本人主要研究方向为计算机视觉，包括视频行为理解、目标检测与分割、三维场景重建与理解、目标抓取姿态估计、AI4S（气象分析、空间科学等）等，欢迎感兴趣同学联系。近几年代表性论文如下：

一、代表性成果

[1]. Wenfei Yang, Huan Ren Ren , Tianzhu Zhang*, Zhe Zhang , Yongdong Zhang , Feng Wu. Cross-Task Relation-Aware Consistency for Weakly Supervised Temporal Action Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2025.

[2]. Wenfei Yang, Chuxin Wang, Tianzhu Zhang*, Yongdong Zhang, Feng Wu. SA3Det++: Side-Aware Quality Estimation for Semi-Supervised 3D Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2025.

[3]. Wenfei Yang, Tianzhu Zhang*, Yongdong Zhang, Feng Wu. Uncertainty guided collaborative training for weakly supervised and unsupervised temporal action detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2022, 1, 1-15.

[4]. Wenfei Yang, Tianzhu Zhang, Yongdong Zhang, Feng Wu. Local correspondence network for weakly supervised temporal sentence grounding. IEEE Transactions on Image Processing (T-IP), 2021, 30: 3252-3262.

[5]. Wenfei Yang, Tianzhu Zhang, Zhendong Mao, Yongdong Zhang, Qi Tian, Feng Wu. Multi-Scale Structure-Aware Network for Weakly Supervised Temporal Action Detection. IEEE Transactions on Image Processing (T-IP), 2021,30: 5848-5861.

二、其他论文

[6]. Zhixin Cheng, Jiacheng Deng, Xinjun Li, Xiaotian Yin, Bohao Liao, Baoqun Yin, Wenfei Yang*, Tianzhu Zhang. CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection. International Conference on Computer Vision (ICCV), 2025.

[7]. Chuxin Wang, Yixin Zha, Wenfei Yang*, Tianzhu Zhang. StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning. International Conference on Computer Vision (ICCV), 2025.

[8]. Wenjie Chang, Hanzhi Chang, Yueyi Zhang, Wenfei Yang*, Tianzhu Zhang. Learning Neural Scene Representation from iToF Imaging. International Conference on Computer Vision (ICCV), 2025.

[9]. Han Jiang, Wenfei Yang*, Tianzhu Zhang, Yongdong Zhang. Diffusion-based Source-biased Model for Single Domain Generalized Object Detection. International Conference on Computer Vision (ICCV), 2025.

[10]. Ziyang Song, Ruijie Zhu, Jing Wang, Chuxin Wang, Jianfeng He, Jiacheng Deng, Wenfei Yang*， Tianzhu Zhang. ER-Depth: Enhancing the Robustness of Self-Supervised MonocularDepth Estimation in Challenging Scenes. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2025.

[11]. Ye Zhou, Wenfei Yang*, Tianzhu Zhang, Xiang Liu. Prototype-based Optimal Transport for Box-Supervised 3D Instance Segmentation. IEEE International Conference on Multimedia & Expo, Oral, 2025.

[12]. Jiacheng Deng, Jiahao Lu, Zhixin Cheng, Wenfei Yang*. DiffCorr: Conditional Diffusion Model with Reliable Pseudo-Label Guidance for Unsupervised Point Cloud Shape Correspondence. AAAI Conference on Artificial Intelligence, 2024. 

[13]. Yuwen Pan, Rui Sun, Yuan Wang, Wenfei Yang*, Tianzhu Zhang, and Yongdong Zhang. Purify then Guide: A Bi-directional Bridge Network for Open-Vocabulary Semantic Segmentation. IEEE Transactions on Circuits and Systems for Video Technology, 2024. 

[14]. Xin Liu, Jiamin Wu, Wenfei Yang*, Xu Zhou, Tianzhu Zhang*. Multi-Modal Attribute Prompting for Vision-Language Models.IEEE Transactions on Circuits and Systems for Video Technology, 2024. 

[15]. Huakai Lai, Wenfei Yang*, Tianzhu Zhang*, Yongdong Zhang. Reliable Phrase Feature Mining for Hierarchical Video-Text Retrieval. IEEE Transactions on Circuits and Systems for Video Technology, 2024. 

[16]. Xiaotian Yin, Jiamin Wu, Wenfei Yang*, Xu Zhou, Shifeng Zhang, Tianzhu Zhang*. Hierarchy-Aware Interactive Prompt Learning for Few-Shot Classification. IEEE Transactions on Circuits and Systems for Video Technology, 2024. 

[17]. Li Liu, Ruijie Zhu, Jiacheng Deng , Ziyang Song , Wenfei Yang*, Tianzhu Zhang*. Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2024. 

[18]. Wenfei Yang, Tianzhu Zhang, Xiaoyuan Yu, Qi Tian, Yongdong Zhang, Feng Wu. Uncertainty guided collaborative training for weakly supervised temporal action detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Oral论文, 2021: 53-63.