Dr. Feng ZHU (朱烽)

Senior Director (R&D) @ Smart City Group of SenseTime

2024年 获得 公安部科学技术奖 一等奖（排名12/15）

2023年 入选 东方英才计划青年项目（原上海市青年拔尖人才）

2022年 获得 深圳人工智能科技进步奖（排名2/8）

2021年 入选 上海产业菁英高层次人才（产业青年英才）

zhufeng@sensetime.com (Work)
zhufengx2011@gmail.com (Personal)
GitHub, Google Scholar

Join Us ！！！Hot Positions@SenseTime

About Me

Feng Zhu is currently a Senior Director (R&D) in Smart City Group of SenseTime, leading a talented research&development team with over 20 full-time reseachers, engineers and interns. His team supports SenseFoundry, a one-stop software platform tailored for Smart City management, delivering cutting-edge AI techniques for large scale applications in Smart City, such as City Security, Traffic Management. Feng Zhu received the B.E. degree and Ph.D. degree in Electronic Engineering in 2011 and 2017, respectively, from the Department of Electronic Engineering and Information Science, University of Science and Technology of China (USTC), under the supervision of Prof. Nenghai Yu. He also worked as a Research Assistant in MMLab during 2012~2017, under the supervision of Prof. Xiaogang Wang.

Dr. Zhu's research centers on urban visual intelligence, with a focus on advancing multimodal representation learning, multimodal foundation models, multimodal agents, and world models. The goal is to develop more generalizable, capable, and human-aligned AI systems by addressing fundamental challenges including poor generalization, limited intelligence beyond specific tasks, and effective alignment with human values and preferences.

News

Publications

  1. Neural-Symbolic Intention Refinement with User Feedback for Text-to-Image Retrieval
    Yu Bai, Lei Zhang, Xiaoyan Hu, Feng Zhu, Rui Zhao.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2026. [PDF]
    GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language Models
    Qinghongbing Xie, Zhaoyuan Xia, Feng Zhu, Lijun Gong, Ziyue Li, Rui Zhao, Long Zeng.
    International Conference on Learning Representations (ICLR), 2026. [PDF]
    On the Suitability of Reinforcement Fine-Tuning to Visual Tasks
    Xiaxu Chen, Wei Li, Chunxu Liu, Chi Xie, XiaoyanHu, Chengqian Ma, Feng Zhu, Rui Zhao.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2025. [PDF]
  2. Re-Aligning Language to Visual Objects with an Agentic Workflow
    Yuming Chen, Jiangyan Feng, Haodong Zhang, Lijun Gong, Feng Zhu, Rui Zhao, Qibin Hou, Ming-Ming Cheng, Yibing Song.
    International Conference on Learning Representations (ICLR), 2025. [PDF]
  3. RelationLMM: Large Multimodal Model as Open and Versatile Visual Relationship Generalist
    Chi Xie, Shuang Liang, Jie Li, Zhao Zhang, Feng Zhu, Rui Zhao, Yichen Wei.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. [PDF]
  4. Hulk: A Universal Knowledge Translator for Human-Centric Tasks
    Yizhou Wang, Yixuan Wu, Shixiang Tang, Weizhen He, Xun Guo, Feng Zhu, Lei Bai, Rui Zhao, Jian Wu, Tong He, Wanli Ouyang.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. [PDF]
  5. Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification
    Weizhen He, Yiheng Deng, Yunfeng Yan, Feng Zhu, Yizhou Wang, Lei Bai, Qingsong Xie, Rui Zhao, Donglian Qi, Wanli Ouyang, Shixiang Tang.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. [PDF]
  6. Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions
    Weizhen He, Yiheng Deng, Shixiang Tang, Qihao Chen, Qingsong Xie, Yizhou Wang, Lei Bai, Feng Zhu, Rui Zhao, Wanli Ouyang, Donglian Qi, Yunfeng Yan.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [PDF][Project][媒体解读]
  7. InstructDET: Diversifying Referring Object Detection with Generalized Instructions
    Ronghao Dang, Jiangyan Feng, Haodong Zhang, Chongjian Ge, Lin Song, Lijun Gong, Chengju Liu, Qijun Chen, Feng Zhu, Rui Zhao, Yibing Song.
    International Conference on Learning Representations (ICLR), 2024. [PDF][Project]
  8. Described Object Detection: Liberating Object Detection with Flexible Expressions
    Chi Xie, Zhao Zhang, Yixuan Wu, Feng Zhu, Rui Zhao, Shuang Liang.
    Conference on Neural Information Processing Systems (NeurIPS), 2023. [PDF][Project]
  9. Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
    Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, Rui Zhao.
    preprint, arXiv:2306.15195, 2023. [PDF][Project]
  10. Advancing Referring Expression Segmentation Beyond Single Image
    Yixuan Wu, Zhao Zhang, Xie Chi, Feng Zhu, Rui Zhao.
    IEEE/CVF Conference on Computer Vision (ICCV), 2023. [PDF]
  11. Better Aligning Text-to-Image Models with Human Preference
    Xiaoshi Wu, Keqiang Sun, Feng Zhu, Rui Zhao, Hongsheng Li.
    IEEE/CVF Conference on Computer Vision (ICCV), 2023. [PDF]
  12. Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities
    Kaijian Liu, Shixiang Tang, Ziyue Li, Zhishuai Li, Lei Bai, Feng Zhu, Rui Zhao.
    IEEE Transactions on Multimedia (TMM), 2023. [PDF]
  13. HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining
    Shixiang Tang, Cheng Chen, Meilin Chen, Qingsong Xie, Yizhou Wang, Yuanzheng Ci, Lei Bai, Feng Zhu, Haiyang Yang, Li Yi, Rui Zhao, Wanli Ouyang.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [PDF]
  14. UniHCP: A Unified Model for Human-Centric Perceptions
    Yuanzheng Ci, Yizhou Wang, Meilin Chen, Shixiang Tang, Lei Bai, Feng Zhu, Rui Zhao, Fengwei Yu, Donglian Qi, Wanli Ouyang.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [PDF]
  15. Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching
    Xiaoshi Wu, Feng Zhu, Rui Zhao, Hongsheng Li.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [PDF]
  16. Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning
    Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan.
    International Conference on Learning Representations (ICLR), 2023. [PDF]
  17. Contextual Image Masking Modeling via Synergized Contrasting without View Augmentation for Faster and Better Visual Pretraining
    Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan.
    International Conference on Learning Representations (ICLR), 2023. [PDF]
  18. Cycle-consistent Masked AutoEncoder for Unsupervised Domain Generalization
    Haiyang Yang, Shixiang Tang, Xiaotong Li, Feng Zhu, Yizhou Wang, Meilin Chen, Lei Bai, Rui Zhao, Wanli Ouyang.
    International Conference on Learning Representations (ICLR), 2023. [PDF]
  19. COCAS+: Large-Scale Clothes-Changing Person Re-identification with Clothes Templates
    Shihua Li, Haobin Chen, Shijie Yu, Zhiqun He, Feng Zhu, Rui Zhao, Jie Chen, Yu Qiao.
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022. [PDF]
  20. Unsupervised Object Detection Pretraining with Joint Object Priors Generation and Detector Learning
    Yizhou Wang, Meilin Chen, Shixiang Tang, Feng Zhu, Haiyang Yang, Lei Bai, Rui Zhao, Yunfeng Yan, Donglian Qi, Wanli Ouyang.
    Conference on Neural Information Processing Systems (NeurIPS), 2022. [PDF]
  21. Saliency Guided Contrastive Learning on Scene Images
    Meilin Chen, Yizhou Wang, Shixiang Tang, Feng Zhu, Haiyang Yang, Lei Bai, Rui Zhao, Donglian Qi, Wanli Ouyang.
    preprint, arXiv:2302.11461, 2022. [PDF]
  22. Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
    Xulin Li, Yan Lu, Bin Liu, Guojun Yin, Qi Chu, Feng Zhu, Rui Zhao, Nenghai Yu.
    European Conference on Computer Vision (ECCV), 2022. [PDF]
  23. Domain Invariant Autoencoders for Self-supervised Learning from Multi-domains
    Haiyang Yang, Meilin Chen, Yizhou Wang, Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Wanli Ouyang.
    European Conference on Computer Vision (ECCV), 2022. [PDF] [Code]
  24. Unifying Vision Unsupervised Contrastive Learning from a Graph Perspective
    Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Chenyu Wang, Wanli Ouyang.
    European Conference on Computer Vision (ECCV), 2022. [PDF] [Code]
  25. Relative Contrastive Loss for Unsupervised Representation Learning
    Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Wanli Ouyang.
    European Conference on Computer Vision (ECCV), 2022. [PDF] [Code]
  26. Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID
    Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, Xiaogang Wang, Hongsheng Li.
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022. [PDF]
  27. DOTIN: Dropping Task-Irrelevant Nodes for GNNs
    Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang.
    preprint, arXiv:2204.13429, 2022. [PDF]
  28. Revisiting the Transferability of Supervised Pretraining: an MLP Perspective
    Yizhou Wang, Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Donglian Qi, Wanli Ouyang.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [PDF]
  29. Feature Erasing and Diffusion Network for Occluded Person Re-Identification
    Zhikang Wang, Feng Zhu, Shixiang Tang, Rui Zhao, Lihuo He, Jiangning Song.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [PDF] [Code]
  30. Align Representations with Base: A New Approach to Self-Supervised Learning
    Shaofeng Zhang, Lyn Qiu, Feng Zhu, Yunchi Yan, Hengrui Zhang, Rui Zhao, Xiaokang Yang.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [PDF] [Code]
  31. Zero-CL: Feature and Instance Decorrelation via Whitening for Negative-Free Contrastive Learning with Symmetric Architecture
    Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang.
    International Conference on Learning Representations (ICLR), 2022. [PDF] [Code]
  32. Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
    Shijie Yu, Feng Zhu, Dapeng Chen, Rui Zhao, Haobin Chen, Shixiang Tang, Jinguo Zhu, Yu Qiao.
    preprint, arXiv:2105.12355, 2021. [PDF]
  33. Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
    Yixiao Ge, Xiao Zhang, Ching Lam Choi, Ka Chun Cheung, Peipei Zhao, Feng Zhu, Xiaogang Wang, Rui Zhao, Hongsheng Li.
    preprint, arXiv:2104.13298, 2021. [PDF]
  34. AutoMA: Towards Automatic Model Augmentation for Transferable Adversarial Attacks
    Haojie Yuan, Qi Chu, Feng Zhu, Rui Zhao, Bin Liu, Nenghai Yu.
    IEEE Transactions on Multimedia (TMM), 2021. [PDF]
  35. Progressive Correspondence Pruning by Consensus Learning
    Chen Zhao, Yixiao Ge, Feng Zhu, Rui Zhao, Hongsheng Li, Mathieu Salzmann.
    IEEE/CVF Conference on Computer Vision (ICCV), 2021. [PDF]
  36. Efficient Open-Set Adversarial Attacks on Deep Face Recognition
    Haojie Yuan, Qi Chu, Feng Zhu, Rui Zhao, Bin Liu, Nenghai Yu.
    IEEE International Conference on Multimedia and Expo (ICME), 2021, Oral. [PDF]
  37. Improving Facial Attribute Recognition by Group and Graph Learning
    Zhenghao Chen, Shuhang Gu, Feng Zhu, Jing Xu, Rui Zhao.
    IEEE International Conference on Multimedia and Expo (ICME), 2021, Oral. [PDF]
  38. Temporal ROI Align for Video Object Recognition
    Tao Gong, Kai Chen, Xinjiang Wang, Qi Chu, Feng Zhu, Dahua Lin, Nenghai Yu, Huamin Feng.
    AAAI Conference on Artificial Intelligence (AAAI), 2021. [PDF]
  39. Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
    Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, Hongsheng Li.
    Conference on Neural Information Processing Systems (NeurIPS), 2020. [PDF] [Project] [Code]
  40. Self-supervising Fine-grained Region Similarities for Large-scale Image Localization
    Yixiao Ge, Haibo Wang, Feng Zhu, Rui Zhao, Hongsheng Li.
    European Conference on Computer Vision (ECCV), 2020, Spotlight (Top 5%). [PDF] [Project] [Code]
  41. DASOT: A Unified Framework Integrating Data Association and Single Object Tracking for Online Multi-Object Tracking
    Qi Chu, Wanli Ouyang, Bin Liu, Feng Zhu, Nenghai Yu.
    AAAI Conference on Artificial Intelligence (AAAI), 2020. [PDF]
  42. Attention-aware Compositional Network for Person Re-identification
    Jing Xu, Rui Zhao, Feng Zhu, Huaming Wang, Wanli Ouyang.
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [PDF]
  43. Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
    Feng Zhu, Hongsheng Li, Wanli Ouyang, Nenghai Yu, and Xiaogang Wang.
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [PDF] [Code]
  44. Crowd Tracking by Group Structure Evolution
    Feng Zhu, Xiaogang Wang, and Nenghai Yu.
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2016. [PDF]
  45. Consistent Matching based on Boosted Salience Channels for Group Re-identification
    Feng Zhu, Qi Chu, and Nenghai Yu.
    IEEE International Conference on Image Processing (ICIP), 2016. [PDF]
  46. Multi-level visual tracking with hierarchical tree structural constraint
    Jingjing Wang, Nenghai Yu, Feng Zhu, and Liansheng Zhuang.
    Neurocomputing, 2016.
  47. Crowd Tracking with Dynamic Evolution of Group Structures
    Feng Zhu, Xiaogang Wang and Nenghai Yu.
    European Conference on Computer Vision (ECCV), 2014. [PDF] [Demo] [Dataset]
  48. Robust FMO Algorithm and Adaptive Redundant Slice Allocation for Wireless Video Transmission
    Feng Zhu, Weiming Zhang, Nenghai Yu and Xianfeng Zhao.
    Telecommunication Systems (Journal), vol. 59, no. 3, pp. 357-363, 2015. [PDF]
  49. Adaptive Error Resilient Coding Based on FMO in Wireless Video Transmission
    Feng Zhu, Weiming Zhang and Nenghai Yu.
    International Conference on Multimedia Information Networking and Security (MINES), 2011. [PDF]

Services