Space-Time Crop & Attend:
Improving Cross-modal Video Representation Learning.
Mandela Patrick*, Po-Yao Huang , Ishan Misra, Florian Metze, Andrea Vedaldi
Facebook AI Research
mandelapatrick,berniehuang,imisra,fmetze,vedaldi@fb.com
Yuki M. Asano , Joao Henriques
Oxford University
yuki, joao@robots.ox.ac.uk
Abstract StiCA ...


雷达卡




京公网安备 11010802022788号







