-
SOGAR: Self-supervised spatiotemporal attention-based social group activity r...
SOGAR: Self-supervised spatiotemporal attention-based social group activity recognition. -
Group activity recognition using self-supervised approach of spatiotemporal t...
Group activity recognition using self-supervised approach of spatiotemporal transformers. -
REACT: Recognize Every Action Everywhere All At Once
Group Activity Recognition (GAR) is a fundamental problem in computer vision, with diverse applications in sports video analysis, video surveillance, and social scene... -
Collective Activities Dataset
The Collective Activities dataset consists of 44 videos taken in unconstrained real-world scenarios of people performing 6 individual actions across 5 group activities.
