I am a Ph.D. student in the CSE Department at HKUST, supervised by Chi-Keung Tang and Yu-Wing Tai. I am now visiting the Computer Vision Lab at ETH Zürich, working with Fisher Yu and Martin Danelljan. I focus on image/video instance segmentation and object tracking, and am interested in its related applications. Prior to that, I received my B.E. degree in Software Engineering from Wuhan University.
- 2021.07: Video Mask Transfiner on high-quality VIS is accepted by ECCV 2022! We released the HQ-YTVIS dataset.
- 2021.03: PCAN serves as the baseline in BDD100K MOTS challenge at CVPR 2022 Workshop on Autonomous Driving.
- 2021.03: Mask Transfiner on high-quality instance segmentation is accepted by CVPR 2022!
- 2022.03: Invited talk on PCAN at AI Time Seminar, Tsinghua Univ (Virtual).
- 2022.02: Invited talk on Mutltiple Object Tracking & Segmentation in Autonomous Driving at TechBeat.
- 2021.12: Invited spotlight talk for PCAN at SwissTech Convention Center, EPFL.
- 2021.10: PCAN for Multiple Object Tracking and Segmentation is accepted by NeurIPS 2021 as spotlight.
- 2021.07: Our paper on occlusion-aware video inpainting accepted by ICCV 2021.
- 2021.01: I joined CVL at ETHz as a visiting PhD student supervised by Prof.Fisher Yu and Dr.Martin Danelljan.
- 2021.03: Our paper BCNet on occlusion-aware instance segmentation accepted by CVPR 2021!
- 2021.10: Passed the PhD Qualifying Exam.
- 2020.07: Two papers (GSNet and CPMask) accepted by ECCV 2020.
- 2020.02: Our paper on 3D human pose estimation has been accepted by CVPR 2020 for oral presentation.
- 2019.07: Our paper on image captioning accepted by ICCV 2019.
- 2019.05: I will start my Ph.D study at CSE, HKUST this autumn.
- 2019.02: Our paper on video captioning accepted by CVPR 2019.
Mask Transfiner for High-Quality Instance SegmentationCVPR 2022
Lei Ke, Martin Danelljan, Xia Li, Yu-Wing Tai, Chi-Keung Tang, Fisher Yu
An efficient transformer-based method for highly accurate instance segmentation.
Transfiner receives 300+ Github stars in 3 months.
Prototypical Cross-Attention Networks for Multiple Object Tracking and SegmentationNeurIPS 2021
Lei Ke, Xia Li, Martin Danelljan, Yu-Wing Tai, Chi-Keung Tang, Fisher Yu
Efficient cross-attention on space-time memory for video instance segmentation.
Spotlight (3% acceptance rate). PCAN receives 200+ Github stars in one month.
2021.01—Future: Visiting PhD student at CVL, ETHz
2019.05—Future: HKUST Computer Vision Research Assistant
2017.05—2017.10: Alibaba Engineering Intern
2016.05—2017.02: Undergraduate Research Assistant at Wuhan University
- Conference Review CVPR 2020/2021/2022, ICCV 2021, ECCV 2022, NeurIPS 2020/2021/2022, ICML 2021/2022, ICLR 2022, ICRA 2022.
- Teaching Assistant Computer Graphics (COMP4411), Spring, 2019-2020.
Introduction to Object-oriented Programming (COMP2011), Fall, 2020-2021.
- Some photography of natural scenery and delicate architecture during my daily life and travelling.