Sciweavers

125 search results - page 14 / 25
» Generative Models for Labeling Multi-object Configurations i...
Sort
View
TOG
2002
162views more  TOG 2002»
13 years 7 months ago
Jigsaw image mosaics
This paper introduces a new kind of mosaic, called Jigsaw Image Mosaic (JIM), where image tiles of arbitrary shape are used to compose the final picture. The generation of a Jigsa...
Junhwan Kim, Fabio Pellacini
CVPR
2012
IEEE
11 years 9 months ago
Discovering localized attributes for fine-grained recognition
Attributes are visual concepts that can be detected by machines, understood by humans, and shared across categories. They are particularly useful for fine-grained domains where c...
Kun Duan, Devi Parikh, David J. Crandall, Kristen ...
ICCV
2007
IEEE
14 years 9 months ago
What, where and who? Classifying events by scene and object recognition
We propose a first attempt to classify events in static images by integrating scene and object categorizations. We define an event in a static image as a human activity taking pla...
Li-Jia Li, Fei-Fei Li 0002
PAKDD
2005
ACM
128views Data Mining» more  PAKDD 2005»
14 years 25 days ago
A Framework for Incorporating Class Priors into Discriminative Classification
Abstract. Discriminative and generative methods provide two distinct approaches to machine learning classification. One advantage of generative approaches is that they naturally mo...
Rong Jin, Yi Liu
ICPR
2000
IEEE
13 years 11 months ago
Hand Posture Estimation by Combining 2-D Appearance-Based and 3-D Model-Based Approaches
This paper proposes a method for the rapid and precise estimation of human hand postures by combining 2-D appearance matching and 3-D model-based fitting. First a rough posture e...
Nobutaka Shimada, Kousuke Kimura, Yoshiaki Shirai,...