67 search results - page 13 / 14 » Quasi-Invariants for Human Action Representation and Recogni... |
IJCV
2010
13 years 3 months ago
2010
Real-world actions occur often in crowded, dynamic environments. This poses a difficult challenge for current approaches to video event detection because it is difficult to segm...
ICIAR
2010
Springer
13 years 3 months ago
2010
Springer
Abstract. Face-to-face communications between humans involve emotions, which often are unconsciously conveyed by facial expressions and body gestures. Intelligent human-machine int...
MM
2003
ACM
13 years 10 months ago
2003
ACM
In this paper, we propose an approach that retrieves motion of objects from the videos based on the dynamic time warping of view invariant characteristics. The motion is represent...
MM
2006
ACM
13 years 11 months ago
2006
ACM
Human vision system actively seeks interesting regions in images to reduce the search effort in tasks, such as object detection and recognition. Similarly, prominent actions in v...
ISRR
2005
Springer
13 years 10 months ago
2005
Springer
ys when planning meant searching for a sequence of abstract actions that satisfied some symbolic predicate. Robots can now learn their own representations through statistical infe...