Sciweavers

159 search results - page 19 / 32
» Many-to-one boundary labeling
Sort
View
ICCV
2011
IEEE
13 years 9 months ago
Annotator Rationales for Visual Recognition
Traditional supervised visual learning simply asks annotators “what” label an image should have. We propose an approach for image classification problems requiring subjective...
Jeff Donahue, Kristen Grauman
ICCV
2005
IEEE
15 years 11 months ago
Incorporating Visual Knowledge Representation in Stereo Reconstruction
In this paper, we present a two-layer generative model that incorporates generic middle-level visual knowledge for dense stereo reconstruction. The visual knowledge is represented...
Adrian Barbu, Song Chun Zhu
91
Voted
ICCV
2009
IEEE
16 years 2 months ago
Scene Shape Priors for Superpixel Segmentation
Unsupervised over-segmentation of an image into superpixels is a common preprocessing step for image parsing algorithms. Superpixels are used as both regions of support for feat...
Alastair P. Moore, Simon J. D. Prince, Jonathan Wa...
ICPR
2002
IEEE
15 years 10 months ago
Illumination Invariant Segmentation of Spatio-Temporal Images by Spatio-Temporal Markov Random Field Model
For many years, object tracking in images has suffered from the problems of occlusions and illumination effects. In order to resolve occlusion problems, we have been proposing the...
Shunsuke Kamijo, Katsushi Ikeuchi, Masao Sakauchi
76
Voted
SIGGRAPH
2010
ACM
15 years 2 months ago
Vector solid textures
In this paper, we introduce a compact random-access vector representation for solid textures made of intermixed regions with relatively smooth internal color variations. It is fea...
Lvdi Wang, Kun Zhou, Yizhou Yu, Baining Guo