mAP (Val): 28.3
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
mAP: 33.8
mAP: 36.1
mAP (Val): 27.6GFlops: 39.6Params (M): 19.3
mAP (Val): 30.0
Accuracy (CS): 91.7
mAP (Val): 23
Accuracy (CS): 74.9
Accuracy (CS): 92.78Accuracy (CV): 97.03
mAP: 32.1
mAP: 34.1
mAP (Val): 41.7
Accuracy (CS): 86.6Accuracy (CV): 93.2
Accuracy (CS): 91.8Accuracy (CV): 94.9
Accuracy (CS): 93.2Accuracy (CV): 96.9
mAP (Val): 27.7
Accuracy (CS): 91.99
Accuracy (CS): 92.24
Accuracy (CS): 92.5Accuracy (CV): 97.4
Accuracy (CS): 87.5Accuracy (CV): 93.2
mAP (Val): 28.4
Accuracy (CS): 91.7Accuracy (CV): 95.2
Accuracy (CS): 76.5Accuracy (CV): 84.7
Accuracy (CS): 92.0Accuracy (CV): 96.5