Sciweavers

569 search results - page 64 / 114
» Composite Models of Objects and Scenes for Category Recognit...
Sort
View
CVPR
2010
IEEE
14 years 4 months ago
Learning Mid-Level Features For Recognition
Many successful models for scene or object recognition transform low-level descriptors (such as Gabor filter responses, or SIFT descriptors) into richer representations of interme...
Y-Lan Boureau, Francis Bach, Yann LeCun, Jean Ponc...
ICPR
2006
IEEE
14 years 8 months ago
Forest Extension of Error Correcting Output Codes and Boosted Landmarks
In this paper, we introduce a robust novel approach for detecting objects category in cluttered scenes by generating boosted contextual descriptors of landmarks. In particular, ou...
Oriol Pujol, Petia Radeva, Sergio Escalera
CIVR
2010
Springer
235views Image Analysis» more  CIVR 2010»
13 years 6 months ago
Dynamic textures for human movement recognition
Human motion can be seen as a type of texture pattern. In this paper, we adopt the ideas of spatiotemporal analysis and the use of local features for motion description. movements...
Vili Kellokumpu, Guoying Zhao, Matti Pietikäi...
JUCS
2007
133views more  JUCS 2007»
13 years 7 months ago
Building Immersive Conversation Environment Using Locomotive Interactive Character
: Generating composite human motion such as locomotion and gestures is important for interactive applications, such as interactive storytelling and computer games. In interactive s...
Rai Chan, Junichi Hoshino
ICCV
2009
IEEE
2205views Computer Vision» more  ICCV 2009»
15 years 19 days ago
Video stabilization using robust feature trajectories
This paper proposes a new approach for video stabilization. Most existing video stabilization methods adopt a framework of three steps, motion estimation, motion compensation an...
Ken-Yi Lee, Yung-Yu, Chuang Bing-Yu, Chen Ming Ouh...