Human skeletons and RGB sequences are both widely-adopted input modaliti...
Recently, learned image compression methods have developed rapidly and
e...
Visual object tracking acts as a pivotal component in various emerging v...
Neural image compression have reached or out-performed traditional metho...
2D image-based virtual try-on has attracted increased attention from the...
The constraint of neighborhood consistency or local consistency is widel...
Triplet loss is widely used for learning local descriptors from image pa...
RGB-Infrared person re-identification (RGB-IR ReID) is a cross-modality
...
The bandwidth of a kernel function is a crucial parameter in the mean sh...