We introduce a method to synthesize animator guided human motion across ...
In this work, we study how to build socially intelligent robots to assis...
Language model (LM) pre-training has proven useful for a wide variety of...
Generative models are now capable of producing highly realistic images t...
In this paper, we introduce Watch-And-Help (WAH), a challenge for testin...
In this paper, we are interested in modeling complex activities that occ...
Recognizing arbitrary objects in the wild has been a challenging problem...
Scene parsing, or recognizing and segmenting objects and stuff in an ima...