View-invariant action recognition
This research addresses the challenge of view-invariant action recognition for applications in surveillance and human-computer interaction, but it appears incremental as it builds on existing work without specifying novel breakthroughs.
The paper tackles the problem of human action recognition from unseen viewpoints, addressing the performance drop when viewpoint changes, and focuses on recognizing actions across different perspectives.
Human action recognition is an important problem in computer vision. It has a wide range of applications in surveillance, human-computer interaction, augmented reality, video indexing, and retrieval. The varying pattern of spatio-temporal appearance generated by human action is key for identifying the performed action. We have seen a lot of research exploring this dynamics of spatio-temporal appearance for learning a visual representation of human actions. However, most of the research in action recognition is focused on some common viewpoints, and these approaches do not perform well when there is a change in viewpoint. Human actions are performed in a 3-dimensional environment and are projected to a 2-dimensional space when captured as a video from a given viewpoint. Therefore, an action will have a different spatio-temporal appearance from different viewpoints. The research in view-invariant action recognition addresses this problem and focuses on recognizing human actions from unseen viewpoints.