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...
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...
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 ...
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...
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...