Temporal action detection (TAD) aims to detect all action boundaries and...
Significant advancements have been made in multi-object tracking (MOT) w...
In this paper, we present a one-stage framework TriDet for temporal acti...
Deep supervised learning algorithms generally require large numbers of
l...
This work addresses the problem of generating 3D holistic body motions f...
The key challenge of sequence representation learning is to capture the
...
Person re-identification aims to identify whether pairs of images belong...
Typical methods for supervised sequence modeling are built upon the recu...
In this paper, we introduce a new large-scale face dataset named VGGFace...
Face recognition performance evaluation has traditionally focused on
one...
Recently, metric learning and similarity learning have attracted a large...