Accuracy: 75.93
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: 74.9
Average Accuracy: 66.45
Accuracy: 52.44
3-fold Accuracy: 98.8
Accuracy: 69.88
Accuracy (Cross-Subject): 89.12Accuracy (Cross-Setup): 90.97
Accuracy (Cross-Subject): 91.6Accuracy (Cross-Setup): 90.4
3-fold Accuracy: 99.7
F-measure (%): 90.27
Top 1 Accuracy: 71.46
Accuracy (Cross-Subject): 71.59Accuracy (Cross-Setup): 70.8
Top-1 Accuracy: 94.3Top-5 Accuracy: 99.2
3-fold Accuracy: 98.69
Accuracy: 62.98
Accuracy (Cross-Subject): 85.6Accuracy (Cross-Setup): 87.5
Accuracy: 52.6
3-fold Accuracy: 99.6
3-fold Accuracy: 99.6
Accuracy (Cross-Subject): 66.9Accuracy (Cross-Setup): 64.6
Accuracy (Cross-Subject): 67.7Accuracy (Cross-Setup): 66.9
Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints
Accuracy (Cross-Subject): 62.8Accuracy (Cross-Setup): 67.9
3-fold Accuracy: 98.64
Accuracy: 21.2
Accuracy (Cross-Subject): 79.2Accuracy (Cross-Setup): 78.3
3-fold Accuracy: 99.6
Accuracy (Cross-Subject): 87.8Accuracy (Cross-Setup): 86.3
Accuracy (Cross-Subject): 92.5Accuracy (Cross-Setup): 90.7