Skeleton-based human action recognition has recently attracted increasing attention due to the popularity of 3D skeleton data. One main challenge lies in the large view variations in …
Human detection and activity recognition is very important research area in the healthcare, video surveillance, pedestrian detection, intelligent vehicle system and home care center …
Robust action recognition under viewpoint changes has received considerable attention recently. To this end, self-similarity matrices (SSMs) have been found to be effective view …
In video sequences, human action recognition is a challenging problem due to motion variation, in frame person difference, and setting of video recording in the field of computer …
We describe a new approach to transfer knowledge across views for action recognition by using examples from a large collection of unlabelled mocap data. We achieve this by directly …
Y Kong, Y Fu - IEEE transactions on pattern analysis and …, 2015 - ieeexplore.ieee.org
The speed with which intelligent systems can react to an action depends on how soon it can be recognized. The ability to recognize ongoing actions is critical in many applications, for …
Y Liu, Z Lu, J Li, T Yang - … on Circuits and Systems for Video …, 2018 - ieeexplore.ieee.org
Recognizing human actions from varied views is challenging due to huge appearance variations in different views. The key to this problem is to learn discriminant view-invariant …
Discriminative appearance features are effective for recognizing actions in a fixed view, but may not generalize well to a new view. In this paper, we present two effective approaches to …