PhD student, Huazhong University of Science and Technology, Computer Vision
-
HUST | Research intern at ByteDance
- Wuhan, China
- https://wjf5203.github.io/
-
TokBench Public
Image and video Tokenizer/VAE selection guide, text and face reconstruction evaluation.
-
-
cocoapi Public
Forked from XD7479/cocoapiCOCO API Customized for YouTubeVIS evaluation
-
SeqFormer Public
SeqFormer: Sequential Transformer for Video Instance Segmentation (ECCV 2022 Oral)