Average accuracy of 3 splits: 76.4
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: 74.8
Average accuracy of 3 splits: 65.9
Average accuracy of 3 splits: 70.9
Average accuracy of 3 splits: 72.0
Average accuracy of 3 splits: 74.3
Average accuracy of 3 splits: 65.4
Average accuracy of 3 splits: 71.8
Average accuracy of 3 splits: 65.2
Average accuracy of 3 splits: 72.6
Average accuracy of 3 splits: 75.7
Average accuracy of 3 splits: 71.13
Average accuracy of 3 splits: 76.5
Average accuracy of 3 splits: 75.7
Average accuracy of 3 splits: 71.5
Average accuracy of 3 splits: 64.8
Average accuracy of 3 splits: 74.2
Average accuracy of 3 splits: 75.9
Average accuracy of 3 splits: 67.2
Average accuracy of 3 splits: 72.2
Average accuracy of 3 splits: 70.3
Average accuracy of 3 splits: 69.4
Average accuracy of 3 splits: 69
Average accuracy of 3 splits: 74.4
Average accuracy of 3 splits: 65.9