from the literature of gesture and motion perception, which has identified many useful properties of gesture motion that correlate with the perception of personality [Lip98, KG10,SN17] and emotion [NLK * 13,CN19]. By changing these properties in synthesized gestures, we may exert some control over the perceived speaker personality and emotion [AHKB20, HES * 22]. ...
Gestures that accompany speech are an essential part of natural and efficient embodied human communication. The automatic generation of such co-speech gestures is a long-standing problem in computer animation and is considered an enabling technology in film, games, virtual social spaces, and for interaction with social robots. The problem is made challenging by the idiosyncratic and non-periodic nature of human co-speech gesture motion, and by the great diversity of communicative functions that gestures encompass. Gesture generation has seen surging interest recently, owing to the emergence of more and larger datasets of human gesture motion, combined with strides in deep-learning-based generative models, that benefit from the growing availability of data. This review article summarizes co-speech gesture generation research, with a particular focus on deep generative models. First, we articulate the theory describing human gesticulation and how it complements speech. Next, we briefly discuss rule-based and classical statistical gesture synthesis, before delving into deep learning approaches. We employ the choice of input modalities as an organizing principle, examining systems that generate gestures from audio, text, and non-linguistic input. We also chronicle the evolution of the related training data sets in terms of size, diversity, motion quality, and collection method. Finally, we identify key research challenges in gesture generation, including data availability and quality; producing human-like motion; grounding the gesture in the co-occurring speech in interaction with other speakers, and in the environment; performing gesture evaluation; and integration of gesture synthesis into applications. We highlight recent approaches to tackling the various key challenges, as well as the limitations of these approaches, and point toward areas of future development.
... Automatic gesture generation makes for more lifelike and engaging artificial agents [85]. It can also aid learning [76] and can communicate social information such as personality [22,72,88], and emotion [12,28,75]. Early work in gesture generation focussed on rule-based approaches [11,53,61,63] that typically would play pre-recorded gesture clips (or "lexemes"), at timings selected by handcrafted rules; see [103] for a review. ...
Diffusion models have experienced a surge of interest as highly expressive yet efficiently trainable probabilistic models. We show that these models are an excellent fit for synthesising human motion that co-occurs with audio, for example co-speech gesticulation, since motion is complex and highly ambiguous given audio, calling for a probabilistic description. Specifically, we adapt the DiffWave architecture to model 3D pose sequences, putting Conformers in place of dilated convolutions for improved accuracy. We also demonstrate control over motion style, using classifier-free guidance to adjust the strength of the stylistic expression. Gesture-generation experiments on the Trinity Speech-Gesture and ZeroEGGS datasets confirm that the proposed method achieves top-of-the-line motion quality, with distinctive styles whose expression can be made more or less pronounced. We also synthesise dance motion and path-driven locomotion using the same model architecture. Finally, we extend the guidance procedure to perform style interpolation in a manner that is appealing for synthesis tasks and has connections to product-of-experts models, a contribution we believe is of independent interest. Video examples are available at https://www.speech.kth.se/research/listen-denoise-action/
... In study 2, the findings from study 1 were extended by including consumer implications in order to demonstrate the downstream consequences of the use of animation in pharmaceutical advertisements. Smith and Neff [9] have investigated the influence of animated gestures in controlling personality perception. A sequence of four diverse gestures with twelve motion adjustments was selected as stimuli for the study. ...
Animation is an excellent method to associate with the audience in a fun and innovative manner. In recent span, animation has been employed in various fields to enhance knowledge, marketing, advertisement, and age groups from infants to adults. The present communication expounds the systematic review on the impact created by animation on the viewer’s visual attention. For this review, a database such as Google Scholar, ScienceDirect, Taylor & Francis, and IEEE Xplore were pursued for publications on the impact of animation on viewer’s visual attention from January 2015 to December 2021. The search results showcased 175 titles with 114 full articles, out of which 35 were related to viewers’ visual attention towards animation. These reviewed studies comprised of physical outcome ( n = 9 ), psychological outcome ( n = 15 ), and cognitive outcome ( n = 11 ) from which the attention-related factors, physical effects, and cognitive effects of animation were assessed. The animation has influenced the viewer’s visual attention through the integration of the different stimuli and the highly organized presentation. Furthermore, the animation has also aided the viewer in attaining greater conceptual understanding, thereby facilitating their cognitive response. As a result, the animation was found to be helpful in enhancing learning skills, food marketing, and teaching strategy. Furthermore, the drawbacks and future recommendations of the studies were elaborated. In addition, challenges and open issues faced during the studies were discussed. Finally, the priority areas in animation identified for promising future directions to visualize large pool data, provide smart communication, and design 3D modeling structures were highlighted.
... These impressions can be based on just a few seconds of observing the other's appearance and (non-)verbal behavior such as facial expressions and gestures [6][7][8][9]. Effects of virtual human behaviour on perception of agent personality and interpersonal attitudes have been investigated in perceptual studies (properties of gestures [10,11] with language [12,13] on personality, posture [14] on emotion, gaze and proxemic behaviors on interpersonal attitudes [15]) as well as in studies focusing on impression shaped during first encounters with virtual characters [16]. Besides the appearance (e.g., hair colour, height), the fact that the MEB is physically embodied by a human makes it different from the VH on a screen. ...
In this paper we present a Multimodal Echoborg interface to explore the effect of different embodiments of an Embodied Conversational Agent (ECA) in an interaction. We compared an interaction where the ECA was embodied as a virtual human (VH) with one where it was embodied as an Echoborg, i.e, a person whose actions are covertly controlled by a dialogue system. The Echoborg in our study not only shadowed the speech output of the dialogue system but also its non-verbal actions. The interactions were structured as a debate between three participants on an ethical dilemma. First, we collected a corpus of debate sessions with three humans debaters. This we used as baseline to design and implement our ECAs. For the experiment, we designed two debate conditions. In one the participant interacted with two ECAs both embodied by virtual humans). In the other the participant interacted with one ECA embodied by a VH and the other by an Echoborg. Our results show that a human embodiment of the ECA overall scores better on perceived social attributes of the ECA. In many other respects the Echoborg scores as poorly as the VH except copresence .
... In future work, we want to explore how personality perceptions are impacted by agent design. Personality design is a critical factor for virtual agents [25], and has been show to be influenced by the agent's verbal behavior [17,52], gesture [46], and appearance [33]. ...
... Studies in [McDonnell et al. 2008] confirmed that motion provides reliable emotional cues that are unaffected by a character's appearance. Perceptual experiments in [Neff et al. 2010;Smith and Neff 2017;Wang et al. 2016] indicate that low-level motion features such as direction, amplitude, speed, frequency, and general posture significantly impact the perceived personality of the performer. Thus, procedurally modifying these key motion features can effectively generate different styles of motions. ...
Style is an intrinsic, inescapable part of human motion. It complements the content of motion to convey meaning, mood, and personality. Existing state-of-the-art motion style methods require large quantities of example data and intensive computational resources at runtime. To ensure output quality, such style transfer applications are often run on desktop machine with GPUs and significant memory. In this paper, we present a fast and expressive neural network-based motion style transfer method that generates stylized motion with quality comparable to the state of the art method, but uses much less computational power and a much smaller memory footprint. Our method also allows the output to be adjusted in a latent style space, something not offered in previous approaches. Our style transfer model is implemented using three multi-layered networks: a pose network, a timing network and a foot-contact network. A one-hot style vector serves as an input control knob and determines the stylistic output of these networks. During training, the networks are trained with a large motion capture database containing heterogeneous actions and various styles. Joint information vectors together with one-hot style vectors are extracted from motion data and fed to the networks. Once the network has been trained, the database is no longer needed on the device, thus removing the large memory requirement of previous motion style methods. At runtime, our model takes novel input and allows real-valued numbers to be specified in the style vector, which can be used for interpolation, extrapolation or mixing of styles. With much lower memory and computational requirements, our networks are efficient and fast enough for real-time use on mobile devices. Requiring no information about future states, the style transfer can be performed in an online fashion. We validate our result both quantitatively and perceptually, confirming its effectiveness and improvement over previous approaches.
We express our personality through verbal and nonverbal behavior. While verbal cues are mostly related to the semantics of what we say, nonverbal cues include our posture, gestures, and facial expressions. Appropriate expression of these behavioral elements improves conversational virtual agents’ communication capabilities and realism. Although previous studies focus on co-speech gesture generation, they do not consider the personality aspect of the synthesized animations. We show that automatically generated co-speech gestures naturally express personality traits, and heuristics-based adjustments for such animations can further improve personality expression. To this end, we present a framework for enhancing co-speech gestures with the different personalities of the Five-Factor model. Our experiments suggest that users perceive increased realism and improved personality expression when combining heuristics-based motion adjustments with co-speech gestures.
Virtual humans with realistic behaviors have become prominent actors of compelling virtual experiences in domains as diverse as entertainment, education, and healthcare. A significant factor contributing to their behavioral realism is their personality, which characterizes distinctive traits consistent over time. Virtual humans can express personality traits through various channels such as voice, face, or body. In this chapter, we will focus on how emotional expression through facial expressions and body pose affect the communication of virtual human personalities. Throughout the chapter, we refer to the five-factor model of personality, which consists of five orthogonal dimensions of openness, conscientiousness, extroversion, agreeableness, and neuroticism. We will investigate their representation through the expression of the basic emotions of happiness, sadness, fear, anger, and disgust.
Static postures and body movements influence interactions. Mirroring promotes bonds, but rapport building depends more on other factors. The openness of postures may signal mental and emotional states. A controversial experiment even suggested that a “superhero” pose might improve confidence, charisma, and performance. Gestures and gait are other sources of information. Nevertheless, hand movements mainly accompany speaking, and humans are typically poor decoders of the walking style. Automatic tools, particularly those used for identification recognition, have a higher degree of accuracy. Individual chronicity influences nonverbal behavior, emotions, and performance, but several factors determine observers’ inferences. Job interviews highlight the inherent challenge of decoding people only from nonverbal clues. Interviewers can underrate some cues and overestimate other ones.
Diffusion models have experienced a surge of interest as highly expressive yet efficiently trainable probabilistic models. We show that these models are an excellent fit for synthesising human motion that co-occurs with audio, e.g., dancing and co-speech gesticulation, since motion is complex and highly ambiguous given audio, calling for a probabilistic description. Specifically, we adapt the DiffWave architecture to model 3D pose sequences, putting Conformers in place of dilated convolutions for improved modelling power. We also demonstrate control over motion style, using classifier-free guidance to adjust the strength of the stylistic expression. Experiments on gesture and dance generation confirm that the proposed method achieves top-of-the-line motion quality, with distinctive styles whose expression can be made more or less pronounced. We also synthesise path-driven locomotion using the same model architecture. Finally, we generalise the guidance procedure to obtain product-of-expert ensembles of diffusion models and demonstrate how these may be used for, e.g., style interpolation, a contribution we believe is of independent interest.
With recent technological advancements, many firms that formerly relied on traditional face-to-face conversations have switched to an online conversation mode. This has not only helped businesses to increase their revenues, but it has also enabled users and customers to access world-class services. Due to scalability concerns with these platforms, many of the online conversations have lost the personal touch associated with a face-to-face based communication. An embodied conversational agent (ECA) can address this void by creating suitable behavior as well as the required voice output via a realistic-looking avatar. However, in order to scale up to a large customer base, the behavior and appearance of agents must be adequately modeled. Traditionally, rule-based methods were used to generate the animations associated with the avatars, but because of their limitations modern approaches use deep learning models to create end-to-end systems. We present various conventional and current methodologies for behavior and appearance modeling in our work. We will discuss similarities between these systems as well as their limitations. We believe that our work will be useful in developing a hybrid system that uses both traditional and modern approach to handle these challenges in creating modern embodied conversational agents.
The concept of androgynous or gender-neutral fashion is known for its distinctive attribute that blends both conventional masculine and feminine design characteristics. In the history of fashion, the notion of androgynous fashion has been evolving since the 1920s, although it was irregular at times. In the postmodern Western cultures, androgynous aesthetic in fashion is increasingly accepted, encouraging the multiplicity of gender expressions. With significant influencers of the generation identifying themselves as gender-neutral and speaking out on the topic, the concept of being gender fluid is catching a lot of attention recently in the international fashion industry. Androgynous fashion is an emergent trend, which reflects in fashion ramps with models showcasing silhouettes and design elements that breakdown gender stereotypes. With this in mind, the current research aims to study androgynous fashion from both conceptual and user-centric perspectives in the Indian context. Data were collected through primary and secondary sources. Relevant secondary data were gathered from various books, research papers and fashion publications to set the conceptual context of the research. Additionally, to gather primary information about the Indian LGBTQ consumers’ perception of androgynous fashion, a questionnaire was circulated amongst young Indian fashion consumers using convenience and snowball sampling methods. The results and analysis of the study reveal the aspirations behind the gender-neutral design genre. This study also brings out the emotional needs of the Indian LGBTQ community members, who are the primary consumers of androgynous aesthetic.
Consistently exhibited personalities are crucial elements of realistic, engaging, and behavior-rich conversational virtual agents. Both nonverbal and verbal cues help convey these agents’ unseen psychological states, contributing to our effective communication with them. We introduce a comprehensive framework to design conversational agents that express personality through non-verbal behaviors like body movement and facial expressions, as well as verbal behaviors like dialogue selection and voice transformation. We use the OCEAN personality model, which defines personality as a combination of five orthogonal factors of openness, conscientiousness, extraversion, agreeableness, and neuroticism. The framework combines existing personality expression methods with novel ones such as new algorithms to convey Laban Shape and Effort qualities. We perform Amazon Mechanical Turk studies to analyze how different communication modalities influence our perception of virtual agent personalities and compare their individual and combined effects on each personality dimension. The results indicate that our personality-based modifications are perceived as natural, and each additional modality improves perception accuracy, with the best performance achieved when all the modalities are present. We also report some correlations for the perception of conscientiousness with neuroticism and openness with extraversion.
Automatic synthesis of realistic gestures promises to transform the fields of animation, avatars and communicative agents. In off‐line applications, novel tools can alter the role of an animator to that of a director, who provides only high‐level input for the desired animation; a learned network then translates these instructions into an appropriate sequence of body poses. In interactive scenarios, systems for generating natural animations on the fly are key to achieving believable and relatable characters. In this paper we address some of the core issues towards these ends. By adapting a deep learning‐based motion synthesis method called MoGlow, we propose a new generative model for generating state‐of‐the‐art realistic speech‐driven gesticulation. Owing to the probabilistic nature of the approach, our model can produce a battery of different, yet plausible, gestures given the same input speech signal. Just like humans, this gives a rich natural variation of motion. We additionally demonstrate the ability to exert directorial control over the output style, such as gesture level, speed, symmetry and spacial extent. Such control can be leveraged to convey a desired character personality or mood. We achieve all this without any manual annotation of the data. User studies evaluating upper‐body gesticulation confirm that the generated motions are natural and well match the input speech. Our method scores above all prior systems and baselines on these measures, and comes close to the ratings of the original recorded motions. We furthermore find that we can accurately control gesticulation styles without unnecessarily compromising perceived naturalness. Finally, we also demonstrate an application of the same method to full‐body gesticulation, including the synthesis of stepping motion and stance.
This research examined the effects of personality/social skills and individual differences in expressive style on impression formation. Particular attention was given to the role of nonverbal behaviors in the formation of initial impressions. Sixty-two subjects were measured on self-report personality and communication skill scales, on posed emotional sending ability, and on physical attractiveness. Subjects were then videotaped while giving a spontaneous “explanation.” Trained coders measured five separate nonverbal cue factors displayed by the subjects in the videotapes. Groups of untrained judges viewed the tapes and rated their impressions of the subjects on scales of likability, speaking effectiveness, and expressivity-confidence. Male subjects who were nonverbally skilled and extraverted tended to display more outwardly focused and fluid expressive behaviors, and made more favorable impressions on judges, than did males who scored low on the measures of nonverbal skills and extraversion. Females who were nonverbally skilled displayed more facial expressiveness, which led to more favorable initial impressions. Sex differences may reflect basic differences in the acquisition and use of expressive nonverbal cues by males and females.
The performance of five methods for determining the number of components to retain (Horn's parallel analysis, Velicer's minimum average partial [MAP], Cattell's scree test, Bartlett's chi-square test, and Kaiser's eigenvalue greater than 1.0 rule) was investigated across seven systematically varied conditions (sample size, number of variables, number of components, component saturation, equal or unequal numbers of variables per component, and the presence or absence of unique and complex variables). We generated five sample correlation matrices at each of two sample sizes from the 48 known population correlation matrices representing six levels of component pattern complexity. The performance of the parallel analysis and MAP methods was generally the best across all situations. The scree test was generally accurate but variable. Bartlett's chi-square test was less accurate and more variable than the scree test. Kaiser's method tended to severely overestimate the number of components. We discuss recommendations concerning the conditions under which each of the methods are accurate, along with the most effective and useful methods combinations.
Virtual sport coaches guide users through their physical activity and provide motivational support. Users’ motivation can rapidly decay if the movements of the virtual coach are too stereotyped. Kinematics patterns generated while performing a predefined fitness movement can elicit and help to prolong users’ interaction and interest in training. Human body kinematics has been shown to convey various social attributes such as gender, identity and acted emotions. To date, no study provides information regarding how spontaneous emotions and personality traits together are perceived from full-body movements. In this paper, we study how people make reliable inferences regarding spontaneous emotional dimensions and personality traits of human coaches from kinematic patterns they produced when performing a fitness sequence. Movements were presented to participants via a virtual mannequin to isolate the influence of kinematics on perception. Kinematic patterns of biological movement were analyzed in terms of movement qualities according to the effort-shape [Dell 1977] notation proposed by [Laban 1950]. Three studies were performed to provide an analysis of the process leading to perception: from coaches’ states and traits through bodily movements
to observers’ social perception. Thirty-two participants (i.e., observers) were asked to rate the movements of the virtual mannequin in terms of conveyed emotion dimensions, personality traits (five-factor model of personality) and perceived movement qualities (effort-shape) from 56 fitness movement sequences. The results showed high reliability for most of the evaluated dimensions, confirming inter-observer agreement from kinematics at zero acquaintance. A large expressive halo merging emotional (e.g., perceived intensity) and personality aspects (e.g., extraversion) was found, driven by perceived kinematic impulsivity and energy. Observers’ perceptions were partially accurate for emotion dimensions and were not accurate for personality traits. Together, these results contribute to both the understanding of dimensions of social perception through
movement, but also to the design of expressive virtual sport coaches.
Personality can be assessed with standardized inventory questions with scaled responses such as "How extraverted is this character?" or with open-ended questions assessing first impressions, such as "What personality does this character convey?" Little is known about how the two methods compare to each other, and even less is known about their use in the personality assessment of virtual agents. We tested what personality virtual agents conveyed through gesture alone when the agents were programmed to display introversion versus extraversion (Experiment 1) and high versus low emotional stability (Experiment 2). In Experiment 1, both measures indicated participants perceived the extraverted agent as extraverted, but the open-question technique highlighted the perception of both agents as highly agreeable whereas the inventory indicated that the extraverted agents were also perceived as more open to new experiences. In Experiment 2, participants perceived agents expressing high versus low emotional stability differently depending on assessment style. With inventory questions, the agents differed on both emotional stability and agreeableness. With the open-ended question, participants perceived the high stability agent as extraverted and the low stability agent as disagreeable. Inventory and open-ended questions provide different information about what personality virtual agents convey and both may be useful in agent development.
Recent advances in rendering and data-driven animation have enabled the creation of compelling characters with impressive levels of realism. While data-driven techniques can produce animations that are extremely faithful to the original motion, many challenging problems remain because of the high complexity of human motion. A better understanding of the factors that make human motion recognizable and appealing would be of great value in industries where creating a variety of appealing virtual characters with realistic motion is required. To investigate these issues, we captured thirty actors walking, jogging and dancing, and applied their motions to the same virtual character (one each for the males and females). We then conducted a series of perceptual experiments to explore the distinctiveness and attractiveness of these human motions, and whether characteristic motion features transfer across an individual's different gaits. Average faces are perceived to be less distinctive but more attractive, so we explored whether this was also true for body motion. We found that dancing motions were most easily recognized and that distinctiveness in one gait does not predict how recognizable the same actor is when performing a different motion. As hypothesized, average motions were always amongst the least distinctive and most attractive. Furthermore, as 50% of participants in the experiment were Caucasian European and 50% were Asian Korean, we found that the latter were as good as or better at recognizing the motions of the Caucasian actors than their European counterparts, in particular for dancing males, whom they also rated more highly for attractiveness.
Bodily expression of affect is crucial to human robot interaction. We distinguish between emotion and mood expression, and focus on mood expression. Bodily expression of an emotion is explicit behavior that typically interrupts ongoing functional behavior. Instead, bodily mood expression is integrated with functional behaviors without interrupting them. We propose a parameterized behavior model with specific behavior parameters for bodily mood expression. Robot mood controls pose and motion parameters, while those parameters modulate behavior appearance. We applied the model to two concrete behaviors — waving and pointing — of the NAO robot, and conducted a user study in which participants (N=24) were asked to design the expression of positive, neutral, and negative moods by modulating the parameters of the two behaviors. Results show that participants created different parameter settings corresponding with different moods, and the settings were generally consistent across participants. Various parameter settings were also found to be behavior-invariant. These findings suggest that our model and parameter set are promising for expressing moods in a variety of behaviors.
Better understanding of how social traits and intentions are conveyed through human body motion is central in creating believable, life-like virtual characters. Body motion conveys socially relevant information on which people make judgments, such as other people's personality or gender. [e.g. Koppensteiner and Grammer 2011, Thoresen et al. 2012]. However, it is unclear how the body motion features are related to the perceived social traits and intentions of others. The main goal of this study is to examine how visual information from human body motion is related to social traits and intention perception. Furthermore, we also investigated if body motion features can be used as predictors of social intentions.
Crowdsourcing is used to obtain relevance judgments for query-document pairs. To obtain accurate judgments, each query-document pair is judged by several workers. Consensus is usually obtained by majority voting and spam most commonly reduced by injecting gold set questions. This study puts the performance of gold sets and majority voting to the test. Based on the analysis of crowdsourcing results for a relevance judgment task, we propose an alternative to reduce spam and increase accuracy. Simulations were used to compare performance between different algorithms, inspecting accuracy and costs for different experimental settings. The results show that gold sets and majority voting are less spam-resistant than many believe and can easily be outperformed.
The question of the relationship between verbal and nonverbal behaviours is addressed from the point of view of the effects that these behaviours have on judgments that participants and observers make about persons enacting these behaviours. Behaviours that produce similar judgments may be said to have similar functions or meanings. Literature relevant to the effects of various verbal and nonverbal behaviours on judgments of control and affiliation is summarised. The theoretical implications of this work are examined in the areas of participant vs observer judgments, judgmental heuristics and rules of combination.
In the 45 years since Cattell used English trait terms to begin the formulation of his “description of personality,” a number of investigators have proposed an alternative structure based on 5 orthogonal factors. The generality of this 5-factor model is here demonstrated across unusally comprehensive sets of trait terms. In the first 3 studies, 1,431 trait adjectives grouped into 75 clusters were analyzed; virtually identical structures emerged in 10 replications, each based on a different factor-analytic procedure. A 2nd study of 479 common terms grouped into 133 synonym clusters revealed the same structure in 2 samples of self-ratings and in 2 samples of peer ratings. None of the factors beyond the 5th generalized across the samples. In the 3rd study, analyses of 100 clusters derived from 339 triat terms suggest their potential utility as Big-Five markers in future studies.
Gesture, or visible bodily action that is seen as intimately involved in the activity of speaking, has long fascinated scholars and laymen alike. Written by a leading authority on the subject, this 2004 study provides a comprehensive treatment of gesture and its use in interaction, drawing on the analysis of everyday conversations to demonstrate its varied role in the construction of utterances. Adam Kendon accompanies his analyses with an extended discussion of the history of the study of gesture - a topic not dealt with in any previous publication - as well as exploring the relationship between gesture and sign language, and how the use of gesture varies according to cultural and language differences. Set to become the definitive account of the topic, Gesture will be invaluable to all those interested in human communication. Its publication marks a major development, both in semiotics and in the emerging field of gesture studies.
In order to analyze the emotional content of motions portrayed by different characters, we created real and virtual replicas of an actor exhibiting six basic emotions: sadness, happiness, surprise, fear, anger, and disgust. In addition to the video of the real actor, his actions were applied to five virtual body shapes: a low- and high-resolution virtual counterpart, a cartoon-like character, a wooden mannequin, and a zombie-like character (Figures 1 and 2). In a point light condition, we also tested whether the absence of a body affected the perceived emotion of the movements. Participants were asked to rate the actions based on a list of 41 more complex emotions. We found that the perception of emotional actions is highly robust and to the most part independent of the character's body, so long as form is present. When motion alone is present, emotions were generally perceived as less intense than in the cases where form was present.
Investigated the performance of 5 methods for determining the number of components to retain—J. L. Horn's (see record 1965-13273-001 ) parallel analysis, W. F. Velicer's (see record 1977-00166-001 ) minimum average partial (MAP), R. B. Cattell's (see PA, Vol 41:969) scree test, M. S. Bartlett's (1950) chi-square test, and H. F. Kaiser's (see record 1960-06772-001 ) eigenvalue greater than 1 rule—across 7 systematically varied conditions (sample size, number of variables, number of components, component saturation, equal or unequal numbers of variables for each component, and the presence or absence of unique and complex variables). Five sample correlation matrices were generated at each of 2 sample sizes from the 48 known population correlation matrices representing 6 levels of component pattern complexity. Results indicate that the performance of the parallel analysis and MAP methods was generally the best across all situations; the scree test was generally accurate but variable; and Bartlett's chi-square test was less accurate and more variable than the scree test. Kaiser's method tended to severely overestimate the number of components. (65 ref)
The five-factor model has recently received wide attention as a comprehensive model of personality traits. The claim that these five factors represent basic dimensions of personality is based on four lines of reasoning and evidence: (a) longitudinal and cross-observer studies demonstrate that all five factors are enduring dispositions that are manifest in patterns of behavior; (b) traits related to each of the factors are found in a variety of personality systems and in the natural language of trait description; (c) the factors are found in different age, sex, race, and language groups, although they may be somewhat differently expressed in different cultures; and (d) evidence of heritability suggests that all have some biological basis. To clarify some remaining confusions about the five-factor model, the relation between Openness and psychometric intelligence is described, and problems in factor rotation are discussed.
This article reports results from a program that produces high-quality animation of facial expressions and head movements as automatically as possible in conjunction with meaning-based speech synthesis, including spoken intonation. The goal of the research is as much to test and define our theories of the formal semantics for such gestures, as to produce convincing animation. Towards this end, we have produced a high-level programming language for three-dimensional (3-D) animation of facial expressions. We have been concerned primarily with expressions conveying information correlated with the intonation of the voice: This includes the differences of timing, pitch, and emphasis that are related to such semantic distinctions of discourse as “focus,” “topic,” and “comment,” “theme” and “rheme,” or “given” and “new” information. We are also interested in the relation of affect or emotion to facial expression. Until now, systems have not embodied such rule-governed translation from spoken utterance meaning to facial expressions. Our system embodies rules that describe and coordinate these relations: intonation/information, intonation/affect, and facial expressions/affect. A meaning representation includes discourse information: What is contrastive/background information in the given context, and what is the “topic” or “theme” of the discourse? The system maps the meaning representation into how accents and their placement are chosen, how they are conveyed over facial expression, and how speech and facial expressions are coordinated. This determines a sequence of functional groups: lip shapes, conversational signals, punctuators, regulators, and manipulators. Our algorithms then impose synchrony, create coarticulation effects, and determine affectual signals, eye and head movements. The lowest level representation is the Facial Action Coding System (FACS), which makes the generation system portable to other facial models.
The common approach to the multiplicity problem calls for controlling the familywise error rate (FWER). This approach, though, has faults, and we point out a few. A different approach to problems of multiple significance testing is presented. It calls for controlling the expected proportion of falsely rejected hypotheses – the false discovery rate. This error rate is equivalent to the FWER when all hypotheses are true but is smaller otherwise. Therefore, in problems where the control of the false discovery rate rather than that of the FWER is desired, there is potential for a gain in power. A simple sequential Bonferroni-type procedure is proved to control the false discovery rate for independent test statistics, and a simulation study shows that the gain in power is substantial. The use of the new procedure and the appropriateness of the criterion are illustrated with examples.
A key goal in agent research is to be able to generate multimodal characters that can reflect a particular personality. The Big Five model of personality provides a framework for codifying personality variation. This paper reviews findings in the psychology literature to understand how the Big Five trait of emotional stability correlates with changes in verbal and nonverbal behavior. Agent behavior was modified based on these findings and a perceptual study was completed to determine if these changes lead to the controllable perception of emotional stability in virtual agents. The results reveal how language variation and the use of self-adaptors can be used to increase or decrease the perceived emotional stability of an agent. Self-adaptors are movements that often involve self-touch, such as scratching or bending one's fingers backwards in an unnatural brace. These results provide guidance on how agent designers can create particular characters, including indicating that for particular personality types, it is important to also produce typically non-communicative gestural behavior, such as the self-adaptors studied.
A significant goal in multi-modal virtual agent research is to determine how to vary expressive qualities of a character so
that it is perceived in a desired way. The “Big Five” model of personality offers a potential framework for organizing these
expressive variations. In this work, we focus on one parameter in this model – extraversion – and demonstrate how both verbal
and non-verbal factors impact its perception. Relevant findings from the psychology literature are summarized. Based on these,
an experiment was conducted with a virtual agent that demonstrates how language generation, gesture rate and a set of movement
performance parameters can be varied to increase or decrease the perceived extraversion. Each of these factors was shown to
be significant. These results offer guidance to agent designers on how best to create specific characters.
We aim at creating an expressive Embodied Conversational Agent (ECA) and address the problem of synthesizing expressive agent gestures. In our previous work, we have described the gesture selection process. In this paper, we present a computational model of gesture qual- ity. Once a certain gesture has been chosen for execution, how can we modify it to carry a desired expressive content while retaining its orig- inal semantics? We characterize bodily expressivity with a small set of dimensions derived from a review of psychology literature. We provide a detailed description of the implementation of these dimensions in our animation system, including our gesture modeling language. We also demonstrate animations with dierent expressivity settings in our ex- isting ECA system. Finally, we describe two user studies that evaluate the appropriateness of our implementation for each dimension of expres- sivity as well as the potential of combining these dimensions to create expressive gestures that reflect communicative intent.
Over the last fifty years, the "Big Five" model of personality traits has become a standard in psychology, and research has systematically documented correlations be- tween a wide range of linguistic variables and the Big Five traits. A distinct line of research has explored methods for automati- cally generating language that varies along personality dimensions. We present PER- SONAGE (PERSONAlity GEnerator), the first highly parametrizable language gener- ator for extraversion, an important aspect of personality. We evaluate two personal- ity generation methods: (1) direct genera- tion with particular parameter settings sug- gested by the psychology literature; and (2) overgeneration and selection using statistical models trained from judge's ratings. Results show that both methods reliably generate ut- terances that vary along the extraversion di- mension, according to human judges.
We present a new technique to generate heterogeneous crowd behaviors using personality trait theory. Our for- mulation is based on adopting results of a user study to derive a mapping from crowd simulation parameters to the perceived behaviors of agents in computer-generated crowd simulations. We also derive a linear mapping between simulation parameters and personality descriptors corresponding to the well-established Eysenck Three- factor personality model. Furthermore, we propose a novel two-dimensional factorization of perceived personality in crowds based on a statistical analysis of the user study results. Finally, we demonstrate that our mappings and factorizations can be used to generate heterogeneous crowd behaviors in different settings.
This paper introduces Linguistic Style Improvisation, a theory and set of algorithms for improvisation of spoken utterances by artificial agents, with applications to interactive story and dialogue systems. We argue that linguistic style is a key aspect of character, and show how speech act representations common in AI can provide abstract representations from which computer characters can improvise. We show that the mechanisms proposed introduce the possibility of socially oriented agents, meet the requirements that lifelike characters be believable, and satisfy particular criteria for improvisation proposed by Hayes-Roth.
Why do dogs wag their tails and cats purr? Why do we get embarrassed, and why does embarrassment make us blush? Why do we frown when we're disappointed? These any many other questions about the emotional life of humans and animals are answered in this remarkable book. The Expression of the Emotions in Man and Animals was an immediate best-seller when it was first published in 1872 and still provides the point of departure for research into emotion and facial expression. In his study of infants and children (including delightful observations of his own baby's smiles and pouts), of the insane, of painting and sculpture, of cats and dogs and monkeys, and of the ways that people in different cultures express their feelings, Darwin's insights have not been surpassed by modern science. This definitive edition contains a substantial new Introduction and Afterword by Paul Ekman. Ekman also provides commentaries that use the latest scientific knowledge to elaborate, support, and occasionally challenge Darwin's study. When it originally appeared, this was the first scientific book to contain photographic reproductions. For this edition, Ekman has returned to Darwin's original notes in order to produce, for the first time, a corrected, authoritative text illustrated by drawings and photographs positioned exactly as its author intended. The Expression of Emotion in Man and Animals reminds us that, in addition to being the nineteenth century's most influential thinker, Darwin was also a writer of consummate skill. Beautifully and profusely illustrated, and filled with insights that immediately ring true, this new edition promises to delight and enthrall a new generation of readers.
The common approach to the multiplicity problem calls for controlling the familywise error rate (FWER). This approach, though, has faults, and we point out a few. A different approach to problems of multiple significance testing is presented. It calls for controlling the expected proportion of falsely rejected hypotheses — the false discovery rate. This error rate is equivalent to the FWER when all hypotheses are true but is smaller otherwise. Therefore, in problems where the control of the false discovery rate rather than that of the FWER is desired, there is potential for a gain in power. A simple sequential Bonferronitype procedure is proved to control the false discovery rate for independent test statistics, and a simulation study shows that the gain in power is substantial. The use of the new procedure and the appropriateness of the criterion are illustrated with examples.
A major goal of research on virtual humans is the animation of expressive characters that display distinct psychological attributes. Body motion is an effective way of portraying different personalities and differentiating characters. The purpose and contribution of this work is to describe a formal, broadly applicable, procedural, and empirically grounded association between personality and body motion and apply this association to modify a given virtual human body animation that can be represented by these formal concepts. Because the body movement of virtual characters may involve different choices of parameter sets depending on the context, situation, or application, formulating a link from personality to body motion requires an intermediate step to assist generalization. For this intermediate step, we refer to Laban Movement Analysis, which is a movement analysis technique for systematically describing and evaluating human motion. We have developed an expressive human motion generation system with the help of movement experts and conducted a user study to explore how the psychologically validated OCEAN personality factors were perceived in motions with various Laban parameters. We have then applied our findings to procedurally animate expressive characters with personality, and validated the generalizability of our approach across different models and animations via another perception study.
A major goal of research on virtual humans is the animation of expressive characters that display distinct psychological attributes. Body motion is an effective way of portraying different personalities and differentiating characters. The purpose and contribution of this work is to describe a formal, broadly applicable, procedural, and empirically grounded association between personality and body motion and apply this association to modify a given virtual human body animation that can be represented by these formal concepts. Because the body movement of virtual characters may involve different choices of parameter sets depending on the context, situation, or application, formulating a link from personality to body motion requires an intermediate step to assist generalization. For this intermediate step, we refer to Laban Movement Analysis, which is a movement analysis technique for systematically describing and evaluating human motion. We have developed an expressive human motion generation system with the help of movement experts and conducted a user study to explore how the psychologically validated OCEAN personality factors were perceived in motions with various Laban parameters. We have then applied our findings to procedurally animate expressive characters with personality, and validated the generalizability of our approach across different models and animations via another perception study.
: Research relevant to psychotherapy regarding facial expression and body movement, has shown that the kind of information which can be gleaned from the patients words - information about affects, attitudes, interpersonal styles, psychodynamics - can also be derived from his concomitant nonverbal behavior. The study explores the interaction situation, and considers how within deception interactions differences in neuroanatomy and cultural influences combine to produce specific types of body movements and facial expressions which escape efforts to deceive and emerge as leakage or deception clues.
Designing virtual characters that are capable of conveying a sense of personality is important for generating realistic experiences, and thus a key goal in computer animation research. Though the influence of gesture and body motion on personality perception has been studied, little is known about which attributes of hand pose and motion convey particular personality traits. Using the "Big Five" model as a framework for evaluating personality traits, this work examines how variations in hand pose and motion impact the perception of a character's personality. As has been done with facial motion, we first study hand motion in isolation as a requirement for running controlled experiments that avoid the combinatorial explosion of multimodal communication (all combinations of facial expressions, arm movements, body movements, and hands) and allow us to understand the communicative content of hands. We determined a set of features likely to reflect personality, based on research in psychology and previous human motion perception work: shape, direction, amplitude, speed, and manipulation. Then we captured realistic hand motion varying these attributes and conducted three perceptual experiments to determine the contribution of these attributes to the character's personalities. Both hand poses and the amplitude of hand motion affected the perception of all five personality traits. Speed impacted all traits except openness. Direction impacted extraversion and openness. Manipulation was perceived as an indicator of introversion, disagreeableness, neuroticism, and less openness to experience. From these results, we generalize guidelines for designing detailed hand motion that can add to the expressiveness and personality of characters. We performed an evaluation study that combined hand motion with gesture and body motion. Even in the presence of body motion, hand motion still significantly impacted the perception of a character's personality and could even be the dominant factor in certain situations.
Action prediction and fluidity are key elements of human–robot teamwork. If a robot’s actions are hard to understand, it can impede fluid human–robot interaction. Our goal is to improve the clarity of robot motion by making it more human-like. We present an algorithm that autonomously synthesizes human-like variants of an input motion. Our approach is a three-stage pipeline. First we optimize motion with respect to spatiotemporal correspondence (STC), which emulates the coordinated effects of human joints that are connected by muscles. We present three experiments that validate that our STC optimization approach increases human-likeness and recognition accuracy for human social partners. Next in the pipeline, we avoid repetitive motion by adding variance, through exploiting redundant and underutilized spaces of the input motion, which creates multiple motions from a single input. In two experiments we validate that our variance approach maintains the human-likeness from the previous step, and that a social partner can still accurately recognize the motion’s intent. As a final step, we maintain the robot’s ability to interact with its world by providing it the ability to satisfy constraints. We provide experimental analysis of the effects of constraints on the synthesized human-like robot motion variants.
Thirty-four college men and 33 women were assessed on extraversion (E), gender diagnosticity (GD), masculine instrumentality (M), and feminine expressiveness (F). Participants were videotaped as they delivered talks, and their nonverbal behavior and personality were judged from videotapes. Participants' extraversion and masculinity–femininity (M–F) were reliably and accurately judged from videotapes. Judged extraversion correlated significantly with E, and judged M–F correlated most with GD, less with M, but not with F. For women but not men, judged M–F correlated strongly (r= .67) with judged physical attractiveness. The current research identified nonverbal cues that correlated with judged and assessed extraversion more successfully than it identified cues that correlated with GD, M, F, and judged M–F. M–F proved to be as observable a trait as extraversion, even though it was judged from different kinds of cues.
Twenty-four perceivers saw portraits of unacquainted persons for either 150ms, 100ms, or 50ms, and rated their personality on adjective scales. Moreover, stimulus persons described themselves on these scales and the NEO Five-Factor Inventory. Consensus among perceivers and self-other agreement were not systematically related to exposure time, but self-other agreement differed strongly between traits, being highest for extraversion. Even ratings of extraversion by single perceivers were related to the stimulus persons’ self-reports. Particularly strong were correlations between perceived extraversion and self-reports on items measuring the extraversion facets excitement seeking and positive emotions. Self-other agreement for extraversion was mostly mediated by cheerfulness of facial expressions that was related to self-reports of extraversion but not of the other personality traits.
When people form impressions about others, they are mostly influenced by non-verbal cues. Thus, politicians and other leaders are judged by the behavior they display. To analyze the relation between non-verbal behavior and impression formation body movements of politicians giving a speech were transformed into animated stick figures. Subjects then rated the stick-figure movies on the five factor model of personality. Motion analysis revealed that observers associate extraversion, agreeableness, conscientiousness, emotional stability and openness with different motion qualities such as the amount of motion and its flow. Additionally, we found significant correlations between these personality traits and dominant activation of different body parts. The current study underlines that body motion is a powerful signal in human communication.
The definitive book on animation, from the Academy Award-winning animator behind Who Framed Roger Rabbit?Animation is one of the hottest areas of filmmaking today--and the master animator who bridges the old generation and the new is Richard Williams. During hisfifty years in the business, Williams has been one of the true innovators, winning three Academy Awards and serving as the link between Disney's golden age of animation by hand and the new computer animation exemplified by Toy Story. Perhaps even more important, though, has been his dedication in passing along his knowledge to a new generation of animators so that they in turn could push the medium in new directions. In this book, based on his sold-out master classes in the United States and across Europe, Williams provides the underlying principles of animation that every animator--from beginner to expert, classic animator to computer animation whiz --needs. Urging his readers to "invent but be believable," he illustrates his points with hundreds of drawings, distilling the secrets of the masters into a working system in order to create a book that will become the standard work on all forms of animation for professionals, students, and fans.
Style translation is the process of transforming an input motion into a new style while preserving its original content. This problem is motivated by the needs of interactive applications, which require rapid processing of captured performances. Our solution learns to translate by analyzing differences between performances of the same content in input and output styles. It relies on a novel correspondence algorithm to align motions, and a linear time-invariant model to represent stylistic differences. Once the model is estimated with system identification, our system is capable of translating streaming input with simple linear operations at each frame.
In this third edition, some amendments and additions have been made to the original text, first published in 1950. As in past editions, the relationship between the inner motivation of movement and the outer functioning of the body is explored. Acting and dancing are shown as activities deeply concerned with man's urge to establish values and meanings. The student is introduced to basic principles underlying movement expression and experience and numerous exercises are intended to challenge his intellectual, emotional and physical responses. The many descriptions of movement scenes and mime-dances are designed to stimulate penetration into man's inner life where movement and action originate. The chapters of the book discuss the following topics: Movement and the Bpdy; The Significance of Movement; Roots of Mime; The Study of Movement Expression; and Three Mime Plays. The book contains nine tables and 23 scenes for study. (Author/DB)
Virtual characters are much in demand for animated movies, games, and other applications. Rapid advances in performance capture and advanced rendering techniques have allowed the movie industry in particular to create characters that appear very human-like. However, with these new capabilities has come the realization that such characters are yet not quite “right.” One possible hypothesis is that these virtual humans fall into an “Uncanny Valley”, where the viewer's emotional response is repulsion or rejection, rather than the empathy or emotional engagement that their creators had hoped for. To explore these issues, we created three animated vignettes of an arguing couple with detailed motion for the face, eyes, hair, and body. In a set of perceptual experiments, we explore the relative importance of different anomalies using two different methods: a questionnaire to determine the emotional response to the full-length vignettes, with and without facial motion and audio; and a 2AFC (two alternative forced choice) task to compare the performance of a virtual “actor” in short clips (extracts from the vignettes) depicting a range of different facial and body anomalies. We found that the facial anomalies are particularly salient, even when very significant body animation anomalies are present.
There is empirical evidence that underlying the Big Five personality factors are two higher-order factors which have come to be known as “alpha” (α) and “beta” (β). The α factor is defined by the agreeableness, conscientiousness, and emotional stability domains; whereas β is delineated by extraversion and intellect. It has been argued that α and β are important constructs because they bridge the gap between psychometric studies of personality and theories of personality development. However, it is unclear if α and β are constructs that can be reliably reproduced across a diverse range of independent samples. In a sample of 1209 MZ and 701 DZ twin pairs from Canada, Germany, and Japan who completed the NEO-PI-R, factorial analyses of the five NEO-PI-R domains extracted two factors resembling α and β. Subsequent multivariate genetic analyses revealed that this factor structure was a clear reflection of the organizing effects of multiple genetic influences, providing evidence for α and β as stable heuristic devices that can be used to integrate personality measurement and developmental theory.
ABSTRACT Following a general model of consensus in interpersonal perception (Kenny, 1991), we report evidence on four sources of consensus and self-other agreement: (a) meaning systems shared by observers, (b) extent of information on target behavior, (c) consistency of target behavior, and (d) non-behavioral information. We argue that these factors can be disentangled more precisely by analyzing ratings by strangers instead of ratings by acquaintances. We then focus on first impressions as a source of self-other agreement, and we report evidence that first impressions of actual persons are quite accurate for Extraversion and Conscientiousness.
Nine-hundred-and-fifty-two individuals completed the Big Five Inventory, and 60 extreme scorers were presented with 30 music excerpts from six popular genres. Music-induced movement was recorded by an optical motion-capture system, the data from which 55 postural, kinematic, and kinetic movement features were computed. These features were subsequently reduced to five principal components of movement representing Local Movement, Global Movement, Hand Flux, Head Speed, and Hand Distance. Multivariate Analyses revealed significant effects on these components of both personality and genre, as well as several interactions between the two. Each personality dimension was associated with a different pattern of movement characteristics, with Extraversion and Neuroticism eliciting the clearest relationships. Latin, Techno, and Rock music, meanwhile, most clearly elicited different movement characteristics.
Personality trait attribution can underpin important social decisions and yet requires little effort; even a brief exposure to a photograph can generate lasting impressions. Body movement is a channel readily available to observers and allows judgements to be made when facial and body appearances are less visible; e.g., from great distances. Across three studies, we assessed the reliability of trait judgements of point-light walkers and identified motion-related visual cues driving observers' judgements. The findings confirm that observers make reliable, albeit inaccurate, trait judgements, and these were linked to a small number of motion components derived from a Principal Component Analysis of the motion data. Parametric manipulation of the motion components linearly affected trait ratings, providing strong evidence that the visual cues captured by these components drive observers' trait judgements. Subsequent analyses suggest that reliability of trait ratings was driven by impressions of emotion, attractiveness and masculinity.
This paper summarizes some of the measures of nonverbal behavior that have been found to be significant indicators of a communicator’s
attitude toward, status relative to, and responsiveness to his addressee. The nonverbal cues considered include posture, position,
movement, facial, and implicit verbal cues. In addition to providing criteria for the scoring of these cues, experimental
findings that relate to the various cues are summarized.
When time is limited, researchers may be faced with the choice of using an extremely brief measure of the Big-Five personality dimensions or using no measure at all. To meet the need for a very brief measure, 5 and 10-item inventories were developed and evaluated. Although somewhat inferior to standard multi-item instruments, the instruments reached adequate levels in terms of: (a) convergence with widely used Big-Five measures in self, observer, and peer reports, (b) test–retest reliability, (c) patterns of predicted external correlates, and (d) convergence between self and observer ratings. On the basis of these tests, a 10-item measure of the Big-Five dimensions is offered for situations where very short measures are needed, personality is not the primary topic of interest, or researchers can tolerate the somewhat diminished psychometric properties associated with very brief measures.
This paper introduces Linguistic Style Improvisation,a theory and set of algorithms for improvisation ofspoken utterances by artificial agents, with applicationsto interactive story and dialogue systems. Weargue that linguistic style is a key aspect of character,and show how speech act representations common inAI can provide abstract representations from whichcomputer characters can improvise. We show thatthe mechanisms proposed introduce the possibility ofsocially oriented...