Top-1 Accuracy: 65.8Top-5 Accuracy: 89.5Parameters: 5.8MGFLOPs: 20.9x6
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: 66.6Top-5 Accuracy: 90.6
Top-1 Accuracy: 62.5
Top-1 Accuracy: 63.5Top-5 Accuracy: 89.0Parameters: 4.8MGFLOPs: 10.3x1
Top-1 Accuracy: 66Top-5 Accuracy: 89.8
Top-1 Accuracy: 65.6Top-5 Accuracy: 89.2
Top-1 Accuracy: 64.3
Top-1 Accuracy: 64.94Top-5 Accuracy: 87.9
Top-1 Accuracy: 66.8Top-5 Accuracy: 90.3
Top-1 Accuracy: 66.5Top-5 Accuracy: 90.1
Top-1 Accuracy: 66.5Top-5 Accuracy: 90.4
Top-1 Accuracy: 65.7Top-5 Accuracy: 89.8
Top-1 Accuracy: 65.7Top-5 Accuracy: 89.8GFLOPs: 18.3
Top-1 Accuracy: 65.2
Top-1 Accuracy: 66.2Top-5 Accuracy: 90.2
Top-1 Accuracy: 66.3
Top-1 Accuracy: 62.5Top-5 Accuracy: 86.2
Top-1 Accuracy: 66.5Top-5 Accuracy: 90.6
Top-1 Accuracy: 66.6Top-5 Accuracy: 91.3
Top-1 Accuracy: 65.4Top-5 Accuracy: 89.8