Accuracy: 81
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
Top 1 Accuracy: 55.0
Accuracy: 82.6
Accuracy: 90.6
Top 1 Accuracy: 47.4
Accuracy: 86.7
Average accuracy of 3 splits: 88.6
Accuracy: 88.7
Accuracy: 94.9
Top 1 Accuracy: 39.1
Accuracy: 87.6
Average accuracy of 3 splits: 87.21
Accuracy: 88.3
Top 1 Accuracy: 50.8
Accuracy: 88.0
Accuracy: 84.2
Accuracy: 91.3
Average accuracy of 3 splits: 87.56
Accuracy: 77.6
Accuracy: 86
Accuracy: 81.8
Accuracy: 88.3
Accuracy: 90.8
Average accuracy of 3 splits: 88.7
Accuracy: 85.5