Website Search
Find information on spaces, staff, and services.
Find information on spaces, staff, and services.
Human action recognition using RGB video is a challenging task because the learning of actions is easily affected by the cluttered background. To cope with this problem, the proposed method estimat...
Human action recognition using RGB video is a challenging task because the learning of actions is easily affected by the cluttered background. To cope with this problem, the proposed method estimates 3D human poses first which can help remove the cluttered background and focus on the human body. In addition to the human poses, the proposed method also utilizes appearance features nearby the predicted joints to make our action prediction context-aware. In this talk, we show how we use a two-stream architecture that aggregates the results from skeleton based and appearance-based approaches to do action recognition.