1. Zero-shot learning by convex combination of semantic embeddings;norouzi;ICLRE,2014
2. HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
3. Decoupled weight decay regularization;loshchilov;International Conference on Learning Representations,0
4. Use what you have: Video retrieval using representations from collaborative experts;liu;British Machine Vision Conference,0