Top-1 Accuracy: 68.1Top-5 Accuracy: 91.2Parameters: N/AGFLOPs: 1181x3
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: 67.7Top-5 Accuracy: 91.1
Top-1 Accuracy: 68.7Top-5 Accuracy: 91.5Parameters: 53.2MGFLOPs: 236x3
Top-1 Accuracy: 69.02Top-5 Accuracy: 92.70
Top-1 Accuracy: 69.5Top-5 Accuracy: 91.5Parameters: N/AGFLOPs: N/A
Top-1 Accuracy: 67.7Top-5 Accuracy: 91.1
Top-1 Accuracy: 67.2Top-5 Accuracy: 89.8
Top-1 Accuracy: 67.1
Top-1 Accuracy: 67.8Top-5 Accuracy: 91.1Parameters: 83.8GFLOPs: 280
Top-1 Accuracy: 67.35Top-5 Accuracy: 90.50Parameters: 5.8MGFLOPs: 20.9x6
Top-1 Accuracy: 67.6
Top-1 Accuracy: 67.8Top-5 Accuracy: 91.2Parameters: 27.4GFLOPs: 110.1
Top-1 Accuracy: 69.5Top-5 Accuracy: 91.9Parameters: 94GFLOPs: 41x6
Top-1 Accuracy: 68.5
Top-1 Accuracy: 67.8
Top-1 Accuracy: 68.2
Top-1 Accuracy: 68.5Top-5 Accuracy: 90.4
Top-1 Accuracy: 67.3Top-5 Accuracy: 91
Top-1 Accuracy: 67.2Top-5 Accuracy: 90.8Parameters: N/AGFLOPs: 850x1
Top-1 Accuracy: 67.0
Top-1 Accuracy: 68.2Top-5 Accuracy: 91.6GFLOPs: 198x1
Top-1 Accuracy: 69.4Top-5 Accuracy: 92.1Parameters: 21.4GFLOPs: 41.8x3
Top-1 Accuracy: 68.1