3-fold Accuracy: 98.0
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
3-fold Accuracy: 97.6
3-fold Accuracy: 98.2
3-fold Accuracy: 97.3
3-fold Accuracy: 97
3-fold Accuracy: 97.1
3-fold Accuracy: 97.62
3-fold Accuracy: 97.6
3-fold Accuracy: 97.2
3-fold Accuracy: 97.2
3-fold Accuracy: 97.4
3-fold Accuracy: 96.9
3-fold Accuracy: 97.1
3-fold Accuracy: 97.8
3-fold Accuracy: 97.8
3-fold Accuracy: 98.6
3-fold Accuracy: 98.6
3-fold Accuracy: 96.8
3-fold Accuracy: 98.2
3-fold Accuracy: 96.5
3-fold Accuracy: 96.7
3-fold Accuracy: 98.6