Average accuracy of 3 splits: 80.9
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
Average accuracy of 3 splits: 80.5
Average accuracy of 3 splits: 80.5
Average accuracy of 3 splits: 78.7
Average accuracy of 3 splits: 79.6
Average accuracy of 3 splits: 83.1
Average accuracy of 3 splits: 82.60
Average accuracy of 3 splits: 77.6
Average accuracy of 3 splits: 80.92
Average accuracy of 3 splits: 81.9
Average accuracy of 3 splits: 77.8
Average accuracy of 3 splits: 82.48
Average accuracy of 3 splits: 78.7
Average accuracy of 3 splits: 85.70
Average accuracy of 3 splits: 85.10
Average accuracy of 3 splits: 80.9
Average accuracy of 3 splits: 77.4
Average accuracy of 3 splits: 83.8
Average accuracy of 3 splits: 83.2
Average accuracy of 3 splits: 84.53
Average accuracy of 3 splits: 81.1
Average accuracy of 3 splits: 84.36
Average accuracy of 3 splits: 86.11
Average accuracy of 3 splits: 83.4