Sciweavers

659 search results - page 32 / 132
» Object Labelling from Human Action Recognition
Sort
View
CVIU
2004
94views more  CVIU 2004»
15 years 1 months ago
Video-based event recognition: activity representation and probabilistic recognition methods
We present a new representation and recognition method for human activities. An activity is considered to be composed of action threads, each thread being executed by a single act...
Somboon Hongeng, Ramakant Nevatia, François...
ICPR
2008
IEEE
16 years 3 months ago
Action recognition based on homography constraints
In this paper, we present a new approach for viewinvariant action recognition using constraints derived from the eigenvalues of planar homographies associated with triplets of bod...
Hassan Foroosh, Nazim Ashraf, Yuping Shen
CVPR
2007
IEEE
16 years 4 months ago
Epitomic Representation of Human Activities
We introduce an epitomic representation for modeling human activities in video sequences. A video sequence is divided into segments within which the dynamics of objects is assumed...
Naresh P. Cuntoor, Rama Chellappa
IJRR
2010
214views more  IJRR 2010»
14 years 11 months ago
Object Recognition in 3D Point Clouds Using Web Data and Domain Adaptation
Over the last years, object detection has become a more and more active field of research in robotics. An important problem in object detection is the need for sufficient labeled ...
Kevin Lai, Dieter Fox
IUI
2012
ACM
13 years 9 months ago
Towards recognizing "cool": can end users help computer vision recognize subjective attributes of objects in images?
Recent computer vision approaches are aimed at richer image interpretations that extend the standard recognition of objects in images (e.g., cars) to also recognize object attribu...
William Curran, Travis Moore, Todd Kulesza, Weng-K...