教师简介

吴贺丰，博士，副教授。本博毕业于中山大学。致力于多模态理解、生成式模型、智能体交互、具身智能等人工智能领域的科学研究与应用实践，在IEEE T-PAMI、CVPR、AAAI、NeurIPS等国际重要期刊和会议上发表论文60余篇，授权中国发明专利10余项。已主持10余项科研项目，包括3项国家自然科学基金项目（1项青年项目、2项面上项目）、1项重点项目课题（200万）等，作为技术骨干参与了1项国家重点研发项目。获得广东省计算机学会优秀论文奖一等奖、国际顶会ACL杰出论文奖、广东省科技进步奖一等奖、广州市珠江科技新星等荣誉。

研究领域

计算机视觉，图像视频分析，多模态理解，生成式模型，智能体交互，具身智能，机器学习，人工智能

近年科研项目

•   国家自然科学基金面上项目，主持，起止年月：2023-01至2026-12.

•   国家自然科学基金面上项目，主持，起止年月：2019-01至2022-12.

•   广东省自然科学基金项目，主持，起止年月：2023-01至2025-12.

•   广州市创新环境建设计划珠江科技新星项目，主持，起止年月：2019-04至2021-03.

•   国家重点研发计划，参与，项目骨干，起止年月：2018-07至2021-06.

近年代表性论著

(*)表示通讯作者

•  Hefeng Wu, Yandong Chen, Lingbo Liu, Tianshui Chen, Keze Wang, Liang Lin. SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting. IEEE Transactions on Image Processing, 34: 4631-4645, 2025.

•  Zhongzhan Huang, Guoming Ling, Shanshan Zhong, Hefeng Wu, Liang Lin. MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models. Proc. of Annual Meeting of the Association for Computational Linguistics (ACL), 11442-11460, 2025. (Outstanding Paper Award)

•  Zhongzhan Huang, Guoming Ling, Vincent S. Liang, Yupei Lin, Yandong Chen, Shanshan Zhong, Hefeng Wu, Liang Lin. RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs. Proc. of Conference on Empirical Methods in Natural Language Processing (EMNLP), Findings, 3860–3887, 2025. 

•  Haijing Liu, Zhiyuan Song, Hefeng Wu*, Tao Pu, Keze Wang, Liang Lin*. Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention. Proc. of Annual Conference on Neural Information Processing Systems (NeurIPS), 2025. 

•  Haijing Liu, Tao Pu, Hefeng Wu*, Keze Wang, Liang Lin*. DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition. Proc. of ACM International Conference on Multimedia (ACM MM), 4708-4717, 2025. 

•  Kaidong Zhang, Rongtao Xu, Pengzhen Ren, Junfan Lin, Hefeng Wu, Liang Lin, Xiaodan Liang. RoBridge: A Hierarchical Architecture Bridging Cognition and Execution for General Robotic Manipulation. Proc. of IEEE International Conference on Computer Vision (ICCV), 2025.

•  Tao Tang, Likui Zhang, Youpeng Wen, Kaidong Zhang, Jia-Wang Bian, Xia Zhou, Tianyi Yan, Kun Zhan, Peng Jia, Hefeng Wu, Liang Lin, Xiaodan Liang. RoboPearls: Editable Video Simulation for Robot Manipulation. Proc. of IEEE International Conference on Computer Vision (ICCV), 2025.

•  Tao Pu, Qianru Lao, Hefeng Wu*, Tianshui Chen, Ling Tian, Jie Liu, Liang Lin. Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels. IEEE Transactions on Multimedia, 2024. 

•  Hefeng Wu, Guangzhi Ye, Ziyang Zhou, Ling Tian, Qing Wang, Liang Lin. Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition. IEEE Transactions on Multimedia, 2024. 

•  Tao Pu, Tianshui Chen, Hefeng Wu, Yongyi Lu, Liang Lin. Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation. IEEE Transactions on Image Processing, 33: 556-568, 2024.

•  Hefeng Wu, Hao Jiang, Keze Wang, Ziyi Tang, Xianghuan He, Liang Lin. Improving Network Interpretability via Explanation Consistency Evaluation. IEEE Transactions on Multimedia, 2024. 

•  Hefeng Wu, Weifeng Chen, Zhibin Liu, Tianshui Chen, Zhiguang Chen, Liang Lin. Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search. IEEE Transactions on Circuits and Systems for Video Technology, 2023.

•  Tianshui Chen, Tao Pu, Hefeng Wu*, Yuan Xie, Lingbo Liu, Liang Lin. Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12): 9887-9903, 2022.

•  Tianshui Chen, Liang Lin, Riquan Chen, Xiaolu Hui, Hefeng Wu. Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(3): 1371-1384, 2022.

•  Lingbo Liu, Jingwen Chen, Hefeng Wu, Jiajie Zhen, Guanbin Li, Liang Lin. Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction. IEEE Transactions on Intelligent Transportation Systems, 23(4): 3377-3391, 2022.

•  Tao Pu, Tianshui Chen, Hefeng Wu, Liang Lin. Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels. Proc. of AAAI Conference on Artificial Intelligence (AAAI), 2091-2098, 2022.

•  Tianshui Chen, Tao Pu, Hefeng Wu, Yuan Xie, Liang Lin. Structured Semantic Transfer for Multi-Label Recognition with Partial Labels. Proc. of AAAI Conference on Artificial Intelligence (AAAI), 339-346, 2022.

•  Jie Wu, Tianshui Chen, Hefeng Wu, Zhi Yang, Guangchun Luo, Liang Lin. Fine-Grained Image Captioning with Global-Local Discriminative Objective. IEEE Transactions on Multimedia, 23: 2413-2427, 2021.

•  Lingbo Liu, Jiaqi Chen, Hefeng Wu, Guanbin Li, Chenglong Li, Liang Lin. Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting. Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4823-4833, 2021. 

•  Tao Pu, Tianshui Chen, Yuan Xie, Hefeng Wu, Liang Lin. AU-Expression Knowledge Constrained Representation Learning for Facial Expression Recognition. Proc. of IEEE International Conference on Robotics and Automation (ICRA), 11154-11161, 2021. 

•  Riquan Chen, Tianshui Chen, Xiaolu Hui, Hefeng Wu*, Guanbin Li, Liang Lin. Knowledge Graph Transfer Network for Few-Shot Recognition. Proc. of AAAI Conference on Artificial Intelligence (AAAI), 10575-10582, 2020. (oral)

•  Lingbo Liu, Jiaqi Chen, Hefeng Wu*, Tianshui Chen, Guanbin Li, Liang Lin. Efficient Crowd Counting via Structured Knowledge Transfer. Proc. ACM International Conference on Multimedia (ACM MM), 2645-2654, 2020.

•  Yuan Xie, Tianshui Chen, Tao Pu, Hefeng Wu, Liang Lin. Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition. Proc. ACM International Conference on Multimedia (ACM MM), 1255-1264, 2020. (oral)

•  Jie Wu, Tianshui Chen, Lishan Huang, Hefeng Wu, Guanbin Li, Ling Tian, Liang Lin. Active Object Search. Proc. ACM International Conference on Multimedia (ACM MM), 973-981, 2020. (oral)

•  Lixian Yuan, Zhilin Qiu, Lingbo Liu, Hefeng Wu*, Tianshui Chen, Pei Chen, Liang Lin. Crowd counting via scale-communicative aggregation networks. Neurocomputing, 409: 420-430, 2020.

•  Hefeng Wu, Yafei Hu, Keze Wang, Hanhui Li, Lin Nie, Hui Cheng. Instance-aware representation learning and association for online multi-person tracking. Pattern Recognition, 94: 25-34, 2019.

•  Tianshui Chen, Muxin Xu, Xiaolu Hui, Hefeng Wu*, and Liang Lin. Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition. Proc. IEEE International Conference on Computer Vision (ICCV), 2019.

•  Ning Liu, Yongchao Long, Changqing Zou, Qun Niu, Li Pan, Hefeng Wu*. ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding. Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3225-3234, 2019.

•  Daiguo Deng, Ruomei Wang, Hefeng Wu*, Huayong He, Qi Li, Xiaonan Luo. Learning deep similarity models with focus ranking for fabric image retrieval. Image and Vision Computing, 70: 11-20, 2018.

•  Ning Liu, Chang Liu, Hefeng Wu*, Hengzheng Zhu, Jin Zhan. Weak-structure-aware visual object tracking with bottom-up and top-down context exploration.  Signal Processing: Image Communication,  68: 169-180,  2018.

•  Hanhui Li, Hefeng Wu, Shujin Lin, Xiaonan Luo. Coupling deep correlation filter and online discriminative learning for visual object tracking. Journal of Computational and Applied Mathematics, 329: 191-201, 2018.

•  Hanhui Li, Hefeng Wu*, Huifang Zhang, Shujin Lin, Xiaonan Luo, Ruomei Wang. Distortion-Aware Correlation Tracking. IEEE Transactions on Image Processing, 26(11): 5421-5434, 2017.

•  Chengying Gao, Yanmei Luo, Hefeng Wu*, Dong Wang. Data-driven image completion for complex objects. Signal Processing: Image Communication, 57: 21-32, 2017.

•  Hanhui Li, Hefeng Wu, Xiangjian He, Shujin Lin, Ruomei Wang, Xiaonan Luo. Multi-view pairwise relationship learning for sketch based 3D shape retrieval. Proc. IEEE International Conference on Multimedia and Expo (ICME), 1434-1439, 2017.

•  Fei Wang, Shujin Lin, Xiaonan Luo, Hefeng Wu, Ruomei Wang, Fan Zhou. A Data-Driven Approach for Sketch-Based 3D Shape Retrieval via Similar Drawing-Style Recommendation. Computer Graphics Forum, 36(7): 157-166, 2017.

•  Hanhui Li, Hefeng Wu*, Shujin Lin, Liang Lin, Xiaonan Luo, Ebroul Izquierdo. Boosting Zero-Shot Image Classification via Pairwise Relationship Learning. Proc. 13th Asian Conference on Computer Vision (ACCV), 85-99, Nov. 2016. (oral)

•  Fei Wang, Shujin Lin, Hefeng Wu, Ruomei Wang, Xiaonan Luo. Data-driven method for sketch-based 3D shape retrieval based on user similar draw-style recommendation. Proc. SIGGRAPH Asia, Posters, 2016. 

•  Jin Zhan, Hefeng Wu*, Huifang Zhang, Xiaonan Luo. Cascaded Probabilistic Tracking with Supervised Dictionary Learning. Signal Processing: Image Communication, 39: 212-225, 2015.

•  Ning Liu, Hefeng Wu, Liang Lin. Hierarchical Ensemble of Background Models for PTZ-based Video Surveillance. IEEE Transactions on Cybernetics, 45(1): 89-102, 2015.