Face benchmarks empower the research community to train and evaluate
hig...
Recently, face recognition in the wild has achieved remarkable success a...
According to WHO statistics, there are more than 204,617,027 confirmed
C...
In this paper, we contribute a new million-scale face benchmark containi...
Non-local operations are usually used to capture long-range dependencies...
Deep neural networks (DNNs) have achieved great success in a wide range ...
Channel pruning, which seeks to reduce the model size by removing redund...
Existing methods in video action recognition mostly do not distinguish h...
Obtained by moving object detection, the foreground mask result is unsha...
Real-time motion detection in non-stationary scenes is a difficult task ...
Real-time moving object detection in unconstrained scenes is a difficult...
From the frame/clip-level feature learning to the video-level representa...
For the two-stream style methods in action recognition, fusing the two
s...