吴嘉欣，现任深圳大学人工智能学院助理教授，硕士生导师，主要研究方向为多媒体内容分析、跨模态检索、智能体等。
先后在深圳大学计算机与软件学院获得学士和硕士学位，师从“国家千人”深圳大学特聘教授江健民教授和钟圣华教授。后于香港城市大学计算机科学系取得博士学位，师从ACM杰出科学家杨宗桦教授 (Prof. Ngo Chong-Wah)。博士毕业后，在香港理工大学计算系从事博士后研究，合作导师为IEEE Fellow李青教授及魏骁勇教授。
在人工智能领域国际顶级会议与期刊（CVPR、ACM MM、ACM TOIS、PR等）发表多篇论文，曾获得国际权威视频检索评测TRECVid第一名，并在国际交互式视频检索竞赛VBS中连续多年名列前茅。具备扎实的科研能力与丰富的应用研究经验。目前已担任多项国际会议（包括MMM 2026、ICMR 2026等）出版主席。
研究兴趣：多媒体内容分析、跨模态检索、医学视频分析、具身智能、智能体
招生信息：
欢迎有志于从事科研或应用竞赛的同学加入课题组！
现面向硕士研究生（每年约招 2 名）和本科生（名额不限）开放招募。
学术氛围：严谨治学、自由开放，Work hard, play harder!
培养理念：因材施教，充分尊重学生个人意愿，根据学生的兴趣与发展规划安排研究课题。在满足毕业要求的前提下，鼓励并支持学生开展学术访问（如香港、新加坡、欧洲等高校）及知名企业实习（如比亚迪、腾讯等）。
申请方式：请将个人简历发送至：jiaxinwu@szu.edu.cn，邮件标题建议格式为：姓名–学校–专业–申请硕士/本科科研
代表性论文:
1. Jiaxin Wu, Chong-Wah Ngo, Wing-Kwong Chan, Sheng-Hua Zhong, Xiong-Yong Wei, Qing Li, Multimodal LLM-based Query Paraphrasing for Video Search, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), accepted, Aug, 2026.(CCF-B期刊)
2. Shihong Huang*, Jiaxin Wu*, Dongmei Jiang, Yi Cai, and Yaowei Wang, Xiao-yong Wei, Compositional Transformation Reasoning for Composed Video Retrieval, The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 25644-25653, June 2026. (*共同一作, CCF A类会议)
3. Jiaxin Wu, Xiao-yong Wei, and Qing Li, Adaptive Multi-Agent Reasoning for Text-to-Video Retrieval, ACM International Conference on Multimedia Retrieval, Amsterdam, June, 2026. (CCF-B会议，口头报告)
4. Shihong Huang*, Jiaxin Wu*, Xiao-yong Wei, Yi Cai, Dongmei Jiang, and Yaowei Wang, Sound Bridge: Associating Egocentric and Exocentric Videos via Audio Cues, The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28942-2895, 2025. (*共同一作, CCF A类会议)
5. Jiaxin Wu, Chong-Wah Ngo, and Wing-Kwong Chan, Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank, In the Proceedings of the International Conference on Multimedia Retrieval (ICMR), 2024. (CCF-B会议，口头报告)
6. Jiaxin Wu, Chong-Wah Ngo, Wing-Kwong Chan, and Zhijian Hou, (Un)likelihood Training for Interpretable Embedding, ACM Transactions on Information Systems, 42(3), pp. 1-26, December 2023. (IF: 5.6, CCF A类期刊)
7. Jiaxin Wu, Sheng-Hua Zhong, and Yan Liu. Dynamic Graph Convolutional Network for Multi-video Summarization, Pattern Recognition, 107, November 2020. (IF: 8.0, 中科院一区期刊)
8. Jiaxin Wu and Chong-Wah Ngo, Interpretable Embedding for Ad-hoc Video Search, In the Proceedings of the ACM Multimedia (ACM MM), October 2020. (CCF A类会议)
9. Jiaxin Wu, Sheng-Hua Zhong, and Yan Liu, MvsGCN: A Novel Graph Convolutional Network for Multi-video Summarization, In the proceedings of the ACM Multimedia (ACM MM), pp. 827-835, October 2019. (CCF A类会议)
