English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Automatic Discovery of Meaningful Object Parts with Latent CRFs

Schnitzspan, P., Roth, S., & Schiele, B. (2010). Automatic Discovery of Meaningful Object Parts with Latent CRFs. In 2010 IEEE Conference on Computer Vision and Pattern Recognition (pp. 121-128). Piscataway, NJ: IEEE. doi:10.1109/CVPR.2010.5540220.

Item is

Basic

show hide
Genre: Conference Paper
Latex : Automatic Discovery of Meaningful Object Parts with Latent {CRF}s

Files

show Files
hide Files
:
schnitzspan10cvpr.pdf (Any fulltext), 2MB
 
File Permalink:
-
Name:
schnitzspan10cvpr.pdf
Description:
-
OA-Status:
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Schnitzspan, Paul1, Author
Roth, Stefan1, Author
Schiele, Bernt2, Author           
Affiliations:
1External Organizations, ou_persistent22              
2Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: -
 Abstract: Object recognition is challenging due to high intra-class variability caused, e.g., by articulation, viewpoint changes, and partial occlusion. Successful methods need to strike a balance between being flexible enough to model such variation and discriminative enough to detect objects in cluttered, real world scenes. Motivated by these challenges we propose a latent conditional random field (CRF) based on a flexible assembly of parts. By modeling part labels as hidden nodes and developing an EM algorithm for learning from class labels alone, this new approach enables the automatic discovery of semantically meaningful object part representations. To increase the flexibility and expressiveness of the model, we learn the pairwise structure of the underlying graphical model at the level of object part interactions. Efficient gradient-based techniques are used to estimate the structure of the domain of interest and carried forward to the multi-label or object part case. Our experiments illustrate the meaningfulness of the discovered parts and demonstrate state-of-the-art performance of the approach.

Details

show
hide
Language(s): eng - English
 Dates: 20102010
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: eDoc: 536678
BibTex Citekey: 419
DOI: 10.1109/CVPR.2010.5540220
Other: Local-ID: C12576EE0048963A-D49250F5CBFD4F78C1257819004AA56C-Schnitzspan2010
 Degree: -

Event

show
hide
Title: 2010 IEEE Conference on Computer Vision and Pattern Recognition
Place of Event: San Francisco, USA
Start-/End Date: 2010-06-15 - 2010-06-17

Legal Case

show

Project information

show

Source 1

show
hide
Title: 2010 IEEE Conference on Computer Vision and Pattern Recognition
  Abbreviation : CVPR 2010
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 121 - 128 Identifier: ISBN: 978-1-4244-6984-0