Xiaoping Che
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaoping Che has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
Chenxin Qu
Beijing Jiaotong University, Beijing, China
5 shared publicationsEnyao Chang
School of Software Engineering, Beijing Jiaotong University
5 shared publications- Xiaofei Di
Beijing Jiaotong University
4 shared publications - Chenxin Qu
School of Software Engineering, Beijing Jiaotong University, Beijing, China
3 shared publications - Enyao Chang
School of Software Engineering, Beijing Jiaotong University
3 shared publications Jianing Zhang
School of Software Engineering, Beijing Jiaotong University
3 shared publications
Latest Publications
- 7 October 2026
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- p. 1-27
Confidence-Aware Gaze-Depth Interaction for Reliable 3D Target Selection in Consumer VR Headsets
1. Eye gaze has long been regarded as a promising input modality for human–computer interaction because it is fast, natural, and closely coupled with visual attention. Early work on eye movement-ba...
- 7 October 2026
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- p. 1-27
Confidence-Aware Gaze-Depth Interaction for Reliable 3D Target Selection in Consumer VR Headsets
1. Eye gaze has long been regarded as a promising input modality for human–computer interaction because it is fast, natural, and closely coupled with visual attention. Early work on eye movement-ba...
- 2 September 2026
- Published by Springer Nature
- p. 405-419
Ranim: A High-Performance Extensible Programmatic Animation Engine Based on WebGPU and Rust
- 2 September 2026
- Published by Springer Nature
- p. 405-419
Ranim: A High-Performance Extensible Programmatic Animation Engine Based on WebGPU and Rust
- Open Access
- 23 August 2026
- Published by Springer Nature in Virtual Reality
Investigating the impact of visual reference grids on the calibration of auditory distance perception from different directions in VR
- 23 August 2026
- Published by Springer Nature in Virtual Reality
Open AccessInvestigating the impact of visual reference grids on the calibration of auditory distance perception from different directions in VR
- Open Access
- 8 July 2026
- Published by Frontiers Media SA in Frontiers in Psychology
- Vol. 17, 1886780
Designing and evaluating LLM-driven coaching agents for VR public speaking practice
Introduction: Public speaking practice in Virtual Reality (VR) provides an immersive and controllable setting, yet many existing systems offer limited adaptive guidance beyond exposure itself. Recent advances in Large Language Models (LLMs) create opportunities for designing coaching interactions that are personalized, context-aware, and socially supportive. Methods: We designed a VR public speaking system in which embodied virtual judges delivered spoken and textual, performance-contingent coaching based on automatic speech recognition, speech synthesis, gaze-related cues, and structured prompting with ERNIE Bot. We evaluated the system in a two-arm randomized controlled user study with 120 participants, with 60 participants assigned to the adaptive coaching condition and 60 to an attention-matched generic feedback control condition. Participants completed two rounds of VR speeches with repeated pre- and post-speech self-report assessments, followed by matched follow-up sessions at one week and one month. Results: Compared with attention-matched generic feedback, the adaptive coaching condition was associated with larger reductions in self-reported state anxiety and PRCA-derived public speaking anxiety appraisals across repeated speaking rounds. At follow-up sessions conducted in the same VR environment without additional coaching, lower self-reported anxiety remained observable in the experimental group. Qualitative feedback suggested that participants experienced the agents as supportive, useful, and lower-pressure, while also noting limitations in realism, speech prosody, and interaction richness. Discussion: The findings provide preliminary evidence that embodied LLM-based coaching can support anxiety-aware VR public speaking practice. However, because the study relied primarily on self-report, did not include physiological outcomes or blinded external performance ratings, and involved repeated exposure to the same VR context, the follow-up findings should be interpreted as maintenance within the VR practice setting rather than evidence of stable trait change, objective performance improvement, or real-world transfer. Future studies should examine whether these self-reported gains generalize to real-world speaking contexts and externally rated public speaking performance.
- 8 July 2026
- Published by Frontiers Media SA in Frontiers in Psychology
- Vol. 17, 1886780
Open AccessDesigning and evaluating LLM-driven coaching agents for VR public speaking practice
Introduction: Public speaking practice in Virtual Reality (VR) provides an immersive and controllable setting, yet many existing systems offer limited adaptive guidance beyond exposure itself. Recent advances in Large Language Models (LLMs) create opportunities for designing coaching interactions that are personalized, context-aware, and socially supportive. Methods: We designed a VR public speaking system in which embodied virtual judges delivered spoken and textual, performance-contingent coaching based on automatic speech recognition, speech synthesis, gaze-related cues, and structured prompting with ERNIE Bot. We evaluated the system in a two-arm randomized controlled user study with 120 participants, with 60 participants assigned to the adaptive coaching condition and 60 to an attention-matched generic feedback control condition. Participants completed two rounds of VR speeches with repeated pre- and post-speech self-report assessments, followed by matched follow-up sessions at one week and one month. Results: Compared with attention-matched generic feedback, the adaptive coaching condition was associated with larger reductions in self-reported state anxiety and PRCA-derived public speaking anxiety appraisals across repeated speaking rounds. At follow-up sessions conducted in the same VR environment without additional coaching, lower self-reported anxiety remained observable in the experimental group. Qualitative feedback suggested that participants experienced the agents as supportive, useful, and lower-pressure, while also noting limitations in realism, speech prosody, and interaction richness. Discussion: The findings provide preliminary evidence that embodied LLM-based coaching can support anxiety-aware VR public speaking practice. However, because the study relied primarily on self-report, did not include physiological outcomes or blinded external performance ratings, and involved repeated exposure to the same VR context, the follow-up findings should be interpreted as maintenance within the VR practice setting rather than evidence of stable trait change, objective performance improvement, or real-world transfer. Future studies should examine whether these self-reported gains generalize to real-world speaking contexts and externally rated public speaking performance.
- Open Access
- 24 November 2025
- Published by Frontiers Media SA in Frontiers in Psychology
- Vol. 16, 1709943
Enhancing emotion recognition in virtual reality: a multimodal dataset and a temporal emotion detector
Emotion is a complex psychophysiological phenomenon elicited by external stimuli, exerting a profound influence on cognitive processes, decision-making, and social behavior. Emotion recognition holds broad application potential in healthcare, education, and entertainment. With virtual reality (VR) emerging as a powerful tool, it offers an immersive and controllable experimental environment. Prior studies have confirmed the feasibility and advantages of VR for emotion elicitation and recognition, and multimodal fusion has become a key strategy for enhancing recognition accuracy. However, publicly available VR multimodal emotion datasets remain limited in both scale and diversity due to the scarcity of VR content and the complexity of data collection. The shortage hampers further progress. Moreover, existing multimodal approaches still face challenges such as noise interference, large inter-individual variability, and insufficient model generalization. Achieving robust and accurate physiological signal processing and emotion modeling in VR environments thus remains an open challenge. To address the issues, we constructed a VR experimental environment and selected 10 emotion-eliciting video clips guided by the PAD(Pleasure-Arousal-Dominance) model. Thirty-eight participants (N=38) were recruited, from whom electrodermal activity, eye-tracking, and questionnaire data were collected, yielding 366 valid trials. The newly collected dataset substantially extends the publicly available VREED dataset, enriching VR-based multimodal emotion resources. Furthermore, we propose the MMTED model (Multi-Modal Temporal Emotion Detector), which incorporates baseline calibration and multimodal fusion of electrodermal and eye-tracking signals for emotion recognition. Experimental results demonstrate the strong performance of the MMTED model, achieving accuracies of 85.52% on the public VREED dataset, 89.27% on our self-collected dataset, and 85.29% on their combination.
- 24 November 2025
- Published by Frontiers Media SA in Frontiers in Psychology
- Vol. 16, 1709943
Open AccessEnhancing emotion recognition in virtual reality: a multimodal dataset and a temporal emotion detector
Emotion is a complex psychophysiological phenomenon elicited by external stimuli, exerting a profound influence on cognitive processes, decision-making, and social behavior. Emotion recognition holds broad application potential in healthcare, education, and entertainment. With virtual reality (VR) emerging as a powerful tool, it offers an immersive and controllable experimental environment. Prior studies have confirmed the feasibility and advantages of VR for emotion elicitation and recognition, and multimodal fusion has become a key strategy for enhancing recognition accuracy. However, publicly available VR multimodal emotion datasets remain limited in both scale and diversity due to the scarcity of VR content and the complexity of data collection. The shortage hampers further progress. Moreover, existing multimodal approaches still face challenges such as noise interference, large inter-individual variability, and insufficient model generalization. Achieving robust and accurate physiological signal processing and emotion modeling in VR environments thus remains an open challenge. To address the issues, we constructed a VR experimental environment and selected 10 emotion-eliciting video clips guided by the PAD(Pleasure-Arousal-Dominance) model. Thirty-eight participants (N=38) were recruited, from whom electrodermal activity, eye-tracking, and questionnaire data were collected, yielding 366 valid trials. The newly collected dataset substantially extends the publicly available VREED dataset, enriching VR-based multimodal emotion resources. Furthermore, we propose the MMTED model (Multi-Modal Temporal Emotion Detector), which incorporates baseline calibration and multimodal fusion of electrodermal and eye-tracking signals for emotion recognition. Experimental results demonstrate the strong performance of the MMTED model, achieving accuracies of 85.52% on the public VREED dataset, 89.27% on our self-collected dataset, and 85.29% on their combination.
- 28 April 2025
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 41 (23) , 15025-15039
User Audio Intelligibility, Recall and Immersion in Virtual Reality Environment
- 28 April 2025
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 41 (23) , 15025-15039
User Audio Intelligibility, Recall and Immersion in Virtual Reality Environment
- Open Access
- 28 March 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-16
Similarity based city data transfer framework in urban digitization
Cross-city transfer learning aims to apply the knowledge and model from data-rich cities to data-poor cities to solve the cold start problem. Existing methods directly transfer the model constructed from developed cities to underdeveloped cities without considering the similarity between them, which leads to a potential transfer mismatch problem, and in turn, decreases the performance of transfer results. Meanwhile, existing transfer learning methods cannot effectively extract the time series features of the data, resulting in the inability to achieve adaptive positive migration across cities. To solve this problem, we propose a similarity-based cross-city transfer learning method named TransCSM, which embeds the urban similarity into an adaptation transfer learning framework to achieve desired data transfer. Specifically, we first constructed an urban similarity model, which utilizes the urban POI (Point Of Interest) data to group the cities with similar characteristics into the same cluster. Then, we build a feature extractor network, that uses convolution neural network (CNN) and Gated Recurrent Unit (GRU) to extract more representative features of time series data. Afterwards, we build an adaptation transfer learning framework to achieve data transfer within the same city cluster, which ensures the reliability of cross-city data transferring results. Finally, we evaluate our proposed method in many public POI datasets from Baidu Map API, and enormous results have demonstrated that our proposed method can achieve superior performance against state-of-the-art methods.
- 28 March 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-16
Open AccessSimilarity based city data transfer framework in urban digitization
Cross-city transfer learning aims to apply the knowledge and model from data-rich cities to data-poor cities to solve the cold start problem. Existing methods directly transfer the model constructed from developed cities to underdeveloped cities without considering the similarity between them, which leads to a potential transfer mismatch problem, and in turn, decreases the performance of transfer results. Meanwhile, existing transfer learning methods cannot effectively extract the time series features of the data, resulting in the inability to achieve adaptive positive migration across cities. To solve this problem, we propose a similarity-based cross-city transfer learning method named TransCSM, which embeds the urban similarity into an adaptation transfer learning framework to achieve desired data transfer. Specifically, we first constructed an urban similarity model, which utilizes the urban POI (Point Of Interest) data to group the cities with similar characteristics into the same cluster. Then, we build a feature extractor network, that uses convolution neural network (CNN) and Gated Recurrent Unit (GRU) to extract more representative features of time series data. Afterwards, we build an adaptation transfer learning framework to achieve data transfer within the same city cluster, which ensures the reliability of cross-city data transferring results. Finally, we evaluate our proposed method in many public POI datasets from Baidu Map API, and enormous results have demonstrated that our proposed method can achieve superior performance against state-of-the-art methods.
- 1 March 2025
- Published by Springer Nature
- p. 71-83
Physiological Factors Based Depression Assessment in Virtual Reality
- 1 March 2025
- Published by Springer Nature
- p. 71-83
Physiological Factors Based Depression Assessment in Virtual Reality
- Open Access
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 143252-143262
Study of Cybersickness in Augmented Reality Railway Inspections Applications
The development of augmented reality (AR) has brought innovation to the working mode in multiple fields to improve the efficiency of multi-party cooperation and the safety rate of operations. However, when users use AR technology, they will inevitably suffer from cybersickness, which may cause symptoms such as nausea, dizziness, eye fatigue, and headaches, severely reducing their experience. Still, there is limited research on AR cybersickness, compared to cybersickness in virtual reality (VR). The causes and symptoms of cybersickness in AR and VR are different, therefore some conclusions in VR may not be applicable. Also, the current research scenarios related to AR cybersickness lack diversity, which is not conducive to the study of the causes of cybersickness. The paper mainly studies the cybersickness in AR railway inspection scenarios, including the causes (latency and the number of interactions) and the symptoms. 54 volunteers were recruited for the experiment, and we defined three latency types and three interaction types based on related interaction criteria. Then we designed a 3 * 3 experiment with latency and interaction quantity as variables. We conducted statistical analysis on the ARSQ data and experimental data. The results show that the severity of cybersickness in AR railway inspections is significantly positively correlated with the number of interactions and latency. Oculomotor is also significantly correlated with the two variables, while the severity of disorientation is not significantly correlated with latency. Besides, it was also observed that in AR, the severity of oculomotor is much higher than disorientation.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 143252-143262
Open AccessStudy of Cybersickness in Augmented Reality Railway Inspections Applications
The development of augmented reality (AR) has brought innovation to the working mode in multiple fields to improve the efficiency of multi-party cooperation and the safety rate of operations. However, when users use AR technology, they will inevitably suffer from cybersickness, which may cause symptoms such as nausea, dizziness, eye fatigue, and headaches, severely reducing their experience. Still, there is limited research on AR cybersickness, compared to cybersickness in virtual reality (VR). The causes and symptoms of cybersickness in AR and VR are different, therefore some conclusions in VR may not be applicable. Also, the current research scenarios related to AR cybersickness lack diversity, which is not conducive to the study of the causes of cybersickness. The paper mainly studies the cybersickness in AR railway inspection scenarios, including the causes (latency and the number of interactions) and the symptoms. 54 volunteers were recruited for the experiment, and we defined three latency types and three interaction types based on related interaction criteria. Then we designed a 3 * 3 experiment with latency and interaction quantity as variables. We conducted statistical analysis on the ARSQ data and experimental data. The results show that the severity of cybersickness in AR railway inspections is significantly positively correlated with the number of interactions and latency. Oculomotor is also significantly correlated with the two variables, while the severity of disorientation is not significantly correlated with latency. Besides, it was also observed that in AR, the severity of oculomotor is much higher than disorientation.