Top-1 Accuracy: 61.3Top-5 Accuracy: 88.2Parameters: 3.1MGFLOPs: 2.7x1
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-5 Accuracy: 93.4Parameters: 51.1
Top-1 Accuracy: 62.2Top-5 Accuracy: 90.3
Top-1 Accuracy: 61.7
MAP: 47.57
Top-1 Accuracy: 49.9Top-5 Accuracy: 79.1
Top-1 Accuracy: 40.2
mAP: 96.1
Top-1 Accuracy: 47.73
Top-1 Accuracy: 61.2Top-5 Accuracy: 89.3
Accuracy: 99.7
Accuracy (% ): 96.53
Top 1 Accuracy: 38.6
Top-1 Accuracy: 52.3
Top-1 Accuracy: 1Top-5 Accuracy: 12Parameters: 2131GFLOPs: 13321
Top-1 Accuracy: 59.5
Top-5 Accuracy: 91.1
mAP: 96.9
Top-1 Accuracy: 59.2
Accuracy: 91.86%
Top-1 Accuracy: 61.7
Accuracy: 80.23%
Accuracy: 98.7
Top-1 Accuracy: 62.0
Top-1 Accuracy: 51.33Top-5 Accuracy: 80.46
Top-1 Accuracy: 60.2
2-Class Accuracy: 75.74%