Expressive facial animation depends on models that can convey subtle, context‑dependent emotions. Procedural methods often rely on manually-tuned heuristics, while data‑driven techniques are constrained by the diversity of their training data. This paper explores the zero-shot potential of large language models (LLMs) to generate facial animations. Using the cognitively-grounded Ortony-Clore-Collins (OCC) model as a framework, we designed 110 text-based scenarios and evaluated the ability of different LLMs – Gemini-2.5 Pro, GPT-4o, and Llama 3.1-8b – to generate corresponding facial animations using the Facial Action Coding System (FACS). A perceptual user study confirmed that animations from Gemini-2.5 Pro were highly recognizable, with participants successfully matching facial expressions to the correct context at rates significantly above chance. A quantitative analysis of the generated Action Units (AUs) indicated both consistency within each OCC emotion category and diversity across different scenarios. Further analysis revealed that the emotional expressions group into six clusters: happiness, sadness, anger/disgust, fear/surprise, shame, and neutral. This work demonstrates a viable, lightweight pipeline connecting textual narrative directly to motion generation without requiring custom training or large-scale motion capture datasets.

This work investigates the effects of personality expression and embodiment in conversational agents. We extend a personality-driven conversational agent framework by integrating LLM-based conversation support to provide information about contemporary scientific topics. We describe a user study built on this system to evaluate two opposing personality styles using three models: a dialogue-only model that conveys personality verbally, an animated human model that expresses personality only through dialogue, and an animated human model expressing personality through dialogue and expressive animations. The users perceive all models positively regarding personality and learning outcomes; however, models with high personality traits are perceived as more engaging than those with low personality traits. We provide an analysis of personality perception, learning, and user experience.

This special issue of ACM Transactions on Applied Perception (TAP) features four articles from the 2025 Symposium on Applied Perception (SAP), held in Vancouver, BC, Canada, on August 9-10, 2025. ACM SAP provides an intimate forum for researchers who combine knowledge, methods, and insights from perception research and computer science. This year, SAP received 22 complete submissions, reviewed under a double-blind process. Seventeen were accepted for publication, and four of these were selected for inclusion in this special issue based on their exceptional quality. Each underwent an additional round of reviews consistent with the journal's editorial standards. The four contributions in this issue examine how perceptual and affective factors influence engagement, learning, health, and motivation across a variety of interactive contexts.

This work presents a comprehensive methodology for creating and annotating a standardized and semantically interpretable dataset to understand personality perception through facial expressions. The dataset is generated using an iterative strategy that employs the existing “First Impressions” dataset to train a deep learning model for classifying the Five-Factor personality traits in videos, thus providing automated annotations. The model is iteratively refined based on user feedback from a small-scale study, achieving high accuracy levels comparable to state-of-the-art systems. We describe two neural network architectures and analyze their performances. Instead of a large collection of videos, we provide temporal Action Unit (AU) intensities defined in the Facial Action Coding System (FACS), which allows for a compact and semantic representation that can be directly used in facial animation. Additionally, we analyze the role of AUs in personality expression. The findings emphasize their significance in emotional expressions related to personality traits and offer insights applicable to the animation of expressive virtual characters.

Immersive virtual environments populated by real and virtual humans provide valuable insights into human decision-making processes under controlled conditions. Existing literature indicates elevated comfort, higher presence, and a more positive user experience when virtual humans exhibit rich behaviors. Based on this knowledge, we conducted a web-based, interactive study, in which participants were embodied within a virtual crowd with complex behaviors driven by an underlying psychological model. While participants interacted with a group of autonomous humanoid agents in a shopping scenario similar to Black Friday, the platform recorded their non-verbal behaviors. In this independent-subjects study, we investigated behavioral and emotional variances across participants with diverse backgrounds focusing on two conditions: perceived agency and the crowd’s emotional disposition. For perceived agency, one group of participants was told that the other crowd members were avatars controlled by humans, whereas another group was told that they were artificial agents. For emotional disposition, the crowd behaved either in a docile or hostile manner. The results suggest that the crowd’s disposition and specific participant traits significantly affected certain emotions and behaviors. For instance, participants collected fewer items and reported a higher increase of negative emotions when placed in a hostile crowd. However, perceived agency did not yield any statistically significant effects.

Research studies suggest that racial and gender stereotypes can influence emotion recognition accuracy both for adults and children. Stereotypical biases have severe consequences in social life but are especially critical in domains such as education and healthcare, where virtual humans have been extending their applications. In this work, we explore potential perceptual differences in the facial emotion recognition accuracy of virtual humans of different genders, races, and ages. We use realistic 3D models of male/female, Black/White, and child/adult characters. Using blendshapes and the Facial Action Coding System, we created videos of the models displaying facial expressions of six universal emotions with varying intensities. We ran an Amazon Mechanical Turk study to collect perceptual data. The results indicate statistically significant main effects of emotion type and intensity on emotion recognition accuracy. Although overall emotion recognition accuracy was similar across model race, gender, and age groups, there were some statistically significant effects across different groups for individual emotion types.

Metrics of similarity between human motion sequences are central to many motion retrieval, classification, and synthesis techniques. However, research on distance measures shows a lack of correlation between human perception and commonly used metrics such as dynamic time warping distance. This paper analyzes the perception of human motion similarity based on the intrinsic qualities of motion described by the Effort component of Laban Movement Analysis. We conducted an Amazon Mechanical Turk study to collect human judgments on the perceptual similarity of various motion styles to the baseline conditions. The results indicate that Effort factors impacting the flow of movement are perceptually more distinguishable than factors affecting the timing, weight, and spatial attention. The results also confirm the lack of correlation between the human perception of motion similarity and standard measures.

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.

In the social psychology literature, crowds are classified as audiences and mobs. Audiences are passive crowds, whereas mobs are active crowds with emotional, irrational and seemingly homogeneous behavior. In this study, we aim to create a system that enables the specification of different crowd types ranging from audiences to mobs. In order to achieve this goal we parametrize the common properties of mobs to create collective misbehavior. Because mobs are characterized by emotionality, we describe a framework that associates psychological components with individual agents comprising a crowd and yields emergent behaviors in the crowd as a whole. To explore the effectiveness of our framework we demonstrate two scenarios simulating the behavior of distinct mob types.

In this paper, a 3D graphics environment for virtual garment design and simulation is presented. The proposed system enables the three dimensional construction of a garment from its cloth panels, for which the underlying structure is a mass-spring model. The garment construction process is performed through automatic pattern generation, posterior correction, and seaming. Afterwards, it is possible to do fitting on virtual mannequins as if in a real life tailor's workshop. The system provides the users with the flexibility to design their own garment patterns and make changes on the garment even after the dressing of the model. Furthermore, rendering alternatives for the visualization of knitted and woven fabric are presented.