ActionVLAD: Learning spatio-temporal aggregation for action classification

Rohit Girdhar, Deva Ramanan, Abhinav Gupta, Josef Sivic, Bryan Russell

URL

Proceedings: CVPR

Year: 2017

Peer Reviewed : Yes

Results: 
HMDB /HMDB Eval: 69.8%
UCF101 /UCF101 Eval: 93.6%
Charades /Video classification: 21% (ActionVLAD (RGB only, BN-inception) + iDT)