Sciweavers

173 search results - page 15 / 35
» Object recognition based on binary partition trees
Sort
View
ICCV
2009
IEEE
14 years 9 months ago
Efficient multi-label ranking for multi-class learning: Application to object recognition
Multi-label learning is useful in visual object recognition when several objects are present in an image. Conventional approaches implement multi-label learning as a set of binary...
Serhat Selcuk Bucak, Pavan Kumar Mallapragada, Ron...
ISPD
1999
ACM
79views Hardware» more  ISPD 1999»
15 years 4 months ago
Partitioning with terminals: a "new" problem and new benchmarks
The presence of fixed terminals in hypergraph partitioning instances arising in top-down standard-cell placement makes such instances qualitatively different from the free hyperg...
Charles J. Alpert, Andrew E. Caldwell, Andrew B. K...
MCS
2005
Springer
15 years 5 months ago
Half-Against-Half Multi-class Support Vector Machines
A Half-Against-Half (HAH) multi-class SVM is proposed in this paper. Unlike the commonly used One-Against-All (OVA) and One-Against-One (OVO) implementation methods, HAH is built ...
Hansheng Lei, Venu Govindaraju
89
Voted
CVPR
2004
IEEE
16 years 1 months ago
Integrating Multiple Model Views for Object Recognition
We present a new approach to appearance-based object recognition, which captures the relationships between multiple model views and exploits them to improve recognition performanc...
Vittorio Ferrari, Tinne Tuytelaars, Luc J. Van Goo...
NIPS
2004
15 years 1 months ago
A Three Tiered Approach for Articulated Object Action Modeling and Recognition
Visual action recognition is an important problem in computer vision. In this paper, we propose a new method to probabilistically model and recognize actions of articulated object...
Le Lu, Gregory D. Hager, Laurent Younes