Average accuracy of 3 splits: 62.8
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 (CS): 96.3Accuracy (CV): 99.0
Average accuracy of 3 splits: 62.8
Average accuracy of 3 splits: 49.2
Accuracy (CS): 97.4Accuracy (CV): 99.4
Accuracy (CS): 96.2Accuracy (CV): 98.0
Accuracy (CS): 94.3Accuracy (CV): 97.2
Average accuracy of 3 splits: 56.4
Average accuracy of 3 splits: 54.9
Accuracy (CS): 94.3Accuracy (CV): 97.9
Average accuracy of 3 splits: 54.8
Accuracy (CS): 93.4Accuracy (CV): 98.1
Accuracy (CS): 96.1Accuracy (CV): 99.0
Accuracy (CS): 94.7Accuracy (CV): 97.7
Accuracy: 81.95
Accuracy (CS): 95.66Accuracy (CV): 98.79
Accuracy (CS): 93.8Accuracy (CV): 97.1
Average accuracy of 3 splits: 51.6
Accuracy (CS): 96.0Accuracy (CV): 98.8
Accuracy (CS): 93.7Accuracy (CV): 98.9
Average accuracy of 3 splits: 54.2
Accuracy (CS): 97.0Accuracy (CV): 99.6
Average accuracy of 3 splits: 62.7
Average accuracy of 3 splits: 51.8
Average accuracy of 3 splits: 59.4
Accuracy (CS): 95.5Accuracy (CV): 98.0