Action@1: 47.7Verb@1: 72.2Noun@1: 57.3GFLOPs: 117x1
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
Action@1: 44.5Verb@1: 67.0Noun@1: 58.5
mAP (Val): 22.8
Action@1: 51.8Verb@1: 71.7Noun@1: 64.1
mAP (Val): 17.4
Action@1: 43.4Verb@1: 64.8Noun@1: 58
mAP (Val): 22.0
Action@1: 47.2Verb@1: 70.4Noun@1: 59.3
Action@1: 49.3Verb@1: 72.5Noun@1: 60.9
Action@1: 52.1Verb@1: 75.0Noun@1: 61.8
Action@1: 44.48Verb@1: 69.06Noun@1: 53.18
Action@1: 51Verb@1: 72Noun@1: 62.9
Action@1: 58.3Verb@1: 76Noun@1: 69
Action@1: 53.6Verb@1: 72.0Noun@1: 66.3
Action@1: 48.4Verb@1: 71.4Noun@1: 60.3
Action@1: 47.8Verb@1: 70.1Noun@1: 61.0
Action@1: 50.5Verb@1: 69.9Noun@1: 63.9
Action@1: 45.7Verb@1: 68.4Noun@1: 58.7
Action@1: 49.9Verb@1: 69.5Noun@1: 61.7
Action@1: 45.26Verb@1: 66Noun@1: 53.35
Action@1: 56.4Verb@1: 76.2Noun@1: 66.4
Action@1: 54.4Verb@1: 73.0Noun@1: 65.4
Action@1: 44.0Verb@1: 66.4Noun@1: 56.8