AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions

Chunhui Gu, Chen Sun, Sudheendra Vijayanarasimhan, Caroline Pantofaru, David A. Ross, George Toderici, Yeqing Li, Susanna Ricco, Rahul Sukthankar, Cordelia Schmid, Jitendra Malik

URL

Proceedings: arXiv

Year: 2016

Peer Reviewed : No

Results: 
AVA /MAP@IOU of 0.5: 18.4% (RGB + Deep Flow)
AVA /MAP@IOU of 0.5: 18.1% (RGB + TVL-1)