Human intelligence can retrieve any person according to both visual and
...
Human-centric perceptions (e.g., pose estimation, human parsing, pedestr...
Self-supervised learning holds promise in leveraging large numbers of
un...
Self-training for unsupervised domain adaptive object detection is a
cha...
Interactive segmentation allows users to extract target masks by making
...
The pretrain-finetune paradigm is a classical pipeline in visual learnin...
Compared with other semantic segmentation tasks, portrait segmentation
r...