Xuming He

Associate Professor PLUS Lab School of Information Science and Technology (SIST) ShanghaiTech University Address Room 1A-221, SIST Building 393 Middle Huaxia Road Pudong, Shanghai, 201210, China Contact Phone: +86 21 20685378 Email: hexm at shanghaitech dot edu dot cn

News

• [01/2023] Two papers accepted in ICLR 2023.

• [01/2023] Congratulations to Tailin Chen for receiving Best Student Paper Award at FG 2023.

• [12/2022] Congratulations to Yongfei Liu for successfully completing his Phd Degree.

• [11/2022] Congratulations to Shipeng Yan for successfully completing his Phd Degree.

• [07/2022] Two papers accepted in ECCV 2022.

Research Interest

• Weakly-supervised/Few-shot learning

• Continual learning/Knowledge discovery

• Semantic segmentation and Scene parsing

• Vision and language representations

• Interpretable machine learning and reasoning

Prospective students

• Prospective graduate students: please check admission website. 学科方向: 计算机科学与技术.

• We also have multiple research projects (minimal 6 months) for undergrad students in SIST.

Selected Publications

• Shipeng Yan, Lanqing Hong, Hang Xu, Jianhua Han, Tinne Tuytelaars, Zhenguo Li, Xuming He. Generative Negative Text Replay for Continual Vision-Language Pretraining, European Conference of Computer Vision (ECCV), 2022

• Jiangwei Xie, Shipeng Yan, Xuming He. General Incremental Learning with Domain-aware Categorical Representations, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022

• Rongjie Li, Songyang Zhang, Xuming He. SGTR: End-to-end Scene Graph Generation with Transformer, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022

• Jialei Zhou, Songyang Zhang, Xuming He. Learning Implicit Temporal Alignment for Few-shot Video Classification, International Joint Conference on Artificial Intelligence (IJCAI), 2021

• Shipeng Yan, Jiangwei Xie, Xuming He. DER: Dynamically Expandable Representation for Class Incremental Learning, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

• Yongfei Liu, Bo Wan, Lin Ma, Xuming He. Relation-aware Instance Refinement for Weakly Supervised Visual Grounding, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

• Yongfei Liu, Xiangyi Zhang, Songyang Zhang, Xuming He. Part-aware prototype Network for Few-shot Semantic Segmentation, European Conference of Computer Vision (ECCV), 2020

• Haozhe Wang, Jiale Zhou, Xuming He. Learning Context-aware Task Reasoning for Efficient Meta-reinforcement Learning, International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2020

• Bo Wan*, Desen Zhou*, Yongfei Liu, Rongjie Li, Xuming He. Pose-aware Multi-level Feature Network for Human Object Interaction Detection, International Conference on Computer Vision (ICCV), 2019

• Songyang Zhang, Shipeng Yan, Xuming He. LatentGNN: Learning Efficient Non-local Relations for Visual Recognition, International Conference on Machine Learning (ICML),2019

• Alexander Mathews, Lexing Xie, Xuming He. SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

• Zeeshan Hayder, Xuming He, Mathieu Salzmann. Boundary-aware Instance Segmentation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

• Buyu Liu, Xuming He. Multiclass Semantic Video Segmentation With Object-Level Active Inference, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015

• Xuming He, and Richard S. Zemel. Learning Hybrid Models for Image Annotation with Partially Labeled Data, Annual Conference on Neural Information Processing Systems (NIPS), 2008

• Xuming He, Richard Zemel, and Miguel Carreira-Perpinan. Multiscale Conditional Random Fields for Image Labelling, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2004