3D panoptic segmentation is a challenging perception task that requires ...
Self-supervised skeleton-based action recognition enjoys a rapid growth ...
Bag manipulation through robots is complex and challenging due to the
de...
The last decades are marked by massive and diverse image data, which sho...
Weakly supervised point cloud semantic segmentation methods that require...
In group activity recognition, hierarchical framework is widely adopted ...
Night-Time Scene Parsing (NTSP) is essential to many vision applications...
Information Bottleneck (IB) based multi-view learning provides an inform...
Video moment retrieval aims to search the moment most relevant to a give...
Convolutional neural networks (CNNs) are highly successful for
super-res...
Single image dehazing is a challenging ill-posed problem due to the seve...
The Information Bottleneck (IB) provides an information theoretic princi...
Multi-index fusion has demonstrated impressive performances in retrieval...