Multiple-object tracking and segmentation (MOTS) is a novel computer vis...
In this paper, we propose a novel perspective-guided convolution (PGC) f...
Recognizing attributes of objects and their parts is important to many
c...
We seek to improve crowd counting as we perceive limits of currently
pre...
The non-local module is designed for capturing long-range spatio-tempora...
Attention-based learning for fine-grained image recognition remains a
ch...