Zhaoquan Yuan is currently an Associate Professor in the School of Computing and Artificial Intelligence at Southwest Jiaotong University (SWJTU), Chengdu, China. He received his bachelor's degree in Computer Science and Technology from the University of Science and Technology of China (USTC), and his Ph.D. in Pattern Recognition and Intelligent Systems from the Institute of Automation, Chinese Academy of Sciences (CASIA), under the supervision of Prof. Changsheng Xu and the co-supervision of Prof. Jitao Sang. He also undertook research visits at the China-Singapore Institute of Digital Media and the Department of Computing at The Hong Kong Polytechnic University during his doctoral studies.
His research interests span computer vision, generative AI, and causal intelligence, with a particular focus on physics-aware 4D reconstruction and generation.
Address: No. 999, Xi'an Road, Pidu District, Chengdu, China PR. Postcode: 611756.
袁召全，现任西南交通大学计算机与人工智能学院副教授，硕士生导师，计算机科学与技术系主任。本科毕业于中国科学技术大学计算机科学与技术学院，博士毕业于中国科学院大学（中国科学院自动化研究所）。曾先后赴中国-新加坡数字媒体研究院、香港理工大学计算机科学系交流访问。主要研究方向包括计算机视觉、生成式人工智能、因果智能，当前重点聚焦物理感知的动态场景重建与生成、智能情报分析。近年来在CVPR、AAAI、ACM MM、IEEE TMM、IJCAI等国际学术会议及期刊发表论文近40篇。曾获ACM MM Asia 2024最佳论文奖、MMM 2021最佳论文奖、2024年度中国发明协会发明创业奖创新奖二等奖、2024年度广西应急管理协会安全科技进步奖。多次担任CVPR、NeurIPS、AAAI、ACM MM、ACL、IJCAI等国际会议程序委员会委员，并担任多个IEEE Transactions、ACM Transactions系列期刊审稿人。先后主持国家自然科学基金面上项目与青年项目、四川省自然科学基金面上项目，以及中国电科、中国民航、中国科学院等单位的横向科技项目。
欢迎满足以下条件的同学加入课题组：
（1）自驱力强，对学术探索或工程技术具有浓厚兴趣与持续热情；
（2）数学与编程基础扎实，对计算机视觉、生成式人工智能、因果智能、强化学习等人工智能前沿方向感兴趣；
（3）责任心强，具备良好的团队合作精神，诚信可靠。
有意向的同学请邮件联系：zqyuancs@gmail.com
Jian-Jun Qiao, Xiao Wu, Zhi-Qi Cheng, Wei Li, Zhaoquan Yuan.
PSGNet: Pure Smoke Image Generation With Gradient and Style Learning.
IEEE Transactions on Visualization and Computer Graphics. 32(7):7259-7272, 2026. (TVCG, CCF-A)
Yuankang Pan, Zhaoquan Yuan*, Fangying Xiong, Ao Luo, Wei Li, Xiao Wu.
LAMDA: Low-Rank Magnitude–Direction Adaptation for Class-Incremental Object Detection.
Proceedings of the 34th ACM International Conference on Multimedia, 2026. DOI: 10.1145/3767308.3835161. (Oral, ACM MM, CCF-A)
Ao Luo, XIN LI, Fan Yang, Yuezun Li, Zhaoquan Yuan, SHAN ZHAO, Bing Su, Xiao Wu.
Optical Flow Matching: Reframing Optical Flow as Continuous Transport Dynamics.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026. (CVPR, CCF-A)
Yuankang Pan, Zhaoquan Yuan*, Xiao Wu, Wei Li, Ao Luo, and Changsheng Xu.
Learning Unknowns without Forgetting Knowns: Compositional and Bidirectional Low-Rank Adaptive OpenWorld Detection Transformer.
IEEE Transactions on Circuits and Systems for Video Technology, 17 February 2026. DOI: 10.1109/TCSVT.2026.3665637. (TCSVT, 中科院1区)
Zhaoquan Yuan, Zining Wang, Yuankang Pan, Ao Luo, Wei Li, Xiao Wu, and Changsheng Xu.
I2CD: An Invertible Causal Framework for Compositional Zero-Shot Learning via Disentangle-Compose-Disentangle.
The AAAI Conference on Artificial Intelligence, 40(15), 12295-12303. January 20–January 27, 2026, Singapore. DOI: https://doi.org/10.1609/aaai.v40i15.38221 (AAAI, CCF-A)
Wei Li, Long Ji, Ying Wang, Xiao Wu, Zhaoquan Yuan*, Penglin Dai.
Monocular Vehicle Pose and Shape Reconstruction via Dynamic Context Adaptation and Progressive Geometry Refinement.
The AAAI Conference on Artificial Intelligence, January 20–January 27, 2026, Singapore. (AAAI, CCF-A)
Fangying Xiong, Zhaoquan Yuan*, Xiao Wu, and Changsheng Xu.
Class-Specific Knowledge-Guided Multimodal Prompt Tuning for Few-Shot Class-Incremental Learning.
IEEE Transactions on Circuits and Systems for Video Technology, 11 August 2025. DOI: 10.1109/TCSVT.2025.3597447. (TCSVT, 中科院1区)
陈智能，袁召全*，杨小汕，曹艺馨，李亮，吴晓，鲍秉坤.
跨模态3D生成：原理、方法与前沿进展
中国图象图形学报，2026:1-37. DOI:10.11834/jig.250655.
Yuankang Pan, Zhaoquan Yuan*, Xiao Wu, Zechao Li, and Changsheng Xu.
THMM-CLIP: Task-Guided Hierarchical Multi-Modal Alignment for Rehearsal-Free Class Incremental Learning.
ACM Transactions on Multimedia Computing, Communications, and Applications, 2025. DOI: 10.1145/3785477. (TOMM)
Yuankang Pan, Zining Wang, Zhaoquan Yuan*, and Wei Li.
Energy-Based Causal Disentanglement for Compositional Zero-Shot Learning.
Multimedia Systems, Volume 32, article number 6, 2026. https://doi.org/10.1007/s00530-025-02064-1.
Xiang Huang, Ao Luo, Xiao Wu, and Zhaoquan Yuan.
Latent Interactiveness Field for Non-Contact Human Object Interaction Detection.
Proceedings of the 33rd ACM International Conference on Multimedia, Oct 27-31, 2025, Dublin, Ireland. (ACM MM, CCF-A)
Qi He, Xiao Wu, Jun-Yan He, Wei Li, and Zhaoquan Yuan.
DualEnhance: External Multimodal Foundation Models Guidance and Internal Fast-Slow Teacher Regulation.
Proceedings of the 33rd ACM International Conference on Multimedia, Oct 27-31, 2025, Dublin, Ireland. (ACM MM, CCF-A)
Wei Li, Yizhao Wan, Xiao Wu, Jianshuai Wang, Penglin Dai, and Zhaoquan Yuan.
HOPNet: Learning Hand-Object-Person Interaction Network for Hand Contact State Detection.
Proceedings of the 33rd ACM International Conference on Multimedia, Oct 27-31, 2025, Dublin, Ireland. (ACM MM, CCF-A)
Mingxuan Zhang, Qi He, Zhaoquan Yuan*, Tingquan He, and Rong Li.
HOOI Detection: Cascade-Clue Integrated Modeling over Multiple Temporal Segments.
Proceedings of the 2025 International Conference on Multimedia Retrieval, Pages 1786-1794,
June 30-July 3, 2025, Chicago, USA. https://doi.org/10.1145/3731715.3733360. (ICMR)
Zhaoquan Yuan, Chengbin Zhao, Yuting Tang, Lishu Guo, Xiao Wu, and Changsheng Xu.
Contrastive Invariant Risk Minimization for Grounded Situation Recognition.
IEEE International Conference on Multimedia & Expo, June 30-July 4, 2025. Nantes, France.
DOI: 10.1109/ICME59968.2025.11210121. (ICME)
Zhou Du, Zhaoquan Yuan*, Xiao Wu, and Changsheng Xu.
Disentanglement-based Equivariant Learning for Compositional VQA.
IEEE Transactions on Multimedia,September 01, 2025. DOI: 10.1109/TMM.2025.3604897 (TMM, 中科院1区)
Xuan Yao, Xiao Peng, Junyu Gao, Zhaoquan Yuan, Xiao Wu, and Changsheng Xu.
Active Cross-modal Domain Adaptation.
IEEE Transactions on Multimedia, 2025. (TMM, 中科院1区)
Yuankang Pan, Zhaoquan Yuan, Xiao Wu, Zechao Li, and Changsheng Xu.
TMM-CLIP: Task-guided Multi-Modal Alignment for Rehearsal-Free Class Incremental Learning.
Proceedings of ACM Multimedia Asia, pp. 1-7. December 03–06, 2024, Auckland, New Zealand.
https://doi.org/10.1145/3696409.3700182.
(MM Asia, 最佳论文奖 )
Chongyang Xiang, Xiao Wu, Jun-Yan He, Zhaoquan Yuan, and Tingquan He.
Person in Uniforms Re-Identification.
ACM Transactions on Multimedia Computing Communications and Applications, Volume 21, Issue 2, pp. 1-23, 2024.
https://doi.org/10.1145/3703839.
Yu-Pei Song, Yuantong Liu, Xiao Wu, Qi He, Zhaoquan Yuan, and Ao Luo.
MagicCartoon: 3D Pose and Shape Estimation for Bipedal Cartoon Characters.
Proceedings of the 32nd ACM International Conference on Multimedia, pp. 8219-8227. Oct 28–Nov 1, 2024, Melbourne, Australia. (ACM MM, CCF-A)
Yu-Pei Song, Xiao Wu, Zhaoquan Yuan, Jian-Jun Qiao, and Qiang Peng.
PostureHMR: Posture Transformation for 3D Human Mesh Recovery.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9732-9741. June 19-21, 2024. Seattle WA, USA. (CVPR, CCF-A)
Ming-Xuan Zhang, Xiao Wu, Zhaoquan Yuan, Qi He, and Xiang Huang.
Human-Object-Object Interaction: Towards Human-Centric Complex Interaction Detection.
Proceedings of the 31st ACM International Conference on Multimedia, pp. 2233-2242. Oct 29–Nov 3, 2023. Ottawa, Canada. (ACM MM, CCF-A)
Ying Shen, Wei Li, Zhaoquan Yuan, and Xiao Wu.
Learning Surface-awareness Network for X-Ray Prohibited Item Detection.
Proceedings of the 5th ACM International Conference on Multimedia in Asia, pp. 1-5. Dec 6-8, 2023. Tainan Taiwan.
Qi He, Zhaoquan Yuan*, Xiao Wu, and Jun-Yan He.
Domain-Specific Conditional Jigsaw Adaptation for Enhancing Transferability and Discriminability.
Proceedings of the 30th ACM International Conference on Multimedia, pp. 6327-6336. Oct 10-14, 2022.
Lisbon Portugal. https://doi.org/10.1145/3503161.3547890. (ACM MM, CCF-A)
Wei Li, Tianzhao Yang, Xiao Wu, and Zhaoquan Yuan.
Learning Graph-based Residual Aggregation Network for Group Activity Recognition.
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, pp. 1102-1108. July 23-29, 2022.
Messe Wien, Vienna, Austria. (IJCAI, CCF-A)
Zhaoquan Yuan, Xiao Peng, Xiao Wu*, and Changsheng Xu.
Hierarchical Multi-Task Learning for Diagram Question Answering with Multi-Modal Transformer.
Proceedings of the 29th ACM International Conference on Multimedia, pp. 1313-1321. Oct 20-24, 2021. Chengdu, China. (ACM MM, CCF-A)
Zhaoquan Yuan, Siyuan Sun, Lixin Duan*, Changsheng Li*, Xiao Wu, and Changsheng Xu.
Adversarial Multimodal Network for Movie Story Question Answering.
IEEE Transactions on Multimedia, vol. 23, pp. 1744-1756, 2021. (TMM, 中科院1区)
Zhaoquan Yuan, Xiao Peng, Xiao Wu*, Bingkun Bao, and Changsheng Xu.
Meta-Learning Causal Feature Selection for Stable Prediction.
2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1-6. IEEE. July 5-9, 2021. Shenzhen, China. (ICME, CCF-B)
Huan Shao, Zhaoquan Yuan*, Xiao Peng, and Xiao Wu.
Contrastive Learning in Frequency Domain for Non-I.I.D. Image Classification.
Proceedings of the 27th International Conference on Multimedia Modeling, pp. 111-122. June 22–24, 2021. Prague, Czech Republic.
(MMM, 最佳论文奖 )
Jun-Yan He, Xiao Wu, Zhi-Qi Cheng, Zhaoquan Yuan, and Yu-Gang Jiang.
DB-LSTM: Densely-Connected Bi-directional LSTM for Human Action Recognition.
Neurocomputing, 444, pp.319-331, 2021 (中科院1区)
Zhaoquan Yuan, Changsheng Xu*, Jitao Sang, Shuicheng Yan, and M. Shamim Hossain.
Learning Feature Hierarchies: A Layer-Wise Tag-Embedded Approach.
IEEE Transactions on Multimedia, vol. 17, no. 6, pp. 816-827, 2015. (TMM, 中科院1区)
Zhaoquan Yuan, Jitao Sang, Changsheng Xu*, and Yan Liu.
A Unified Framework of Latent Feature Learning in Social Media.
IEEE Transactions on Multimedia, vol. 16, no. 6, pp. 1624-1635, 2014. (TMM, 中科院1区)
Zhaoquan Yuan, Jitao Sang, Yan Liu, and Changsheng Xu*.
Latent Feature Learning in Social Media Network.
Proceedings of the 21st ACM international conference on Multimedia, pp. 253-262. Oct 21-25, 2013. Barcelona, Spain. (ACM MM, CCF-A)
Zhaoquan Yuan, Jitao Sang, and Changsheng Xu*.
Tag-aware Image Classification via Nested Deep Belief Nets.
2013 IEEE international conference on Multimedia and Expo, pp. 1-6. IEEE. July 15-19, 2013. San Jose, CA, USA. (ICME)
Last updated date: Aug 26, 2026.