职称

副研究员

电子邮件

xqli@shu.edu.cn

办公室

计1109室

研究方向

计算机视觉，生成式人工智能(AIGC)

个人简介

李晓强，博士，副经理，副研究员，博士生导师；中国计算机学会（CCF）高级会员，中国图象图形学会（CSIG）会员，CCF计算机视觉专委会委员，CSIG学术会议与交流工作委员会委员，IEEE 会员，ACM 会员。在包括《IEEE Transaction on Image》、《IEEEE Transactions on Multimedia》、《计算机学报》等国内外期刊和CCF列表的国际会议如CVPR、ICCV、ICML、AAAI、IJCAI、NeurIPS、ACM Multimdia、ICLR等发表论文100余篇，其中包括CCF A类论文20余篇；申请或授权专利30余项。主持和参与完成科研项目20 余项，包括国家自然科学基金、863 计划项目、上海市自然科学基金等。2015年获得上海科技进步三等奖；2023年获得上海技术发明二等奖；2017年获得获上海市级教学成果奖一等奖。目前承担上海市2025年度关键技术研发计划“元宇宙”专项项目1项、国家自然科学基金2025年联合基金重点项目1项。指导的博士生获2022年上海市计算机学会优秀博士论文提名奖1项；指导的硕士生获2025年上海市计算机学会优秀硕士论文；指导本科生获世界老员工超级计算机大赛（ASC）大赛一等奖2项；近5年来指导的本科生有20余人次被推荐到清大、北大、复旦、上海交大、浙江大学、伊利诺伊大学香槟分校等国内外知名高校攻读硕士或博士学位。

代表性论文或专著（从最近的开始填）

CCF A类会议和期刊

1.Xiangyu Zheng, Songcheng He, Wanyun Li, Xiaoqiang Li, Wei Zhang. Shallow Features Matter: Hierarchical Memory with Heterogeneous Interaction for Unsupervised Video Object Segmentation. ACMM2025.

2.Ziyun Dai, Xiaoqiang Li, Shaohua Zhang, Yuanchen Wu, Jide Li. See different, think better: Visual Variations Mitigating Hallucinations in LVLMs. ACMM 2025.

3.Chao yin, Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation. ACMM2025.

4.Yuanchen Wu, Ke Yan, Shouhong Ding,  Xiaoqiang Li,, Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration. ICML2025.

5.Yuhang Li, Tong Liu, Yangguang Cui, Ming Hu, Xiaoqiang Li, One Arrow, Two Hawks: Sharpness-aware Minimization for Federated Learning via Global Model Trajectory, ICML2025. 

6.Yuanchen Wu, Lu Zhang, Hang Yao, Junlong Du, Ke Yan, Shouhong Ding, Yunsheng Wu, Xiaoqiang Li. Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception. CVPR2025.

7.Xichen Ye, Yifan Wu, Weizhong Zhang, Xiaoqiang Li* and et al. Optimized Gradient Clipping for Noisy Label Learning. AAAI2025.

8.Yuanchen Wu, Junlong Du, Ke Yan, Shouhong Ding, Xiaoqiang Li*. ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts. ICLR2025.

9.Yuanchen Wu, Xiaoqiang Li* and et.al. DINO is Also a Semantic Guider: Exploiting Class-aware Affinity for Weakly Supervised Semantic Segmentation.October 28-November 1, 2024, Melbourne, VIC, Australia. ACMM 2024.

10.Yuanchen Wu, Xichen Ye, Kequan Yang, Jide Li, Xiaoqiang Li*. DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation. CVPR2024.

11.Songmin Dai, Yifan Wu, Xiaoqiang Li*, Xiangyang Xue. Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection. The Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024, 38(2):1454-1462, Washington, USA. AAAI2024.

12.Xichen Ye, Xiaoqiang Li*, Songmin Dai, Tong Liu, Yan Sun, Weiqin Tong. Active Negative Loss Functions for Learning with Noisy Labels, 37th Conference on Neural Information Processing Systems , New Orleans, USA. NeurIPS2023.

13.Yuanchen Wu, Xiaoqiang Li*, Songmin Dai, Jide Li, Tong Liu, Shaorong Xie. Hierarchical Semantic Contrast for Weakly Supervised Semantic Segmentation, the Thirty-Second International Joint Conference on Artificial Intelligence, Macao, China. IJCAI2023.

14.Songmin Dai, Xiaoqiang Li*, Yue Zhou, Xichen Ye, Tong Liu. GradPU: Positive-Unlabeled Learning via Gradient Penalty and Positive. The Thirty-Seventh AAAI Conference on Artificial Intelligence, 37(6):7296-7303, Washington,USA. AAAI2023.

15.Congcong Zhu, Xintong Wan, Shaorong Xie, Xiaoqiang Li*, Yinzheng Gu. Occlusion-robust Face Alignment using A Viewpoint-invariant Hierarchical Network Architecture, , 11112-11121. CVPR 2022.

16.Congcong Zhu, Xiaoqiang Li*, Jide Li, Songmin Dai. Improving Robustness of Facial Landmark Detection by Defending against Adversarial Attacks, 11731-11740. ICCV2021.

17.Congcong Zhu, Xiaoqiang Li*, Jide Li, Guangtai Ding, Weiqin Tong，Spatial-Temporal Knowledge Integration: Robust Self-Supervised Facial Landmark Tracking. ACM Multimedia, 2020, 4135-4143. ACMM2020

18.Songmin Dai ; Xiaoqiang Li* ; Lu Wang; Pin Wu; Weiqin Tong; Yimin Chen. Learning Segmentation Masks with the Independence Prior. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 3429-3436. 2019.  AAAI2019

19.Chao Yin, Kequan Yang, Jide Li, Xiaoqiang Li. Mutual Iterative Refinement Network for Scribble-Supervised Camouflaged Object Detection. IEEE Transactons on Image Process, 34:7347-7361, 2025.

20.Pinxue Guo, Wei Zhang, Xiaoqiang Li, Wenqiang Zhang. Adaptive Online Mutual Learning Bi-Decoders for Video Object Segmentation. IEEE Transactons on Image Process, 31: 7063-7077, 2022.