Sciweavers

166 search results - page 26 / 34
» A Hybrid Learning Approach for Better Recognition of Visual ...
Sort
View
ICIP
2007
IEEE
14 years 1 months ago
Incorporating Primal Sketch Based Learning Into Low Bit-Rate Image Compression
This paper proposes an image compression approach, in which we incorporate primal sketch based learning into the mainstream image compression framework. The key idea of our approa...
Yang Li, Xiaoyan Sun, Hongkai Xiong, Feng Wu
CVPR
2006
IEEE
14 years 1 months ago
Depth from Familiar Objects: A Hierarchical Model for 3D Scenes
We develop an integrated, probabilistic model for the appearance and three-dimensional geometry of cluttered scenes. Object categories are modeled via distributions over the 3D lo...
Erik B. Sudderth, Antonio B. Torralba, William T. ...
RSS
2007
152views Robotics» more  RSS 2007»
13 years 9 months ago
Dimensionality Reduction Using Automatic Supervision for Vision-Based Terrain Learning
Abstract— This paper considers the problem of learning to recognize different terrains from color imagery in a fully automatic fashion, using the robot’s mechanical sensors as ...
Anelia Angelova, Larry Matthies, Daniel M. Helmick...
CVPR
2010
IEEE
14 years 3 months ago
Data Fusion through Cross-modality Metric Learning using Similarity-Sensitive Hashing
Visual understanding is often based on measuring similarity between observations. Learning similarities specific to a certain perception task from a set of examples has been show...
Michael Bronstein, Alexander Bronstein, Nikos Para...
ICCV
2011
IEEE
12 years 7 months ago
Relative Attributes
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
Devi Parikh, Kristen Grauman