Xueyang Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xueyang Wang has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Xin Yi
Tsinghua University, Beijing, China
9 shared publications - Hewu Li
Tsinghua University, Beijing, China
8 shared publications - Shuning Zhang
Tsinghua University, Beijing, China
3 shared publications - Xinyi Fu
The Future Laboratory, Tsinghua University, Beijing, China
3 shared publications - Kewen Peng
Kahlert School of Computing, University of Utah, Salt Lake City, USA
2 shared publications - Qinxuan Cen
Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Demonstrating Roomify: Spatially-Grounded Style Transformation for Immersive Virtual Environments
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessDemonstrating Roomify: Spatially-Grounded Style Transformation for Immersive Virtual Environments
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Toward Context-Adaptive Extended Reality: Dissolving the Trade-offs between Experience and Protection
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessToward Context-Adaptive Extended Reality: Dissolving the Trade-offs between Experience and Protection
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-22
VisGuardian: A Lightweight Group-based Visual Privacy Control Technique For Smart Glasses in Home Environments
Always-on sensing of AI applications on AR glasses makes traditional permission techniques inefficient for context-dependent private visual data within home environments. Home presents a challenging privacy context due to massive sensitive objects and the intimate nature of daily routines. We propose VisGuardian, a fine-grained content-based visual permission technique for AR glasses. VisGuardian features a group-based control mechanism that enables users to efficiently manage permissions for multiple private objects. VisGuardian detects objects using YOLO and adopts a pre-classified schema to group them. By selecting a single object, users can obscure groups of related objects based on criteria including privacy sensitivity, object category, or spatial proximity. A technical evaluation shows VisGuardian achieves mAP50 of 0.6704 with only 14.0 ms latency and a 1.7% increase in battery consumption per hour. Furthermore, a user study (N=24) comparing VisGuardian to slider-based and object-based baselines found it to be significantly faster for setting permissions and was preferred by users for its efficiency, effectiveness, and ease of use.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Open AccessVisGuardian: A Lightweight Group-based Visual Privacy Control Technique For Smart Glasses in Home Environments
Always-on sensing of AI applications on AR glasses makes traditional permission techniques inefficient for context-dependent private visual data within home environments. Home presents a challenging privacy context due to massive sensitive objects and the intimate nature of daily routines. We propose VisGuardian, a fine-grained content-based visual permission technique for AR glasses. VisGuardian features a group-based control mechanism that enables users to efficiently manage permissions for multiple private objects. VisGuardian detects objects using YOLO and adopts a pre-classified schema to group them. By selecting a single object, users can obscure groups of related objects based on criteria including privacy sensitivity, object category, or spatial proximity. A technical evaluation shows VisGuardian achieves mAP50 of 0.6704 with only 14.0 ms latency and a 1.7% increase in battery consumption per hour. Furthermore, a user study (N=24) comparing VisGuardian to slider-based and object-based baselines found it to be significantly faster for setting permissions and was preferred by users for its efficiency, effectiveness, and ease of use.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-28
Mind the Gap: Mapping Wearer–Bystander Privacy Tensions and Context-Adaptive Pathways for Camera Glasses
Camera glasses create fundamental privacy tensions between wearers seeking recording functionality and bystanders concerned about unauthorized surveillance. We present a systematic multi-stakeholder evaluation of privacy mechanisms through surveys (N=525) and paired interviews (N=20) in China. Study 1 quantifies expectation-willingness gaps: bystanders consistently demand stronger information transparency and protective measures than wearers will provide, with disparities intensifying in sensitive contexts where 65–90% of bystanders would take defensive action. Study 2 evaluates twelve privacy-enhancing technologies, revealing four fundamental trade-offs that undermine current approaches: visibility versus disruption, empowerment versus burden, protection versus agency, and accountability versus exposure. These gaps reflect structural incompatibilities rather than inadequate goodwill, with context emerging as the primary determinant of privacy acceptability. We propose context-adaptive pathways that dynamically adjust protection strategies: minimal-friction visibility in public spaces, structured negotiation in semi-public environments, and automatic protection in sensitive contexts. Our findings contribute a diagnostic framework for evaluating privacy mechanisms and implications for context-aware design in ubiquitous sensing.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-28
Open AccessMind the Gap: Mapping Wearer–Bystander Privacy Tensions and Context-Adaptive Pathways for Camera Glasses
Camera glasses create fundamental privacy tensions between wearers seeking recording functionality and bystanders concerned about unauthorized surveillance. We present a systematic multi-stakeholder evaluation of privacy mechanisms through surveys (N=525) and paired interviews (N=20) in China. Study 1 quantifies expectation-willingness gaps: bystanders consistently demand stronger information transparency and protective measures than wearers will provide, with disparities intensifying in sensitive contexts where 65–90% of bystanders would take defensive action. Study 2 evaluates twelve privacy-enhancing technologies, revealing four fundamental trade-offs that undermine current approaches: visibility versus disruption, empowerment versus burden, protection versus agency, and accountability versus exposure. These gaps reflect structural incompatibilities rather than inadequate goodwill, with context emerging as the primary determinant of privacy acceptability. We propose context-adaptive pathways that dynamically adjust protection strategies: minimal-friction visibility in public spaces, structured negotiation in semi-public environments, and automatic protection in sensitive contexts. Our findings contribute a diagnostic framework for evaluating privacy mechanisms and implications for context-aware design in ubiquitous sensing.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-24
Roomify: Spatially-Grounded Style Transformation for Immersive Virtual Environments
We present Roomify, a spatially-grounded transformation system that generates themed virtual environments anchored to users’ physical rooms while maintaining spatial structure and functional semantics. Current VR approaches face a fundamental trade-off: full immersion sacrifices spatial awareness, while passthrough solutions break presence. Roomify addresses this through spatially-grounded transformation—treating physical spaces as “spatial containers” that preserve key functional and geometric properties of furniture while enabling radical stylistic changes. Our pipeline combines in-situ 3D scene understanding, AI-driven spatial reasoning, and style-aware generation to create personalized virtual environments grounded in physical reality. We introduce a cross-reality authoring tool enabling fine-grained user control through MR editing and VR preview workflows. Two user studies validate our approach: one with 18 VR users demonstrates a 63% improvement in presence over passthrough and 26% over fully virtual baselines while maintaining spatial awareness; another with 8 design professionals confirms the system’s creative expressiveness (scene quality: 5.95/7; creativity support: 6.08/7) and professional workflow value across diverse environments.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-24
Open AccessRoomify: Spatially-Grounded Style Transformation for Immersive Virtual Environments
We present Roomify, a spatially-grounded transformation system that generates themed virtual environments anchored to users’ physical rooms while maintaining spatial structure and functional semantics. Current VR approaches face a fundamental trade-off: full immersion sacrifices spatial awareness, while passthrough solutions break presence. Roomify addresses this through spatially-grounded transformation—treating physical spaces as “spatial containers” that preserve key functional and geometric properties of furniture while enabling radical stylistic changes. Our pipeline combines in-situ 3D scene understanding, AI-driven spatial reasoning, and style-aware generation to create personalized virtual environments grounded in physical reality. We introduce a cross-reality authoring tool enabling fine-grained user control through MR editing and VR preview workflows. Two user studies validate our approach: one with 18 VR users demonstrates a 63% improvement in presence over passthrough and 26% over fully virtual baselines while maintaining spatial awareness; another with 8 design professionals confirms the system’s creative expressiveness (scene quality: 5.95/7; creativity support: 6.08/7) and professional workflow value across diverse environments.
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Actual Achieved Gain and Optimal Perceived Gain: Modeling Human Take-over Decisions Towards Automated Vehicles' Suggestions
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Open AccessActual Achieved Gain and Optimal Perceived Gain: Modeling Human Take-over Decisions Towards Automated Vehicles' Suggestions
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (5) , 3459-3469
VR Whispering: A Multisensory Approach for Private Conversations in Social Virtual Reality
Private conversations in social Virtual Reality (VR) environments lack the nuanced cues of physical interactions, potentially diminishing the sense of privacy and social presence. This paper introduces Whisper, a novel multisensory interaction technique designed to enhance private conversations for social VR applications. We first conducted a formative study (N=20) to understand private conversation demands, limitations of existing methods, and user expectations in social VR. Informed by these insights, Whisper incorporates visual (avatar proximity, gestures and illumination), auditory (voice conversation), and tactile (simulated airflow) elements to simulate the act of whispering, providing users with an intuitive and immersive method of private communication. The technique also features a contextual record to maintain conversation continuity. We evaluated Whisper through a comparative user study (N=24) in party and classroom scenarios. Results demonstrate that Whisper significantly outperforms existing methods in sense of privacy, mode distinguishability, intimacy, perceptual realism, and social presence.
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (5) , 3459-3469
VR Whispering: A Multisensory Approach for Private Conversations in Social Virtual Reality
Private conversations in social Virtual Reality (VR) environments lack the nuanced cues of physical interactions, potentially diminishing the sense of privacy and social presence. This paper introduces Whisper, a novel multisensory interaction technique designed to enhance private conversations for social VR applications. We first conducted a formative study (N=20) to understand private conversation demands, limitations of existing methods, and user expectations in social VR. Informed by these insights, Whisper incorporates visual (avatar proximity, gestures and illumination), auditory (voice conversation), and tactile (simulated airflow) elements to simulate the act of whispering, providing users with an intuitive and immersive method of private communication. The technique also features a contextual record to maintain conversation continuity. We evaluated Whisper through a comparative user study (N=24) in party and classroom scenarios. Results demonstrate that Whisper significantly outperforms existing methods in sense of privacy, mode distinguishability, intimacy, perceptual realism, and social presence.
- Open Access
- 11 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 147-153
The Synergy of Dialogue and Art: Exploring the Potential of Multimodal AI Chatbots in Emotional Support
The rapid advancements in generative AI have spurred the development of AI chatbots for emotional support. In this work, we designed ArtTheraCat, a novel multimodal chatbot that promotes mental health by integrating supportive dialogue with artistic image generation. Utilizing images as an auxiliary medium, ArtTheraCat guides users through a process of emotion externalization in multi-turn dialogues, which can facilitates self-awareness, reflection, and positive emotional encouragement. Results from a user study involving 21 participants indicate a significant improvement in their emotional state post-interaction with ArtTheraCat, especially in reducing negative affects. Qualitative analysis highlighted the role of generated images as a non-verbal medium in emotional release and self-insight. The findings of this paper provide practical guidance for the design of multimodal mental health chatbots.
- 11 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 147-153
Open AccessThe Synergy of Dialogue and Art: Exploring the Potential of Multimodal AI Chatbots in Emotional Support
The rapid advancements in generative AI have spurred the development of AI chatbots for emotional support. In this work, we designed ArtTheraCat, a novel multimodal chatbot that promotes mental health by integrating supportive dialogue with artistic image generation. Utilizing images as an auxiliary medium, ArtTheraCat guides users through a process of emotion externalization in multi-turn dialogues, which can facilitates self-awareness, reflection, and positive emotional encouragement. Results from a user study involving 21 participants indicate a significant improvement in their emotional state post-interaction with ArtTheraCat, especially in reducing negative affects. Qualitative analysis highlighted the role of generated images as a non-verbal medium in emotional release and self-insight. The findings of this paper provide practical guidance for the design of multimodal mental health chatbots.
- Open Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Modeling the Trade-off of Privacy Preservation and Activity Recognition on Low-Resolution Images
A computer vision system using low-resolution image sensors can provide intelligent services (e.g., activity recognition) but preserve unnecessary visual privacy information from the hardware level. However, preserving visual privacy and enabling accurate machine recognition have adversarial needs on image resolution. Modeling the trade-off of privacy preservation and machine recognition performance can guide future privacy-preserving computer vision systems using low-resolution image sensors. In this paper, using the at-home activity of daily livings (ADLs) as the scenario, we first obtained the most important visual privacy features through a user survey. Then we quantified and analyzed the effects of image resolution on human and machine recognition performance in activity recognition and privacy awareness tasks. We also investigated how modern image super-resolution techniques influence these effects. Based on the results, we proposed a method for modeling the trade-off of privacy preservation and activity recognition on low-resolution images.
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessModeling the Trade-off of Privacy Preservation and Activity Recognition on Low-Resolution Images
A computer vision system using low-resolution image sensors can provide intelligent services (e.g., activity recognition) but preserve unnecessary visual privacy information from the hardware level. However, preserving visual privacy and enabling accurate machine recognition have adversarial needs on image resolution. Modeling the trade-off of privacy preservation and machine recognition performance can guide future privacy-preserving computer vision systems using low-resolution image sensors. In this paper, using the at-home activity of daily livings (ADLs) as the scenario, we first obtained the most important visual privacy features through a user survey. Then we quantified and analyzed the effects of image resolution on human and machine recognition performance in activity recognition and privacy awareness tasks. We also investigated how modern image super-resolution techniques influence these effects. Based on the results, we proposed a method for modeling the trade-off of privacy preservation and activity recognition on low-resolution images.