Yunpeng Song's research while affiliated with Xi'an Jiaotong University and other places

... MuSeNet's uniqueness lies in its ability to effectively integrate information from different modalities, thus improving the accuracy and performance of music emotion classification. Another model, FusionNet, combines audio and lyric information [21]. It uses deep convolutional neural networks (CNN) and recurrent neural networks (RNN) structures to process different modal data. ...

... The key focus of the paper [16] is the introduction of the SapiMouse dataset, designed for training and evaluating systems in user authentication and bot detection based on mouse dynamics. Article [17] highlights the central theme of creating an endto-end deep framework designed for detecting bots through computer mouse movements. The paper [18] introduces Re-Mouse, a unique real-world mouse dynamics dataset, offering insight into combating session-replay bots, a challenging issue in domains frequented by the same genuine users Kinematics pertains to the study of object motion without considering the reasons behind this movement [19], and in this case, the object is the mouse used for user input. ...

... The second approach focuses on enhancing individuals' understanding of AI error patterns, aiding in the development of humans' accurate mental models for AI capabilities [1,8,30]. For instance, Bansal et al. [1] introduced the concept of "mental models of AI error boundaries", highlighting factors shaping these models. ...

... Deep learning algorithms have been used to make classification decisions for many touch-based mobile authentication models. For studies [7][8][9], CNN architectures were used for classification. In [7], researchers used their proposed feature representation tactic, multiple channels biological graph (MCBG), with CNN to enhance their continuous mobile authentication scheme. ...

... (2.2%) Users, especially those who used their devices only for limited purposes, tended to be skeptical about the effectiveness and necessity of security software: "I use <anti-virus software's name>, but I don't see the benefits. When [71], cyberstalking [72], [73], excessive parental control [74]- [76], voyeurism [77], [78], and bugging [77], [78]. In previous studies, privacy abuse has been researched in cooperation with professional organizations by means of closed questionnaires and interviews [68], [70], [71]. ...

... In this regard, family's support provides a dynamic and lasting cushion to prevent senior adults from being eliminated in technological innovations of payment methods, which sheds light on richer nuances of the family's backing, instead of merely a channel in short-term set-up and acceptance that prior work focused on [45,69]. Meanwhile, it also enriched the research venue on account sharing [1,53,56,72,87] by providing new practical evidence of family's financial support with shared devices/accounts. Indeed, the traditional family model with stronger inter-generation financial ties in many nonwestern cultures [51,89] is substantial yet largely neglected in technology design. ...