This is your work, valued
The University of Hong Kong. PhD student. Computer Vision. Multimodal Models.
ReferFormer. [CVPR2022] Official Implementation of ReferFormer
356Optimizer-Experiments-Pytorch. SGD/ADAM/Amsgrad/AdamW/RAdam/Lookahead
10SP-TAD. Towards High-Quality Temporal Action Detection with Sparse Proposals
10FFmpeg-CUDA. C++
6action-recognition. A codebase for simple action-recognition
2DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
1