Val: 90.77
Papers with Code · CC BY-SA 4.0
Action Recognition In Videos
Action Recognition in Videos is a task in computer vision and pattern recognition where the goal is to identify and categorize human actions performed in a video sequence. The task involves analyzing the spatiotemporal dynamics of the actions and mapping them to a predefined set of action classes, such as running, jumping, or swimming.
논문
Top-1 Accuracy(5-Way-1-Shot): 49.2Top-1 Accuracy(5-Way-5-Shot): 62.3
Val: 96.7
Val: 95.31
Val: 95.31
Val: 96.7
Val: 96.68
Accuracy (CS): 85.5
Val: 92.7
3-fold Accuracy: 43.9
mAP (Val): 18.24
Clip Hit@1: 49.7Video hit@1: 62.8Video hit@5: 85.5
mAP (Val): 20.2
mAP: 75.6