Shivani Agarwal, Dan Roth  Home/Search
Context Related
| uiuc.edu/~danr/Paper...vrelations.ps.gz Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: uiuc.edu/~danr/publications (more) Homepages: S.Agarwal D.Roth |
Rate this article:      (best)Comment on this article |
Abstract: We present an approach for learning to detect objects in still gray images, that is based on a sparse, part-based representation of objects. A vocabulary of information-rich object parts is automatically constructed from a set of sample images of the object class of interest. Images are then represented using parts from this vocabulary, along with spatial relations observed among them. Based on this representation, a feature-efficient learning algorithm is used to learn to detect instances of... (Update)
Context of citations to this paper: More
.... developed in the context of natural language problems is its success in facilitating learning in visual recognition problems [31, 1], as part of our attempt to study learning in multi modal environments. The knowledge representation and learning approach are identical...
Cited by: More
Research Summary 1997-2001 - Roth (Correct)
Active bibliography (related documents): More All
0.2: Learning Representative Local Features For Face Detection - Chen, Gu, Li, Zhang (Correct)
0.2: Translation Invariance in Object Recognition, and Its Relation .. - Dill, Edelman (1997) (Correct)
0.2: The Use of Classifiers in Sequential Inference - Punyakanok, Roth (2001) (Correct)
Similar documents based on text: More All
0.2: An Experimental Study of Semi-Supervised EM - Algorithms In Audio (2003) (Correct)
0.2: An Analysis of Interest Operators for FIDO - Cmu-Ri-Tr- (1983) (Correct)
0.1: ZOO: A Desktop Experiment Management Environment - Ioannidis (1996) (Correct)
Related documents from co-citation: More All
2: UIUC Computer Science Department (context) - Roth, learning et al. - 1999
2: Learning to recognize objects - Roth, Yang et al. - 2000
BibTeX entry: (Update)
S. Agarwal and D. Roth. Detecting objects by learning relations over parts. Technical Report UIUCDCSR - http://citeseer.ist.psu.edu/agarwal02detecting.html More
@inproceedings{ agarwalroth02,
author = "Shivani Agarwal and Dan Roth",
title = "Learning a sparse representation for object detection",
booktitle = "Proceedings of the 7th European Conference on Computer Vision",
volume = "4",
pages = "113-130",
year = "2002",
url = "citeseer.ist.psu.edu/agarwal02detecting.html" }
Citations (may not include all citations):227 Recognition by components: a theory of human image understan.. (context) - Biederman - 1987
84 object detection applied to faces and cars (context) - Schneiderman, Kanade et al. - 2000
64 Learning to resolve natural language ambiguities: A unied ap.. - Roth - 1998
58 Unsupervised learning of models for recognition - Weber, Welling et al. - 2000
34 A SNoW-based face detector - Yang, Roth et al. - 2000
20 Visual object recognition (context) - Logothetis, Sheinberg - 1996
19 A computational model for visual selection - Amit, Geman - 1999
18 Computer and Robot Vision II (context) - Haralick, Shapiro - 1993
15 UIUC Computer Science Department (context) - Carlson, Cumby et al. - 1999
15 Hierarchical structure in perceptual representation (context) - Palmer - 1977
8 Learning to recognize objects - Roth, Yang et al. - 2000
7 Object detection in images by components - Mohan - 1999
6 Recognition of objects and their component parts: responses .. (context) - Wachsmuth, Oram et al. - 1994
Documents on the same site (http://l2r.cs.uiuc.edu/~danr/publications.html): More
Defaults and Relevance in Model Based Reasoning - Khardon, Roth (1997) (Correct)
Learning to Reason with a Restricted View - Khardon, Roth (1995) (Correct)
Learning to Reason - Khardon (1994) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC