AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions.
Chunhui GuChen SunSudheendra VijayanarasimhanCaroline PantofaruDavid A. RossGeorge TodericiYeqing LiSusanna RiccoRahul SukthankarCordelia SchmidJitendra MalikPublished in: CoRR (2017)