Sciweavers

515 search results - page 99 / 103
» Learning Image Components for Object Recognition
Sort
View
MM
2010
ACM
169views Multimedia» more  MM 2010»
14 years 9 months ago
CO3 for ultra-fast and accurate interactive segmentation
This paper presents an interactive image segmentation framework which is ultra-fast and accurate. Our framework, termed "CO3", consists of three components: COupled repr...
Yibiao Zhao, Song Chun Zhu, Siwei Luo
CVPR
2004
IEEE
15 years 11 months ago
BoostMap: A Method for Efficient Approximate Similarity Rankings
This paper introduces BoostMap, a method that can significantly reduce retrieval time in image and video database systems that employ computationally expensive distance measures, ...
Vassilis Athitsos, Jonathan Alon, Stan Sclaroff, G...
ICMCS
2007
IEEE
155views Multimedia» more  ICMCS 2007»
15 years 3 months ago
Hidden Maximum Entropy Approach for Visual Concept Modeling
Recently, the bag-of-words approach has been successfully applied to automatic image annotation, object recognition, etc. The method needs to first quantize an image using the vis...
Sheng Gao, Joo-Hwee Lim, Qibin Sun
PR
2007
81views more  PR 2007»
14 years 9 months ago
Graph embedding using tree edit-union
In this paper we address the problem of how to learn a structural prototype that can be used to represent the variations present in a set of trees. The prototype serves as a patte...
Andrea Torsello, Edwin R. Hancock
CVPR
2006
IEEE
15 years 11 months ago
Composite Templates for Cloth Modeling and Sketching
Cloth modeling and recognition is an important and challenging problem in both vision and graphics tasks, such as dressed human recognition and tracking, human sketch and portrait...
Hong Chen, Zijian Xu, Ziqiang Liu, Song Chun Zhu