3 papers
cs.CV2021
Home Action Genome: Cooperative Compositional Action Understanding
Nishant Rai, Haofeng Chen, Jingwei Ji +5
Existing research on action recognition treats activities as monolithic events occurring in videos. Recently, the benefits of formulating actions as a combination of atomic-actions…
cs.CV2021
Weak Multi-View Supervision for Surface Mapping Estimation
Nishant Rai, Aidas Liaudanskas, Srinivas Rao +3
We propose a weakly-supervised multi-view learning approach to learn category-specific surface mapping without dense annotations. We learn the underlying surface geometry of common…
cs.CV2021
CoCon: Cooperative-Contrastive Learning
Nishant Rai, Ehsan Adeli, Kuan-Hui Lee +2
Labeling videos at scale is impractical. Consequently, self-supervised visual representation learning is key for efficient video analysis. Recent success in learning image represen…