Long Chen

sca-cnn.cvpr17. Image Captions Generation with Spatial and Channel-wise Attention

sp-aen.cvpr18. Zero-Shot Visual Recognition using Semantic-Preserving Adversarial Embedding Networks

Thesis-latex. my Ph.D. thesis (Zhejiang University)

WSAG. [EMNLP'22] Weakly-Supervised Temporal Article Grounding

faster-rcnn.pytorch. fork from https://github.com/jwyang/faster-rcnn.pytorch

YouwikiHow. YouwikiHow dataset for weakly-supervised article grounding

Seminar. copy from https://github.com/D-X-Y/Seminar-X

S3D_Feature_Extractors. Extract S3D Video Features