mAP: 53.8
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
Accuracy (Cross-Subject): 95.1Accuracy (Cross-Setup): 96.1
mAP: 84.0
Accuracy (Cross-Subject): 95.6Accuracy (Cross-Setup): 96.7
Accuracy: 83.16
Accuracy (Cross-Subject): 90.5Accuracy (Cross-Setup): 91.4
mAP: 90.5
mAP: 87.9
mWAP: 30.5
Accuracy (Cross-Subject): 94.3Accuracy (Cross-Setup): 92.4
Accuracy (Cross-Subject): 91.1Accuracy (Cross-Setup): 92.8
mAP: 83.4
mWAP: 60.8
Accuracy (Cross-Subject): 90.0Accuracy (Cross-Setup): 91.7
mAP: 95.9
Accuracy (Cross-Subject): 89.4Accuracy (Cross-Setup): 91.4
Top-1 Accuracy: 34.2
mAP: 78.9
mWAP: 40.7
mAP: 89.9
Accuracy (Cross-Subject): 92.9Accuracy (Cross-Setup): 94.4
mAP: 90.05
mAP: 94.3
Accuracy (Cross-Subject): 95.3Accuracy (Cross-Setup): 96.4
mAP: 84.4
Accuracy (Cross-Subject): 90.3Accuracy (Cross-Setup): 92.7
mAP: 93.7
mAP: 53.8