Action Parsing
2 papers with code • 0 benchmarks • 2 datasets
Action parsing is the task of, given a video or still image, assigning each frame or image a label describing the action in that frame or image.
Benchmarks
These leaderboards are used to track progress in Action Parsing
TAPOS
Home Action Genome
Latest papers
Frontal Low-rank Random Tensors for Fine-grained Action Segmentation
In this paper, we propose an approach to representing high-order information for temporal action segmentation via a simple yet effective bilinear form.
Local Temporal Bilinear Pooling for Fine-grained Action Parsing
yz-cnsdqz/TemporalActionParsing-FineGrained
•
•
CVPR 2019
Fine-grained temporal action parsing is important in many applications, such as daily activity understanding, human motion analysis, surgical robotics and others requiring subtle and precise operations in a long-term period.
