Recent advances in generative AI have introduced AI-extended characters, which refer to AI-generated personas grounded in pre-existing human or fictional referents. While prior research focuses on direct social interaction, their capacity to foster parasocial interaction (PSI) in media remains underexplored. We analyzed 1,460 audience comments from 299 AI talk show videos to investigate this gap. Our findings identify three distinct objects of PSI within AI-extended characters: referents, AI proxies, and blended characters. Although referents remain the primary focus, PSI toward AI proxies and blended characters suggests that audience engagement with AI media may extend beyond the original referents. We further found that humanlikeness and AI awareness appeared as recurring themes in how audiences interpreted these relationships. This work provides a preliminary understanding of human engagement with AI-extended characters and offers design implications for future AI-mediated creative media content.

Moving target selection in multimedia interactive systems faces unprecedented challenges as users increasingly interact across diverse, dynamic contexts-from live streaming in moving vehicles to VR gaming in varying environments. Existing approaches rely on probabilistic models that relate endpoint distribution to target properties (size, speed). However, these methods require substantial training data for each new context and lack transferability across scenarios, limiting their practical deployment in diverse multimedia environments where rich multimodal contextual information is readily available. This paper introduces MAGNeT (Multimodal Adaptive Gaussian Networks), which addresses these problems by combining classical statistical modeling with context-aware multimodal method. MAGNeT dynamically fuses pre-fitted Ternary-Gaussian models from various scenarios based on real-time contextual cues, enabling effective adaptation with minimal training data while preserving model interpretability. We take experiments on self-constructed 2D and 3D moving target selection datasets under in-vehicle vibration conditions. Extensive experiments demonstrate that MAGNeT achieves lower error rates with few-shot samples, by applying context-aware fusion of Gaussian experts from multi-factor conditions.

Stereotyped movements play a crucial role in diagnosing Autism Spectrum Disorder (ASD). However, recognizing them poses challenges, due to limited data availability and the movements' specificity and varying duration. To support in-depth analysis of ASD children's movements, we constructed the ACSA653 dataset, comprising 653 videos across six classes of stereotyped movements. This dataset surpasses existing ones in both scale and category. To improve the recognition of stereotyped movements, we propose APMFNet, a model that integrates three modules: Visual Motion Learning (VML), Skeleton Relation Mining (SRM), and Multi-channel Fusion (MF). The VML module focuses on extracting spatial and motion information from RGB and optical-flow sequences. The SRM module effectively mines essential motion patterns associated with stereotyped movements through cross-modal graph. The MF module fuses multi-modal information through cross-modality attention to facilitate decision-making. Tested on ACSA653, APMFNet outperforms current state-of-the-art methods, suggesting its potential to identify stable patterns of stereotyped movements in children with ASD.

Human cognition and behavior can be unconsciously affected by personal avatars in the virtual world, a phenomenon known as the Proteus Effect. When using first-person non-human avatars, the characteristics of virtual hands may also induce relevant cognitive and even behavioral patterns in real human hands. Therefore, evaluating human-avatar gesture consistency may be a potentially effective method for objectively assessing the Proteus Effect when using non-human avatars. To explore this question, we first created human and non-human avatars, including three animals. Then, we constructed a dataset of hand gestures and trained a model to dynamically recognize real-hand gestures that were consistent with corresponding avatar hands. Next, we designed a virtual reality experimental task involving grasping objects with intuitive gestures and performed a 2 (avatar type: human/non-human) $* 2$ (virtual hand: presence/absence of spontaneous movement) within-subject experiment to examine the effects of avatar characteristics on self-illusion and human-avatar gesture consistency. The results showed that participants performed a significantly larger percentage of gestures that were consistent with their currently used avatars. Additionally, participants did experience self-illusion when using non-human avatars, although the levels were significantly lower than those when using human avatars. Therefore, self-illusion may serve as a perceptual antecedent of the Proteus Effect, even with non-human avatars, inadvertently altering the behavioral gestures of their real hands. In conclusion, detecting human-avatar gesture consistency can help evaluate the Proteus Effect.

Children diagnosed with Autism Spectrum Disorder (ASD) often exhibit motor disorders. Dance Movement Therapy (DMT) has shown great potential for improving the motor control ability of children with ASD. However, traditional DMT methods often lack vividness and are difficult to implement effectively. To address this issue, we propose a Mixed Reality DMT approach, utilizing interactive virtual agents. This approach offers immersive training content and multi-sensory feedback. To improve the training performance of children with ASD, we introduce a novel training paradigm featuring a self-guided mode. This paradigm enables the rapid creation of a virtual twin agent of the child with ASD using a single photo to embody oneself, which can then guide oneself during training. We conducted an experiment with the participation of 24 children diagnosed with ASD (or ASD propensity), recording their training performance under various experimental conditions. Through expert rating, behavior coding of training sessions, and statistical analysis, our findings revealed that the use of the twin agent for self-guidance resulted in noticeable improvements in the training performance of children with ASD. These improvements were particularly evident in terms of enhancing movement quality and refining overall target-related responses. Our study holds clinical potential in the field of medical treatment and rehabilitation for children with ASD.