Compositionality, the ability to combine existing concepts and generaliz...
Identifying humans with their walking sequences, known as gait recogniti...
This paper addresses the problem of human rendering in the video with
te...
Gait recognition, which identifies individuals based on their walking
pa...
Phrase grounding models localize an object in the image given a referrin...
Most current state-of-the-art connectome reconstruction pipelines have t...
The task of referring relationships is to localize subject and object
en...
When learning to sketch, beginners start with simple and flexible shapes...
Deep learning methods have achieved promising performance in many areas,...