A complete representation of 3D objects requires characterizing the space of deformations in an interpretable manner, from articulations of a single i...

In the paradigm of online continual learning, one neural network is exposed to a sequence of tasks, where the data arrive in an online fashion and pre...

Graph convolution networks (GCNs) based methods for 3D human pose estimation usually aggregate immediate features of single-hop nodes, which are unawa...

The ability to capture detailed interactions among individuals in a social group is foundational to our study of animal behavior and neuroscience. Rec...

Zero-shot learning (ZSL) requires one to associate visual and semantic information observed from data of seen classes, so that test data of unseen cla...