I am Xiangtai and I work as a Research Fellow at MMLab@NTU S-Lab advised by Prof.Chen Change Loy.

I obtained my PhD degree at Peking University (PKU). My PhD supervisor is Prof.Yunhai Tong. I obtained my bachelor degree at Beijing University of Posts and Telecommunications (BUPT).

I am working on the following research directions:

πŸ”­ Pixel-Wised Scene Understanding for Video/Image Scene Understanding, including (Semantic/Instance/Panoptic) Segmentation and Object Detection, zero/few shot variants.

πŸ”­ General deep learning Method with its application, including Vision Transformer, Efficient Model Design, Neural Collapse.

πŸ”­ Vision meets language, including Open Vocabulary Learning, Visual Prompting, Visual Grounding.

Previously, I did some research on Image/Video Semantic/Instance/Panoptic Segmentation as well as several related problems during my PhD.

πŸ”₯ News

  • 2022.11:Two paper on Video Scene Understanding is accepted by T-PAMI.
  • 2022.09:One paper on Neural Collapse is accepted by NeurIPS-2022.
  • 2022.08: Β πŸŽ‰πŸŽ‰ Join the MMLab@NTU S-Lab! Our four works (Video K-Net, PanopticPartFormer, FashionFormer, and PolyphonicFormer in CVPR-22/ECCV-22) code are all released. Check out my github homepage.
  • 2022.07: Β πŸŽ‰πŸŽ‰ Our SFNet-Lite (extension of SFNet-ECCV20) achieve the best mIoU and speed trade-off. on multiple driving datasets. SFNet-Lite can obtain 80.1 mIoU while running at 50 FPS, 78.8 mIoU while running at 120 FPS. Code.
  • 2022.07: Β πŸŽ‰πŸŽ‰ Three papers are accepted by ECCV-2022. One paper is accepted by ICIP-2022.
  • 2022.07: Β πŸŽ‰πŸŽ‰ Graduated From PKU.
  • 2022.03: Β πŸŽ‰πŸŽ‰ Video K-Net is accepted by CVPR-2022 as oral presentation.

πŸ“ Selected Publications

Full Publications Per Year can be found in Here.

* means equal contribution.

Code can be found in this.

Selected Conference

Selected Journal

Selected Arxiv

πŸŽ– Honors and Awards

  • National Scholarship, Ministry of Education of China in PKU (year 2020-2021) (year 2019-2020)
  • President Scholarship of PKU (year 2020-2021)
  • 2017, 2022 Beijing Excellent Graduates
  • 2017, 2022 BUPT/PKU Excellent Graduates
  • 2021.11 Winner of Segmenting and Tracking Every Point and Pixel: 6th Workshop on ICCV-2021 Track2 (Project Leader and First Author)

πŸ“– Educations

  • 2017.09 - 2022.06, PhD in Peking University (PKU)
  • 2013.09 - 2017.06, Bachelor in Beijing University of Posts and Telecommunications (BUPT)

πŸ’¬ Invited Talks

  • 2022.05 Invited talk on Panoptic Segmentation and Beyond in Baidu PaddleSeg Group
  • 2021.12 Invited talk on Video Segmentation in DiDi Auto-Driving Group
  • 2021.10 Invited talk on Aligned Segmentation HuaWei Noah Auto-Driving Group

πŸ’» Internships and Professional activities