团队介绍：团队由赵才荣教授领衔，胡亮教授、张奇副教授共同组成导师组，主要从事高效可信视觉识别、模式识别与机器学习、计算机视觉等方向研究。团队现有导师3名、博士生25名、硕士生27名。团队围绕国家重大需求和国际学术前沿，承担国自然企业联合重点项目等5项国家自然科学基金项目、国家重点研发计划子课题及多项企业合作项目，近五年在 TPAMI、CVPR 等顶级期刊会议发表高水平论文100余篇，并取得 AAAI 2026 Best Paper、CVPR 2025 Oral、ICLR Spotlight 等高水平学术成果。团队骨干导师胡亮教授、张奇副教授均为国家基金委海外优青和上海市海外高层次人才计划入选者。团队育人成效显著，培养研究生获评上海市计算机学会优秀博士论文1篇、优秀硕士论文2篇。团队在科研创新和成果转化方面成效显著，获上海市自然科学二等奖、上海市科技进步一等奖、吴文俊人工智能科技进步二等奖、全国人工智能应用场景创新挑战赛总决赛特等奖、上海市计算机学会教学成果一等奖、2025年同济大学“十大最具转化潜力科技成果奖”等荣誉，获评上海市计算机学会优秀博士学位论文1篇、优秀硕士学位论文2篇、中国电子学会优秀硕士学位论文1篇。

        在 VILL，我们不仅追求学术的高度，更传递团队的温度。实验室拥有浓厚且自由的学术讨论氛围，鼓励师生之间、同窗之间进行跨学科的灵感碰撞。除了严谨的科研工作，我们同样注重团队建设与生活平衡，是一个充满朝气、真诚友好的科研大家庭。VILL 实验室常年欢迎对视觉感知与智能学习充满激情的学子加入，与我们并肩探索人工智能的无限可能！

         视觉与智能学习实验室主页：https://vill.tongji.edu.cn/

主持科研项目（纵向课题）情况：

1. 国家自然科学基金联合重点项目，U25A201239，“面向闽台舆情的多模态内容分析与理解关键技术研究”、2026/01-2029/12、在研、主持。

2. 上海市“通用人工智能大模型”基础研究专项计划，2025SHZDZX025G10， “面向内容溯源的 LLM 可解释性与可归因性网络架构与算法”、2025/11-2026/10，在研、主持。

3. 国家自然科学基金面上项目，62473286，“基于安全计算的可信行人再识别研究”、2025/01-2028/12、在研、主持。

4. 国家自然科学基金面上项目，62076184，“面向遮挡行人再识别的多粒度表示与度量研究”、2021/01-2024/12、已结题、主持。

5. 国家自然科学基金面上项目，61673299，“基于多粒度的行人再辨识研究”、2017/01-2020/12、已结题、主持。

6. 国家重点研发计划213项目,  “国XXXX技术应用示范”， 负责其中子课题：“监控视频智能分析”， XXXXXXXXX213，2018/01-2020/12、已结题，主持。

7. 国家自然科学基金青年科学基金项目，61203247、“基于稀疏视觉特征学习的真实环境人脸识别研究”、2013/01-2015/12、已结题、主持。

主持企业合作（横向）项目：

1. 企业合作项目（阿里云计算有限公司），“视频语音文本跨模态数据自监督学习及应用”，2022/06-2023/06、已结题、主持。

2. 企业合作项目（上海汽车工业科技发展重点基金项目），“基于点云识别的感知融合及环境建模技术”，2022/07-2025/06、已结题、参与（第二）。

3. 企业合作项目(上海电气集团智慧城市信息科技有限公司)，“地下空间明火烟雾与积水浸水智能分析预警技术”，2024/02-2024/06、已结题、主持。

4. 企业合作项目（上港集团）“基于基础仿真的集装箱码头特定布局下内外集卡运行冲突与改善研究”，2024/7-2024/12、 已结题、主持。

5. 企业合作项目（湖南星电集团有限责任公司），“配网作业现场视频目标检测与追踪技术开发”，2025/06-2026/03、已结题、主持。

近年发表主要学术期刊与会议论文(实验室主页提供了论文原文和源码下载链接)：

[1]. Wentao Gu, Xinyang Jiang, Junyao Gao, Zifan Song, Yuhao Xue, Cairong Zhao*. pFedVIReID: Personalized Federated Learning for VI-ReID with Decoupled Local and Global Tuning. IEEE Transactions on Multimedia, 2026, Accepted. (CCF A）

[2]. Wentao Gu, Yuquan Li, XINYANG JIANG, Zilong Wang, Dongsheng Li, Zehui Li, Zijian Dong, Cairong Zhao*. Joint Adaptation of Uni-modal Foundation Models for Multi-modal Alzheimer's Disease Diagnosis. ICLR 2026, Accepted. (CCF A)

[3]. Ding Qi, Jian Li, Shuguang Dou, Zifan Song, Junyao Gao, Yabiao Wang, Chengjie Wang, Cairong Zhao*. Asynchronous Matching with Dynamic Sampling for Multimodal Dataset Distillation. ICLR 2026, Accepted. (CCF A)

[4]. Zifan Song, Kaitao Song, Guosheng Hu, Ding Qi, Junyao Gao, Xiaohua Wang, Dongsheng Li, Cairong Zhao*. Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading. ICLR 2026, Accepted. (CCF A)

[5]. Yubin Wang, XINYANG JIANG, De Cheng, Xiangqian Zhao, Zilong Wang, Dongsheng Li, Cairong Zhao*. Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts. ICLR 2026, Accepted. (CCF A)

[6]. Xiaowen Zhang, Zijie Yue, Yong Luo, Cairong Zhao, Qijun Chen, Miaojing Shi. Bootstrapping MLLM for WeaklySupervised ClassAgnostic Object Counting. ICLR 2026, Accepted. (CCF A)

[7]. Weixun Wan, XINYANG JIANG, Zilong Wang, Bei Li, Cairong Zhao*. Tuning Medical Foundation Models for Inner Ear Temporal CT Analysis with Plug-and-play Domain Knowledge Aggregator. The Fortieth AAAI Conference on Artificial Intelligence (AAAI) 2026, Accepted. (CCF A)

[8]. Xueyu Chen, Kaitao Song, Zifan Song, Dongsheng Li, Cairong Zhao*. Improving Long-Context Summarization with Multi-Granularity Retrieval Optimization. The Fortieth AAAI Conference on Artificial Intelligence (AAAI) 2026, Accepted. (CCF A)

[9]. Li yong cheng, Wang xuekuan, Zhifei Zhang, Cairong Zhao*.“Dual-Phase Visual-Language Pretraining and Adaptation for Long-Tailed Multi-Label Recognition.” The Fortieth AAAI Conference on Artificial Intelligence (AAAI) 2026, Accepted. (CCF A)

[10]. Ji Chenhao, et al, Cairong Zhao*. DiffPano++: Scalable and Consistent Multi-View Panorama Generation with Spherical Epipolar-Aware Diffusion, International Journal of Computer Vision (IJCV), 2026, Accepted. (SCI, IF:19.5, 中科院一区，CCF A）

[11]. Ji, Chenhao, Chaohui Yu, Junyao Gao, Fan Wang, and Cairong Zhao*. "CamPVG: Camera-Controlled Panoramic Video Generation with Epipolar-Aware Diffusion." In Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1-12. 2025. (CCF A)

[12]. Chen, Xueyu, Ran Miao, Liang Hu, Qi Zhang, Kaitao Song, Usman Naseem, and Cairong Zhao*. "Beyond topology-based graph mining: Deep analysis research networks via evolutionary topology and content fusion." Information Fusion (2025): 103922. (CCF A)

[13]. Zhao, Jiale, Xinyang Jiang, Junyao Gao, Yuhao Xue, and Cairong Zhao*. "One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models." In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 187-196. 2025. (CCF A)

[14]. Gao, Junyao, Yanan Sun, Yanchen Liu, Yinhao Tang, Yanhong Zeng, Ding Qi, Kai Chen, and Cairong Zhao*. "Styleshot: A snapshot on any style." IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1215-1228, 2026. (CCF A）

[15]. Cairong Zhao*, Shuguang Dou, Jiale Zhao, Xinyang Jiang, Junyao Gao, Yuge Zhang, Bo Li, and Dongsheng Li. "EA-HAS-Bench and Language-Enhanced Shrinkage Search for Energy-aware NAS." IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 11596-11613, 2025. (CCF A）

[16]. Song, Zifan, Xiao Gong, Guosheng Hu, Shuguang Dou, Qingsong Zhao, and Cairong Zhao*. "DPL++: Advancing the network performance via image and label perturbations." IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 10262-10279, 2025. (CCF A）

[17]. Qi, Ding, Jian Li, Junyao Gao, Shuguang Dou, Ying Tai, Jianlong Hu, Bo Zhao, Yabiao Wang, Chengjie Wang, and Cairong Zhao*. "Towards Universal Dataset Distillation via Task-Driven Diffusion." In Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10557-10566. (CVPR) 2025. (CCF A)

[18]. Zhiyuan Yang, et al, Cairong Zhao*. Fusion4DAL: Offline Multi-modal 3D Object Detection for 4D Auto-labeling. International Journal of Computer Vision (IJCV), pp.1-19. (CCF A）

[19]. Yubin Wang，et al, Cairong Zhao*. Uni2Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection. The ThirteenthInternational Conference on Learning Representations（ICLR）2025. (CCF A)

[20]. Junyao Gao, et al, Cairong Zhao*. FaceShot: Bring Any Character into Life. The ThirteenthInternational Conference on Learning Representations（ICLR）2025. (CCF A)

[21]. Zifang Song, et al, Cairong Zhao*. AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data, NIPS 2024. (CCF A)

[22]. Ding Qi, et al, Cairong Zhao*. Fetch and Forge: Efficient Dataset Condensation for Object Detection, NIPS 2024. (CCF A)

[23].  Qingsong Zhao, et al, Cairong Zhao*. Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection? NIPS 2024. (CCF A)

[24]. Chenhao Ji, et al, Cairong Zhao*. DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion, NIPS 2024. (CCF A)

[25]. Yuanpeng Tu, Boshen Zhang, Liang Liu, Yuxi Li, Xuhai Chen, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Cairong Zhao*. Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection, ECCV 2024. (CCF B)

[26]. Zefan Qu, Xinyang Jiang, Yifan Yang, Dongsheng Li, Cairong Zhao*. Online Video Quality Enhancement with Spatial-Temporal Look-up Tables, ECCV 2024. (CCF B)

[27]. Qingsong Zhao, Yi Wang, Shuguang Dou, Chen Gong, Yin Wang，Cairong Zhao*. Adaptive Discriminative Regularization for Visual Classification, IJCV,132, 4327–4342 (2024). (CCF A）

[28]. Junyao Gao, Xinyang Jiang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cairong Zhao*. Re-ID-leak: Membership Inference Attacks Against Person Re-Identification, IJCV,132, 4673–4687 (2024). (CCF A）

[29]. Shuguang Dou*, Xinyang Jiang*, Lu Liu, Lu Ying, Caihua Shan, Yifei Shen, Xuanyi Dong, Yun Wang, Dongsheng Li, Cairong Zhao*. Hierarchically Recognizing Vector Graphics and A New Chart-based Vector Graphics Dataset, TPAMI, 1 - 18 , 2024. (CCF A）

[30]. Cairong Zhao, Yubin Wang, Xinyang Jiang, Yifei Shen, Kaitao Song, Dongsheng Li, Duoqian Miao: Learning Domain Invariant Prompt for Vision-Language Models. IEEE Transactions on Image Processing. 2024, 33: 1348-1360. (CCF A） 

[31]. Zifan Song, Guosheng Hu, Cairong Zhao*，Diverse Person: Customize Your Own Dataset for Text-Based Person Search. AAAI 2024: 4943-4951 (CCF A)

[32]. Yubin Wang, Xinyang Jiang, De Cheng, Dongsheng Li, Cairong Zhao*,Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models. AAAI 2024: 5749-5757(CCF A)

[33]. Yuanpeng Tu, Yuxi Li, Boshen Zhang, Liang Liu, Jiangning Zhang, Yabiao Wang, Cairong Zhao*, Self-Supervised Likelihood Estimation with Energy Guidance for Anomaly Segmentation in Urban Scenes. AAAI 2024: 21637-21645 (CCF A)

[34]. Wenli Sun, Xinyang Jiang, Shuguang Dou, Dongsheng Li, Duoqian Miao,Cheng Deng, Cairong Zhao*. Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification. IEEE Transactions on Information Forensics and Security. 2024, 19: 307-319. (CCF A）

[35]. Zifan Song, Xiao Gong, Guosheng Hu, Cairong Zhao*. Deep Perturbation Learning: Enhancing the Network Performance via Image Perturbations.The Fortieth International Conference on Machine Learning, ICML 2023. (CCF A)

[36]. Yuanpeng Tu, Boshen Zhang, Yuxi Li, Liang Liu, Jian Li, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Cairong Zhao*. Learning with Noisy labels via Self-supervised Adversarial Noisy Masking. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023. (CCF A)

[37]. Yuanpeng Tu, Boshen Zhang, Yuxi Li, Liang Liu, Jian Li, Yabiao Wang, Chengjie Wang, Cairong Zhao*. Learning from Noisy Labels with Decoupled Meta Label Purifier. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023. (CCF A)

[38]. Shuguang Dou, Xinyang Jiang, Cairong Zhao*, Dongsheng Li. EA-HAS-BENCH: ENERGY-AWARE HYPERPARAME-TER AND ARCHITECTURE SEARCH BENCHMARK. The Eleventh International Conference on Learning Representations, 2023 (CCF A).

[39]. Shuguang Dou, Cairong Zhao*, Xinyang Jiang, Shanshan Zhang, Weishi Zheng, Wangmeng Zuo. Human Co-Parsing Guided Alignment for Occluded Person Re-identification. IEEE Transactions on Image Processing, 32: 458-470, 2023. (CCF A）

[40]. Cairong Zhao*, Chutian Wang, Guosheng Hu, Haonan Chen, Jinhui Tang ISTVT: Interpretable Spatial-Temporal Video Transformer for Deepfake Detection. IEEE Transactions on Information Forensics and Security，18: 1335-1348 , 2023. (CCF A）

[41]. Junyao Gao, Xinyang Jiang, Huishuai Zhang, Yifan Yang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cheng Deng, Cairong Zhao*. Similarity Distribution based Membership Inference Attack on Person Re-identification. Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023. (CCF A)

[42]. Yufeng Jin, Guosheng Hu, Haonan Chen, Duoqian Miao, Liang Hu, Cairong Zhao*. Cross-Modal Distillation for Speaker Recognition.Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023. (CCF A)

[43]. Cairong Zhao* , Liang Zhu , Shuguang Dou , Weihong Deng，Liang Wang.Detecting Overlapped Objects in X-Ray Security Imagery by a Label-Aware Mechanism，IEEE Transactions on Information Forensics and Security，2022，17：998-1009. (CCF A）

[44]. Cairong Zhao*, Yuanpeng Tu, Zhihui Lai, Fuming Shen, Heng Tao Shen, and Duoqian Miao. Salience-Guided Iterative Asymmetric Mutual Hashing for Fast Person Re-identification, IEEE Transactions on Image Processing, 2021,30:7776-7789.( CCF A）

[45]. Cairong Zhao*, Shuyang Feng, Brian Nlong Zhao, Zhijun Ding, Jun Wu, Fuming Shen, and Hengtao Shen. Scene Text Image Super-Resolution via Parallelly Contextual Attention Network. In Proceedings of the 29th ACM International Conference on Multimedia, 2021. （CCF A）

[46]. Cairong Zhao*, Xinbi Lv*, Shuguang Dou*, Shanshan Zhang, Jun Wu, Liang Wang. Incremental Generative Occlusion Adversarial Suppression Network for Person ReID. IEEE Transactions on Image Processing, 2021, 30:4212-4224.（CCFA）

[47]. 赵才荣*, 齐鼎, 窦曙光, 涂远鹏, 孙添力, 柏松, 蒋忻洋, 白翔*,苗夺谦*. 智能视频监控关键技术: 行人再识别研究综述, 中国科学.信息科学  2021, 51（12）:1979-2015. （CCF A）

[48]. Cairong Zhao*, Xinbi Lv*，Zhang Zhang, Wangmeng Zuo, Jun Wu, Duoqian Miao, Deep Fusion Feature Representation Learning with Hard Mining Center-Triplet Loss for Person Re-identification. IEEE Transactions on Multimedia, 2020, 22(12):3180-3195. (CCFA)