Accuracy (Top-1): 79.39
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
Video hit@1 : 73.3Video hit@5: 91.9
Top-3 Accuracy (%): 10.47
Video hit@1 : 75.5Video hit@5: 92.8
accuracy: 91%
Accuracy: 3.05
Top-1 Accuracy: 95.9
Video hit@1 : 71.7Video hit@5: 90.4
Activity Recognition: 0.76
accuracy: 96.25%
Accuracy (Cross-Subject): 94.4Accuracy (Cross-View): 96.5
Accuracy: 89.75
Top 1 Accuracy: 92.7
Accuracy: 89.3
Accuracy: 90.25
Clip Hit@1: 41.9Video hit@1 : 60.9Video hit@5: 80.2
Clip Hit@1: 47.9Video hit@1 : 66.4Video hit@5: 87.4
Clip Hit@1: 46.1Video hit@1 : 61.1Video hit@5: 85.5
1:1 Accuracy: 97.91
Accuracy: 87.25
Accuracy: 93.4
Accuracy: 90.4
accuracy: 88.8%