Sciweavers

101 search results - page 10 / 21
» Coarse-to-Fine Object Recognition Using Shock Graphs
Sort
View
116
Voted
ICRA
2010
IEEE
170views Robotics» more  ICRA 2010»
15 years 10 days ago
Categorizing object-action relations from semantic scene graphs
— In this work we introduce a novel approach for detecting spatiotemporal object-action relations, leading to both, action recognition and object categorization. Semantic scene g...
Eren Erdal Aksoy, Alexey Abramov, Florentin Wö...
MM
2006
ACM
218views Multimedia» more  MM 2006»
15 years 7 months ago
SmartLabel: an object labeling tool using iterated harmonic energy minimization
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
Wen Wu, Jie Yang
PR
2007
81views more  PR 2007»
15 years 1 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
2007
IEEE
16 years 3 months ago
Learning and Matching Line Aspects for Articulated Objects
Traditional aspect graphs are topology-based and are impractical for articulated objects. In this work we learn a small number of aspects, or prototypical views, from video data. ...
Xiaofeng Ren
ICMCS
2005
IEEE
136views Multimedia» more  ICMCS 2005»
15 years 7 months ago
Human Posture Recognition with Convex Programming
We present a novel human posture recognition method using convex programming based matching schemes. Instead of trying to segment the object from the background, we develop a nove...
Hao Jiang, Ze-Nian Li, Mark S. Drew