Atomic action recognition
3 papers with code • 1 benchmarks • 2 datasets
CATER
PSI-AVA
Most implemented papers
Semi-Supervised Few-Shot Atomic Action Recognition
Sausage-SONG/Few-shot-action-recognition
•
•
Despite excellent progress has been made, the performance on action recognition still heavily relies on specific datasets, which are difficult to extend new action classes due to labor-intensive labeling.
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context
tencentyouturesearch/actiondetection-lstc
•
•
We demonstrate that both temporal grains are beneficial to atomic action recognition.
Towards Holistic Surgical Scene Understanding
Second, we present Transformers for Action, Phase, Instrument, and steps Recognition (TAPIR) as a strong baseline for surgical scene understanding.
