Sciweavers

9 search results - page 1 / 2
» CENTRIST: A Visual Descriptor for Scene Categorization
Sort
View
PAMI
2011
12 years 7 months ago
CENTRIST: A Visual Descriptor for Scene Categorization
—CENTRIST (CENsus TRansform hISTogram), a new visual descriptor for recognizing topological places or scene categories, is introduced in this paper. We show that place and scene ...
Jianxin Wu, James M. Rehg
MM
2010
ACM
336views Multimedia» more  MM 2010»
13 years 4 months ago
Movie genre classification via scene categorization
This paper presents a method for movie genre categorization of movie trailers, based on scene categorization. We view our approach as a step forward from using only low-level visu...
Howard Zhou, Tucker Hermans, Asmita V. Karandikar,...
ICIP
2009
IEEE
14 years 5 months ago
Recognizing Human Actions By Fusing Spatio-temporal Appearance And Motion Descriptors
In this paper we propose a new method for human action categorization by using an effective combination of a new 3D gradient descriptor with an optic flow descriptor, to represent...
MM
2009
ACM
159views Multimedia» more  MM 2009»
13 years 11 months ago
Visual categorization with negative examples for free
Automatic visual categorization is critically dependent on labeled examples for supervised learning. As an alternative to traditional expert labeling, social-tagged multimedia is ...
Xirong Li, Cees G. M. Snoek
EMMCVPR
2005
Springer
13 years 10 months ago
Object Categorization by Compositional Graphical Models
This contribution proposes a compositionality architecture for visual object categorization, i.e., learning and recognizing multiple visual object classes in unsegmented, cluttered...
Björn Ommer, Joachim M. Buhmann