1. Daps: Deep action proposals for action understanding;escorcia;Eur Conf Comput Vis,0
2. Attention is not all you need: Pure attention loses rank doublyexponentially with depth;dong;Int Conf Machine Learning,0
3. Mobilenets: Efficient convolutional neural networks for mobile vision applications;howard;IEEE Conf Comput Vis Pattern Recog,0
4. SlowFast Networks for Video Recognition
5. Enriching Local and Global Contexts for Temporal Action Localization