Bruno Feijó

Verified

Bruno verified their affiliation via an institutional email.

Learn more

Verified

Bruno verified their affiliation via an institutional email.

Learn more

• MSc, MPhil, DIC, PhD
• Professor (Full) at Pontifical Catholic University of Rio de Janeiro

This paper proposes the use of narrative patterns as an effective guide to preserve thematic consistency in the composition of stories using Large Language Models (LLMs). Our approach drove inspiration from a well-accepted, thorough, and overarching classification of folklore types and the deservedly famous Monomyth characterization of heroic quest...

This article presents a novel and highly interactive process to generate natural language narratives based on our ongoing work on semiotic relations, providing four criteria for composing new narratives from existing stories. The wide applicability of this semiotic reconstruction process is suggested by a reputed literary scholar’s deconstructive c...

In this paper we introduce a novel highly interactive process to generate natural language narratives on the basis of our ongoing work on semiotic relations. To the two basic components of interactive systems, namely, a software tool and a user interface, we add a third component-AI agents, understood as an upgraded rendition of software agents. Ou...

The use of narrative generation methods in games is a complex challenge that involves multiple problems of plot-based processes integrated with character-based methods. Examples of these problems are the high computational complexity of many story generation algorithms, the difficulties associated with the generation of interactive narratives that...

In this paper we propose a new plot composition method based on situation calculus and Petri net models, which are applied, in a complementary fashion, to a narrative open to user co-authorship. The method starts with the specification of situation calculus schemas, which allow a planning algorithm to check if the specification covers the desired c...

In this paper, we present a novel character-based model for interactive storytelling in games, which combines multi-agent planning with a drama management strategy based on production rules to guide the narrative generation process. The underlying proposed method is capable of generating and controlling the enactment of character-based narratives i...

This paper presents an architecture for generating music for video games based on the Transformer deep learning model. The system generates music in various layers, following the standard layering strategy currently used by composers designing video game music. The music is adaptive to the psychological context of the player, according to the arous...

The situation calculus logic model is convenient for modelling the actions that can occur in an information system application. The interplay of pre-conditions and post-conditions determines a semantically justified partial order of the defined actions and serves to enforce integrity constraints. This form of specification allows the use of plan-ge...

The production of high-quality digital games usually requires a few hundred individuals, including designers, artists, and story writers. Currently, development teams are increasingly applying procedural content generation techniques to reduce their work overload. However, there is a lack of methods to handle the procedural generation of branching...

Inspired by conceptual blending models and considering plot generation as a plan-generation problem, this paper proposes a robust method that reuses existing stories to generate new narrative variants. This method generates variants that combine episodes extracted and adapted from different stories that share the same narrative structure. By combin...

The new generation of games searches for in-depth narratives. Innovations in this new trend require a better understanding of interactive narratives based on the emergence of a novel discipline named Computational Narratology. This paper proposes that this new discipline results from the transdisciplinary convergence of concepts and implementation...

Visual object tracking aims to deliver accurate estimates about the state of the target in a sequence of images or video frames. Nevertheless, tracking algorithms are sensitive to different kinds of image perturbations that frequently cause tracking failures. Indeed, tracking failures result from the insertion of imprecise target-related data into...

In almost all forms of storytelling, the background and the current state of mind of the audience members predispose them to experience a given story from a uniquely personal perspective. However, traditional story writers usually construct their narratives based on the average preferences of their audience, which does not guarantee satisfying narr...

The production of high-quality commercial games requires the work of a few hundred individuals, including designers, artists, and story writers, to produce game content, such as 3D models, textures, and narratives. Over the last decade, the production of game content has grown to the point of becoming a bottleneck in companies’ schedules and budget...

Human-Robot Interaction challenges the field of research on Artificial Intelligence in many ways, especially regarding the complexity of the physical world. While physical interactions require Artificial Intelligence techniques to handle dynamic, nondeterministic, and partially unknown environments, the communication with humans requires socially a...

In almost all forms of storytelling, the background and the current state of mind of the audience members predispose them to experience a given story from a unique personal perspective. However, traditional story writers usually construct their narratives based on an average understanding of the preferences of their audience, which does not guarant...

This article proposes the Persona method. The goal of the prosposed method is to learn and classify the facial actions of actors in video sequences. Persona is based on standard action units. We use a database with main expressions mapped and pre-classified that allows the automatic learning and faces selection. The learning stage uses Support Vect...

Current video games use simple methods to deal with interactive narratives and the enormous variety of player types. In this paper, we propose a novel approach to interactive storytelling in games, in which the quests and the ongoing story are determined in view of individual personality traits and behavioral attitudes in a nondeterministic way. Ou...

Software designers are facing huge challenges imposed by a new generation of applications that mix real and digital worlds, such as pervasive games. This type of game has recently become a worldwide phenomenon, with thousands of people walking in the streets with smartphones to interact with the physical environment. In this paper, we propose a new...

There is a growing trend of entertainment applications where players wear non-see-through HMD devices (i.e. they see only virtual contents) and move freely in a physical environment, being able to touch physical objects and walls, feel hot air stream on their faces, and interact with other real people, while fully immersed in the simulation. Curren...

Interactive storytelling systems usually adopt computer graphics to represent virtual story worlds, which facilitates the dynamic generation of visual content. However, the quality of the images and motion produced by these systems is still inferior compared to the high quality experience found in live-action films. Interactive rates in photorealis...

Narrative and storytelling have become central issues in the new generation of video games. In this paper, we propose a modelling strategy to combine a chosen repertoire of story variants of the same narrative pattern into a network structure. We follow a Computational Narratology orientation and aim at two complementary objectives: (1) the analysi...

Procedural Content Generation (PCG) is the pro-grammatic generation of game content using a random orpseudo-random process that produces an unpredictable stretchof gaming spaces. Many games use this technique to increase thelength of gaming, and some of them rely greatly on the proceduralcontent generation. This paper aims to detail a fast and dire...

Usually in games, the interaction between playerand NPCs are very limited and does not allow the spontaneouscreation of long-term relationships. The NPCs are cold, directand faithfully follow his instructions while keeping a well-definedpattern of behavior. The present paper proposes a model toease the way NPCs act and react, based on human psychol...

Computer games are real-time applications that create interactive virtual environments, usually as discrete time-stepped simulations. These simulations may have predefined time step sizes or may use variable time step sizes. These approaches are common in games, but not flexible. In the first approach, when the game runs on a machine with abundant...

In this paper we describe the main concepts of a new game genre (live-action virtual reality game) made possible by the advances of virtual reality technologies and context-awareness. This set of games requires that players wear HMD devices, from where they see a complete virtual world that is built using part of the physical configuration as the b...

Virtual reality has received a lot of attention lately due to a new wave of affordable HMD devices arriving in the consumer market. These new display devices – along with the availability of fast wireless networking, comprehensive wearable technologies, and robust context-aware devices – are enabling the emergence of a new type of mixed-reality sys...

Video games add new dimensions to traditional storytelling by allowing players to change narratives through their own actions. In modern Role-Playing Games (RPGs), this is usually done by adopting branching storylines based on key choices presented to players at certain points of the game. However, such branching points are usually presented throug...

We propose to examine here a heroic narrative pattern, in which the protagonist begins as a simpleton, learns about the world and about himself along successive stages, falls down nevertheless in a crucial instant, but is then led to rise again and move towards a high position that nobody else was worthy to attain. A major feature of the pattern is...

In this paper we propose a real time 360° video stitching and streaming processing methodology focused on GPU. The solution creates a scalable solution for large resolutions, such as 4K and 8K per camera, and supports broadcasting solutions with cloud architectures. The methodology uses a group of deformable meshes, processed using OpenGL (GLSL) an...

This paper summarizes current notes about a new mixed-reality paradigm that we named as "pervasive virtuality". This paradigm has emerged recently in industry and academia through different initiatives. In this paper we intend to explore this new area by proposing a set of features that we identified as important or helpful to realize pervasive vir...

This paper proposes the concept of "live-action virtual reality games" as a new genre of digital games based on an innovative combination of live-action, mixed-reality, context-awareness, and interaction paradigms that comprise tangible objects, context-aware input devices, and embedded/embodied interactions. Live-action virtual reality games are "...

An intriguing phenomenon in human storytelling – inexhaustible source of inspiration for digital storytelling – is our ability to still recognize a story that the narrator has felt free to change to a considerable extent. We have been witnessing a renewed interest of the movie industry in adaptations of folktales, mostly for adult audiences. Howeve...

A small number of variants of a widely disseminated folktale is surveyed , and then analyzed in an attempt to determine how such variants can emerge while staying within the conventions of the genre. The study follows the classification of types and motifs contained in the Index of Antti Aarne and Stith Thompson. The paper's main contribution is th...

To tell a story, the storyteller uses all his/her skills to entertain an audience. This task not only relies on the act of telling a story, but also on the ability to understand reactions of the audience during the telling of the story. A well-trained storyteller knows whether the audience is bored or enjoying the show just by observing the spectat...

Games have not received the full attention of the requirements engineering community. This scenario is becoming more critical as we move towards newer forms of games, such as pervasive games. Pervasiveness (the quality that distinguishes pervasive games from traditional digital games) holds several meanings, including being ubiquitous, permeating s...

Quests are a fundamental storytelling mechanism used by computer role-playing games to engage players in the game's narrative. Although role-playing games have evolved in many different ways in the last years, their basic narrative structure is still based on static plots manually created by game designers. In this paper, we present a method for th...

CPUs and GPUs have been evolving rapidly over time regarding their capabilities and processing power. This has opened many new possibilities for interactive and real time systems, such as more sophisticated scene realism, more precise and complex artificial intelligence, and better physical simulations. However, these improvements come at a cost: i...

We introduce in the present paper an operationally defined subclass within the genre of detective stories, specified on the basis of the logic programming model adopted in our Logtell project. Special attention is given to the treatment of communicative events. An SWI-Prolog plan-based tool was developed to compose consistent plots, conforming to t...

KW-GPS is a system to assist users intent on enjoying Web resources related to a domain-restricted collection of stories. In this system, each story is referenced in a virtual library in terms of the following data: (1) the URLs of resources associated with the story, which include but are not limited to plot-summaries, narrative texts, and videos;...

Computer games are creative projects that require the input of professionals with very diverse backgrounds, including game designers, artists, and software developers. Game development frequently is a complex process due to different expectations of the involved stakeholders. With pervasive games, this situation becomes more chaotic as there are no...

Simulation systems are becoming common in different knowledge fields, such as aeronautics, defense, and industrial applications, among many others. While in the past these systems where mostly based on typical Virtual Reality Environments, with the advance of the game industry simulators are being developed using typical game engines and gaming sof...

Cellular automata can be applied to solve several problems in a variety of areas, such as biology, chemistry, medicine, physics, astronomy, economics, and urban planning. The automata are defined by simple rules that give rise to behavior of great complexity running on very large matrices. 2D applications may require more than 10^6x10^6 matrix cell...

In shoot'em up games, the player engages in a solitary assault against a large number of enemies, which calls for a very fast adaptation of the player to a continuous evolution of the enemies attack patterns. This genre of video game is quite appropriate for studying and evaluating dynamic difficulty adaptivity in games that can adapt themselves to...

Evaluating dynamic difficulty adaptivity in shoot'em up games

We introduce in the present paper an operationally defined subclass within the genre of detective stories, specified on the basis of the logic programming model adopted in our Logtell project. Special attention is given to the treatment of communicative events. An SWI-Prolog plan-based tool was developed to compose consistent plots, conforming to t...

Object tracking in video sequences is still a challenging issue in real-time video processing. In this paper we propose an integrated detection and tracking method suitable for high-definition videos at real-time frame rates. In this method we implement a frame segmentation procedure using integral images of the background, which permits to discard...

A system (named KW-GPS) to assist users intent on enjoying Web resources related to a domain-restricted collection of stories is described. Each story is referenced in a virtual library in terms of: (1) the URLs of resources associated with the story, which include but are not limited to plot-summaries, narrative texts and videos; and in terms of (...

Drawing is a primary human skill that has been used for thousands of years as a visual complement to written and oral storytelling. The advent of interactive narratives brings the possibility of interaction to the traditional stories. In this paper, we present a storytelling system able to dramatize interactive narratives in augmented reality over...

Location-based applications suffer from many drawbacks related to the underlying infrastructure necessary to support this functionality. This work analyzes location based games for cellphones, in order to investigate possible approaches to handle technology limitations in this kind of application. Resumo. Aplicações baseadas em localização possuem...

Comics are a unique and classical form of storytelling. The advent of interactive narratives brings the possibility of interaction to the traditional comic books. In this paper we present a non-branching interactive comics system capable of generating dynamic interactive narratives in the format of comic books. The system allows users to interact w...

In this paper, we propose a temporal planning model for real-time generation of narratives in Interactive Storytelling systems. The model takes into account continuous branched time and the specification of constraints defined as temporal formulae over dramatic properties of the narrative (e.g. joy or tension). In order to address real-time generat...

a) Interactive TV (b) Interactive Cinema Figure 1: The multiuser natural language interaction system for interactive storytelling. Abstract Interactive narratives designed for television and cinema demands new interaction mechanisms. In the TV context, thousands of viewers sharing the same narrative at different places must have the opportunity to...

Story plots must contain, besides physical action events, a minimal set of information-gathering events, whereby the various characters can form their beliefs on the facts of the mini-world in which the narrative takes place. In this paper, we present an approach to model such events within a plan-based storytelling context. Three kinds of such eve...

In recent years interactive narratives emerged as a new form of digital entertainment, allowing users to interact and change stories according to their own desires. In this paper, we explore the use of social networks as a way of interaction in interactive narratives. We present the interaction interface of an interactive storytelling system that a...

This paper introduces an approach to render 3D tubes by using hardware tessellation. The proposed technique explores the new GPU pipeline—hull, tessellator, and domain stages—so that the tube mesh can be created in the last possible step inside the pipeline, thereby reducing the bottleneck of the CPU to GPU bandwidth and enabling real-time frame ra...

The development of interactive narratives with the quality of feature films is the central challenge of what we can name Video-Based Interactive Storytelling. A promising approach to this question is the use of prerecorded videos with real actors. Amongst several technical challenges, this approach firstly requires automatic video editing methods f...

Within an interactive storytelling context, stories are essentially nonlinear, i.e., they correspond to multiple alternative sequences of events and each event can usually have multiple different outcomes. In this context, branching-time logics tend to be a coherent option to handle the possible states of an interactive story. In addition, importan...

Several fields in Computer Science use distributed computing to solve many intensive computational problems. Digital games use this approach mainly in multiplayer games, where a mainframe or cluster processes the majority of game logic. Single player games can also use distribute computing to process game logic and visualization algorithms, usually...

The ability that users have to interact and change stories according to their own desires is what differentiates interactive narratives from conventional films. Moreover, this ability expands the boundaries of computer games towards new forms of digital entertainment. However, designing an interaction model for an interactive storytelling system in...

This paper presents a model of a Supporting Characters Director for interactive storytelling systems. The model can enhance the dramatization, improve the realism, and increase the duration of the stories being generated. The Director generates and manages three types of supporting characters. Some has the ability to interact with the main characte...

Being able to refine a mesh without comprimising the memory bandwidth is a powerful tool that might be explored with the new Tessellator part of the graphics pipeline. In this paper we provide a detailed implementation of two local subdivision algorithms - PN-Triangles and Phong Tessellation - using the new Tessellator pipeline. Moreover, a explici...

In this work, we investigate the application of modeling alternatives regarding fuzzy Markov chain-based, multitemporal, cascade classification of remote sensing data. From a theoretical viewpoint, alternative designs for the fuzzy Markov chain-based model are formally presented. From a pragmatic perspective, experimental results are discussed and...

Um dos maiores gargalos do pipeline gráfico é a largura de banda disponível entre a GPU e a CPU. Uma vez que largura de banda é limitada pelo hardware, o foco das novas APIs gráficas foi a criação de funcionalidades de para otimizar o uso da banda. As APIs gráficas do DirectX11 e OpenGL4 adicionaram um excelente mecanismo para a redução do volume d...

In this tutorial we intend to cover one of the innovations brought by DirectX11. Previous versions of DirectX didn‘t support native multithreading and most part of the API was not thread-safe. The user needed to add mutexes in the code to avoid race conditions in order to support a multi-threaded renderer. Moreover, the lack of native support would...

Distributed computing is being used in several fields to solve many computation intensive problems. In digital games, it is used mainly in multi-player games, where the majority of the game logic is processed in a mainframe or cluster. Single player games could also use distributed computing to process the game logic, devoting host processing to re...

The way emotions are expressed in a film has great impact on the viewer's understanding of the narrative. Over the years, filmmakers developed several techniques to enhance the perception of these emotions, such as the photography and the audio editing of the scenes. This paper proposes two cinematography-inspired autonomous agents designed to bett...

In this paper, we present a new technique for highly efficient terrain rendering using continuous view-dependent Level-of-Detail based on hardware tessellation unit found in modern GPUs. Our technique is based on parallel local processing, in the sense that the results at each terrain patch do not depend on results already obtained at other patches...

Nowadays, multithread hardware architectures like multi-core CPUs and GPUs found on PCs and game consoles (as Microsoft Xbox 360 and Sony Playstation 3) are a trend. Hence, real-time simulation and visualization systems, such as scientific visualization, games and virtual reality environments, will not get the best performance on such architectures...

Computing and presenting emergent crowd simulations in real time is a computationally intensive task. This intensity is mostly due to the complexity of the traversal algorithm needed for the interactions of all elements against each other on the basis of a proximity query. By using special data structures such as grids, and due to the parallel natu...