Top 1 Accuracy: 84.33Top 5 Accuracy: 96.85
Papers with Code · CC BY-SA 4.0
Activity Recognition
Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.
<span class="description-source">Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters </span>
논문
Action@1: 37.39
Top-1 (%): 64.4
Accuracy (% ): 93.75
mAP: 40
Accuracy: 92.5
Accuracy: 93.25
Val: 98.15
Top-1: 65.25Top-5: 87.93
Top 1 Accuracy: 97.0
Val: 95.56
Action@1: 36.8Verb@1: 64.8Noun@1: 47.4GFLOPs: 1.74x1
Val: 97.4
leave one out cross validation(LOOCV): 98.27
Top-1 Accuracy: 42.85
Top 1 Accuracy: 95.5Top 5 Accuracy: 99.8
Position Accuracy: 96.32 %Armstand Accuracy: 99.72 %Rotation Type Accuracy: 97.45 %No. of Somersaults Accuracy: 96.88 %