Zhaoquan Yuan

Associate Professor, Ph.D.

School of Computing and Artificial Intelligence, Southwest Jiaotong University

Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, China

contact

ADRESS: No. 999, Xi'an Road, Pidu District, Chengdu, China PR.

POSTCODE: 611756.

EMAIL: zqyuan0@gmail.com

BRIEF BIOGRAPHY

Zhaoquan Yuan is now an Associate Professor at the School of Computing and Artificial Intelligence, and Vice Dean of the Institute of Advanced Technology and Equipment, Southwest Jiaotong University (SWJTU). I graduated with my bachelor's degree from the School of Computer Science and Technology, University of Science and Technology of China (USTC), and received my Ph.D. degree in Pattern Recognition and Intelligent System from Multimedia Computing Group (MMC), National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, advised by Prof. Changsheng Xu, and co-supervised by Prof. Jitao Sang. I was a research visitor in the China-Singapore Institute of Digital Media (CSIDM) and Department of Computing of The Hong Kong Polytechnic University, respectively.

My research interests encompass a variety of fields, including multi-modal semantic understanding, generative AI, continual learning, and computer vision.

I am looking for highly-motivated students with solid mathematical background or proficient coding skills. If you are interested in working with me, please send me an email. Thanks!

NEWS

[March 27, 2024] Paper "PostureHMR: Posture Transformation for 3D Human Mesh Recovery" is accepted by CVPR-24 (CCF-A).
[July 27, 2023] Paper "Human-Object-Object Interaction: Towards Human-Centric Complex Interaction Detection" is accepted by ACM MM-23 (CCF-A).
[Dec 27, 2022] 邵焕同学获西南交通大学2022年度优秀硕士论文奖！
[June 30, 2022] Paper "Domain-Specific Conditional Jigsaw Adaptation for Enhancing transferability and Discriminability" is accepted by ACM MM-22 (CCF-A).
[Junly 4, 2021] Paper "Hierarchical Multi-Task Learning for Diagram Question Answering with Multi-Modal Transformer" is accepted by ACM MM-21 (CCF-A, Oral). [新闻报道]
[June 24, 2021] Paper "Contrastive learning in frequency domain for Non-I.I.D. image classification" is awarded as best paper at MMM-21. [新闻报道]
[March 6, 2021] Paper "Meta-Learning Causal Feature Selection for Stable Prediction" is accepted by ICME-21 (Oral, acceptance rate =15%).
[June 1, 2020] Paper "Adversarial Multimodal Network for Movie Question Answering" is accepted by IEEE Trans. on Multimedia.

TEACHING

Undergraduate Courses

Natural Language Processing, B2558, SCAI008012, 2023--2024(2)
Digital Image Processing, B2790, SCAI004012, 2023--2024(1)
Digital Image Processing, B2630, SCAI004012, 2022--2023(1)
Digital Image Processing, B0600, 3143324, 2021--2022(1)
Digital Image Processing, B0312, 0371053, 2020--2021(2)
Digital Image Processing, B1250, 3143324, 2020--2021(1)
Digital Image Processing, B0445, 0371053, 2019--2020(2)
Digital Image Processing, B1932, 3143324, 2019--2020(1)
Digital Image Processing, B0332, 0371053, 2018--2019(2)

Graduate Courses

Natural Language Processing. 2023--2024(2)
Natural Language Processing. 2022--2023(2)
Natural Language Processing. 2021--2022(2)

SELECTED PUBLICATIONS Go Top

PostureHMR: Posture Transformation for 3D Human Mesh Recovery.
Yu-Pei Song, Xiao Wu, Zhaoquan Yuan, Jian-Jun Qiao, Qiang Peng.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 19-21, 2024. Seattle WA, USA. (Accepted, CVPR, CCF-A类)
Human-Object-Object Interaction: Towards Human-Centric Complex Interaction Detection.
Ming-Xuan Zhang, Xiao Wu, Zhaoquan Yuan, Qi He, Xiang Huang.
Proceedings of the 31st ACM International Conference on Multimedia, pp. 2233-2242. 2023. Oct 29–Nov 3, 2023. Ottawa, Canada. (ACM MM, CCF-A类)
Learning Surface-awareness Network for X-Ray Prohibited Item Detection.
Ying Shen, Wei Li, Zhaoquan Yuan, Xiao Wu.
Proceedings of the 5th ACM International Conference on Multimedia in Asia, pp. 1-5. 2023. Dec 6-8, 2023. Tainan Taiwan.
Domain-Specific Conditional Jigsaw Adaptation for Enhancing Transferability and Discriminability.
Qi He, Zhaoquan Yuan^*, Xiao Wu, and Jun-Yan He.
Proceedings of the 30th ACM International Conference on Multimedia, pp. 6327-6336. 2022. Oct 10-14, 2022. Lisbon Portugal. (ACM MM, CCF-A类)
Learning Graph-based Residual Aggregation Network for Group Activity Recognition.
Wei Li, Tianzhao Yang, Xiao Wu, and Zhaoquan Yuan.
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, pp. 1102-1108. 2022. July 23-29, 2022. Messe Wien, Vienna, Austria. (IJCAI, CCF-A类)
Hierarchical Multi-Task Learning for Diagram Question Answering with Multi-Modal Transformer.
Zhaoquan Yuan, Xiao Peng, Xiao Wu^*, and Changsheng Xu.
Proceedings of the 29th ACM International Conference on Multimedia, pp. 1313-1321, 2021. Oct 20-24, 2021. Chengdu, China. (ACM MM, CCF-A类)
Adversarial Multimodal Network for Movie Story Question Answering.
Zhaoquan Yuan, Siyuan Sun, Lixin Duan^*, Changsheng Li^*, Xiao Wu, and Changsheng Xu.
IEEE Transactions on Multimedia, vol. 23, pp. 1744-1756, 2021. (TMM, 中科院JCR-1区)
Meta-Learning Causal Feature Selection for Stable Prediction.
Zhaoquan Yuan, Xiao Peng, Xiao Wu^*, Bingkun Bao, and Changsheng Xu.
2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1-6. IEEE, 2021. July 5-9, 2021. Shenzhen, China. (ICME, CCF-B类)
Contrastive Learning in Frequency Domain for Non-I.I.D. Image Classification.
Huan Shao, Zhaoquan Yuan^*, Xiao Peng, and Xiao Wu.
Proceedings of the 27th International Conference on Multimedia Modeling, pp. 111-122, 2021. June 22–24, 2021. Prague, Czech Republic. (MMM, 最佳论文奖)
DB-LSTM: Densely-Connected Bi-directional LSTM for Human Action Recognition.
Jun-Yan He, Xiao Wu, Zhi-Qi Cheng, Zhaoquan Yuan, and Yu-Gang Jiang.
Neurocomputing, 444, pp.319-331. (中科院JCR-2区)
Learning Feature Hierarchies: A Layer-Wise Tag-Embedded Approach.
Zhaoquan Yuan, Changsheng Xu^*, Jitao Sang, Shuicheng Yan, and M. Shamim Hossain.
IEEE Transactions on Multimedia, vol. 17, no. 6, pp. 816-827, 2015. (TMM, 中科院JCR-1区)
A Unified Framework of Latent Feature Learning in Social Media.
Zhaoquan Yuan, Jitao Sang, Changsheng Xu^*, and Yan Liu.
IEEE Transactions on Multimedia, vol. 16, no. 6, pp. 1624-1635, 2014. (TMM, 中科院JCR-1区)
Latent Feature Learning in Social Media Network.
Zhaoquan Yuan, Jitao Sang, Yan Liu, and Changsheng Xu^*.
Proceedings of the 21st ACM international conference on Multimedia, pp. 253-262, 2013. Oct 21-25, 2013. Barcelona, Spain. (ACM MM, CCF-A类)
Tag-aware Image Classification via Nested Deep Belief Nets.
Zhaoquan Yuan, Jitao Sang, and Changsheng Xu^*.
2013 IEEE international conference on Multimedia and Expo, pp. 1-6. IEEE, 2013. July 15-19, 2013. San Jose, CA, USA. (ICME, CCF-B类)

GRANT AND FUNDS Go Top

Causal Mechanism-based Multimodal Continual Learning, 2024.01 -- 2025.12, Natural Science Foundation of Sichuan, 24NSFSC0900
Machine Learning and Reasoning in Video Question Answering, 2019.01 -- 2021.12, National Natural Science Foundation of China, 61802053
Machine Reasoning Research Towards Multimodal Question Answering, 2020.01 -- 2022.12, Sichuan Science and Technology Program, 2020YJ0037
Key Technologies of Video Question Answering System, China Postdoctoral Science Foundation, 2020M683353
Semantic Understanding toward Video Question Answering, 2019.01 -- 2020.12, Fundamental Research Funds for the Central Universities, 2682019CX62

PROFESSIONAL ACTIVITIES Go Top

Program Committee Member

ACM International Conference on Multimedia, 2019 – present
Association for the Advancement of Artificial Intelligence, 2022 – present
Annual Meeting of the Association for Computational Linguistics, 2023 – present
International Conference on Empirical Methods in Natural Language Processing, 2021 – present
ACM International Conference on Multimedia Retrieval, 2019 – present
IEEE International Conference on Multimedia and Expo, 2019 – present
International Conference on Multimedia Modeling, 2019 – present
ACM International Conference on Multimedia in Asia, 2019 – present

Journal Reviewer

IEEE Transactions on Multimedia
IEEE Transactions on Neural Networks and Learning Systems
IEEE Transactions on Cybernetics
Pattern Recognition
Multimedia Systems
Multimedia Tools and Applications

STUDENTS Go Top

PhD Students

Zhou Du (Co-superviser)
Fangying Xiong (Co-superviser)
Yuankang Pan (Co-superviser)

Master Students

Yuke Li
Yuting Tang
Maorui Zhang
Cong Zheng
Xuehui Chen
Yang Liu (Co-superviser)
Tao Liu (Co-superviser)
JichenG Liu (Co-superviser)
Jiangbo Chai
Zihao Luan
Hongxiao Yuan
Ting Pan
Fanpeng Li
Zimeng Wang (Co-superviser)
Shengkai Wan (Co-superviser)
Xinhan Lian (Co-superviser)
Zining Wang
Wen Xu
Jie Tang
Zijia Liang
Bojie Ma (Co-superviser)
Yuan Ma (Co-superviser)
Zhun Zhong (Co-superviser)
Huancheng Xu
Baili Zhou
Chengbin Zhao (Co-superviser)
Xiao Peng (Graduated in 2022, 就职于商汤科技)
Huan Shao (Graduated in 2022, 就职于蚂蚁金服)

RESOURCE Go Top

招生信息 Go Top

袁召全，现任西南交通大学计算机与人工智能学院副教授，先进技术与装备研究院副院长（挂职），硕士生导师。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）。曾先后在中国-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。曾获国际学术会议MMM-2021最佳论文奖。近年来在CVPR、ACM MM、IJCAI、IEEE TMM等国际学术会议及期刊发表论文近20篇。任多届ACM MM、CVPR、ACL、AAAI、EMNLP、ICMR、ICME等国际会议程序委员会委员，及多个IEEE Trans期刊审稿人。所指导的研究生曾获西南交通大学优秀硕士论文奖。目前主持国家自然科学基金青年项目、四川省自然科学基金项目、四川省科技计划基础研究项目、中国博士后基金项目等多项。主要研究方向包括多模态语义理解、生成式AI、持续深度学习、计算机视觉等。

欢迎具备以下条件的同学加入科研团队：
（1）有上进心与科研热情；
（2）数学与编程基础扎实，对多模态智能分析、生成式AI、深度学习、计算机视觉等前沿技术感兴趣；
（3）责任心强，诚信可靠。
有意向的同学请邮件联系：zqyuan0@gmail.com。

Last updated date: March 27, 2024.