Recent advances in egocentric video understanding models are promising, ...
First-person video highlights a camera-wearer's activities in the contex...
Complex physical tasks entail a sequence of object interactions, each wi...
We introduce an approach for pre-training egocentric video models using
...
We introduce environment predictive coding, a self-supervised approach t...
The data drawn from biological, economic, and social systems are often
c...
Embodied agents operating in human spaces must be able to master how the...
First-person video naturally brings the use of a physical environment to...
Learning how to interact with objects is an important step towards embod...
Learning how to interact with objects is an important step towards embod...
We present a new approach to modeling visual attributes. Prior work cast...
Very deep convolutional neural networks offer excellent recognition resu...
Distant Supervision for Relation Extraction uses heuristically aligned t...