2013年毕业于北京邮电大学，获博士学位。2011-2013年受国家留学基金委资助赴美国加州大学河滨分校联合培养博士生，师从IEEE Fellow。2024年受国家留学基金委资助赴新加坡科技设计大学访问学者。目前从事视觉问答、轻量级姿态估计、图像语义分割、人体行为识别和零样本学习等人工智能领域的研究工作，积极跟踪新涌现的人工智能领域的计算机视觉技术。近年来，以第一作者/通信作者在IEEE Transactions on Image Processing、IEEE
Transactions on Multimedia，ACM Transactions on Multimedia Computing,
Communications, and Applications，International Joint Conference on Artificial
Intelligence （IJCAI）、Science China Information Sciences、Knowledge-based
systems、《软件学报》、Engineering
Applications of Artificial Intelligence等国内外权威刊物和会议发表论文40余篇，以第一发明人授权/申请相关发明专利20余项。目前，作为项目负责人主持国家自然科学基金面上项目1项，江苏省自然科学基金面上项目1项，产学研合作项目1项，横向课题2项，以主要参与人参与江苏省自然科学基金重点项目1项。主持结题国家自然科学基金青年项目1项，省部级项目1项，市厅级项目1项，产学研合作项目1项，横向课题若干。
指导的硕士研究生多次获得国家奖学金、小米奖学金、集萃研究生奖学金、江苏省优秀硕士研究生论文和南京邮电大学优秀硕士研究生论文等。
代表性成果：
[1] Qun Li, Lu Huang, Fu Xiao*, Na Zhao and
Bir Bhanu, Toward generative understanding: Incremental few-shot semantic
segmentation with diffusion models[J], IEEE Transactions on Image Processing,
2026, 35(1): 743-758. (CCF推荐A类期刊)
[2] Qun Li, Haixin Sun, Fu Xiao*, Yiming
Wang, Xinping Gao, Bir Bhanu. PS-CoT-Adapter: adapting plan-and-solve
chain-of-thought for ScienceQA. Science China Information Sciences, 2025,
68(1): 119101. (CCF推荐A类期刊)
[3] Baoquan Sun, Qun Li*, Ziyi Zhang. Dynamic
context modeling based lightweight high-resolution network for dense
prediction[J], Engineering Applications of Artificial Intelligence, 2024,
129(1):1-45. (中科院一区)
[4] Qun Li, Baoquan Sun, Bir Bhanu.
Lite-FENet: Lightweight multi-scale feature enrichment network for few-shot
segmentation. Knowledge-based systems, 2023, 278(10):1-9. (中科院一区)
[5] Qun Li, Ziyi Zhang, Fu Xiao*, Feng
Zhang, Bir Bhanu. Dite-HRNet: Dynamic Lightweight High-Resolution Network for
Human Pose Estimation. International Joint Conference on Artificial
Intelligence (IJCAI), 2022: 1095-1101. (15%接收率, CCF推荐 A类会议).
[6] Qun Li, Ziyi Zhang, Feng Zhang, Fu
Xiao*. HRNeXt: High-Resolution Context Network for Crowd Pose Estimation. IEEE
Transactions on Multimedia, 2022. (CCF推荐B类期刊, 中科院一区)
[7] Qun Li, Fu Xiao*, Bir Bhanu, Biyun
Sheng, Richang Hong. Inner Knowledge-based Img2Doc Scheme for Visual Question
Answering. ACM Transactions on Multimedia Computing, Communications, and
Applications, 2022, 18(3): 76:1-76:21. (CCF推荐B类期刊)
[8] 李群, 肖甫*, 张子屹, 张锋, 李延超. 基于空时变换网络的视频摘要生成. 软件学报，2022, 33(9): 3195-3209. (国内一级学报)
[9] Qun Li, Rui Yang, Fu Xiao*, Bir Bhanu,
Feng Zhang. Attention-based anomaly detection in multiview surveillance
videos[J]. Knowledge-based systems, 2022, 252(5): 1-11. (中科院一区)
[10] Qun Li, Fu Xiao*, Le An, Xianzhong Long,
Xiaochun Sun. Semantic concept network and deep walk-based visual question
answering[J], ACM Transactions on Multimedia Computing, Communications, and
Applications, 2019, 15(2s): 1-19. (CCF推荐B类期刊)
