Professor
Artificial Intelligence Institute, Shanghai Jiao Tong University
800 Dongchuan Road, Software Building, Shanghai 200240 China

Research Interests

My research interests lie in the fields of computer vision, deep learning, and medical image analysis, particularly in image segmentation, 3D vision and their application to medical image analysis.

Short Bio

Wei Shen is a professor at the Artificial Intelligence Institute, Shanghai Jiao Tong University. He received NSFC Excellent Young Scientists Fund. He was an Assistant Research Professor at the Department of Computer Science, Johns Hopkins University, worked with Bloomberg Distinguished Professor Alan Yuille. He has over 100 peer-reviewed publications in computer vision and machine learning related areas, including IEEE Trans. PAMI, IJCV, IEEE Trans. Medical Imaging, NeurIPS, ICML, ICCV, CVPR, ECCV and MICCAI. He served as an Area Chair for multiple top-tier international conferences, such as ICCV, CVPR, NeurIPS and ICML. He is an Associate Editor for Pattern Recognition and SCIENCE CHINA Information Sciences. He received the MICCAI Young Scientist Award in 2023, CSIG Young Scientist Award in 2025 and Huawei Spark Award in 2026.

Recent News

• I was awarded Huawei Spark Award.
• Five papers have been accepted to CVPR 2026.
• One paper has been accepted to IEEE TPAMI.
• I will serve as an Area Chair for ECCV 2026.
• I was awarded CSIG Young Scientist Award.
• I will serve as an Area Chair for ICML 2026.
• One paper has been accepted to IEEE JBHI.
• Five papers have been accepted to AAAI 2026, where one is oral.
• Two papers have been accepted to NeurIPS 2025, where one is oral.

  • HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
  • OPMapper: Enhancing Open-Vocabulary Semantic Segmentation with Multi-Guidance Information

• I will serve as an Area Chair for CVPR 2026.
• Two papers have been accepted to ICCV 2025.

  • Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations
  • A Token-level Text Image Foundation Model for Document Understanding

• My PhD student Chen Yang passed his doctoral oral defense. Congratulations!
• One paper has been accepted to ICML 2025.

  • Tackling View-Dependent Semantics in 3D Language Gaussian Splatting

• My computer vision textbook Hands On Computer Vision was published, which is now available for purchase at JD and other booksellers.
• One paper has been accepted to IJCV.

  • Segment Anything in 3D with Radiance Fields

• Five papers have been accepted to CVPR 2025.
• I will serve as an Area Chair for NeurIPS 2025.
• One paper has been accepted to IEEE TPAMI.

  • CCDPlus: Towards Accurate Character to Character Distillation for Text Recognition

• Two papers have been accepted to ICLR 2025.
• I will serve as an Area Chair for ICML 2025.
• Two papers have been accepted to AAAI 2025.

  • Segment Any 3D Gaussians

• I will serve as an Area Chair for ICCV 2025.
• One paper has been accepted to ACM Trans. Graphics (Siggraph Asia 2024).

  • GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting

• Four papers have been accepted to ECCV 2024.

  • Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors
  • Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation
  • PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer
  • UniProcessor: A Text-induced Unified Low-level Image Processor

• Two papers have been accepted to MICCAI 2024.

  • EndoGSLAM: Real-Time Dense Reconstruction and Tracking in Endoscopic Surgeries using Gaussian Splatting
  • Missing as Masking: Arbitrary Cross-modal Feature Reconstruction for Incomplete Multimodal Brain Tumor Segmentation

• I serve as an Associate Editor for Pattern Recognition from 2024.
• I will serve as an Area Chair for NeurIPS 2024.
• One paper has been accepted to IEEE TMI.

  • Efficient Deformable Tissue Reconstruction via Orthogonal Neural Plane

• One paper has been accepted to CVPR 2024.

  • Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model

• Three papers have been accepted to AAAI 2024.

  • SAM-PARSER: Fine-tuning SAM Efficiently by Parameter Space Reconstruction
  • ViTree: Single-Path Neural Tree for Step-Wise Interpretable Fine-Grained Visual Categorization
  • Partial Label Learning with a Partner

• Our MICCAI 2023 paper receives Young Scientist Award.

  • Neural LerPlane Representations for Fast 4D Reconstruction of Deformable Tissues

• One paper has been accepted to NeurIPS 2023.

  • Segment Anything in 3D with NeRFs

• I will serve as an Area Chair for WACV 2024.
• Three papers have been accepted to ICCV 2023.
• I will serve as an Area Chair for NeurIPS 2023.
• Four papers have been accepted to CVPR 2023.
• One paper has been accepted to IEEE TPAMI.

  • A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction

• I will serve as an Area Chair for CVPR 2023.