- Ego-Exo4D and ROSA accepted to CVPR 2024, both as oral.
- Ego4D Goal-Step and HT-Step presented at NeurIPS 2023 in New Orleans.
- Ego-Only, DiffMAE, and SMAUG presented remotely at ICCV 2023, Paris, France.
- DMAE presented at CVPR 2023.
- 3/3 submissions accepted to ECCV 2022.
- 3/3 submissions accepted to CVPR 2022.
- iBOT accepted to ICLR 2022.
- DeepLab2 released, with MaX-DeepLab and Axial-DeepLab officially re-implemented in TensorFlow2.
- MaX-DeepLab accepted to CVPR 2021, proposing Mask Transformers for end-to-end panoptic segmentation.
- Axial-DeepLab, the first architecture with global attention in all layers, accepted to ECCV 2020.
Research Experience
Currently a Research Scientist at FAIR (Meta). Previously, spent two years as a student researcher at Google and had wonderful summers at Allen Institute for Artificial Intelligence and TuSimple.
Education
Ph.D. in Computer Science from Johns Hopkins University, advised by Professor Alan Yuille; M.S. in Electrical Engineering from the University of California, Los Angeles; B.S. in Information Engineering from Shanghai Jiao Tong University.
Background
Research Interest: Computer Vision with a focus on understanding images and videos.