Rutishauser, Ueli and Walther, Dirk B. and Koch, Christof and Perona, Pietro
(2004)
Is bottom-up attention useful for object recognition?
In:
CVPR 2004. Proceedings of the 2004 IEEE Computer Society on Computer Vision and Pattern Recognition.
Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
Vol.2.
IEEE
, Los Alamitos, CA, pp. 37-44.
ISBN 0-7695-2158-4.
https://resolver.caltech.edu/CaltechAUTHORS:20110901-160517067
![[img]](https://authors.library.caltech.edu/style/images/fileicons/application_pdf.png)  Preview |
|
PDF
- Published Version
See Usage Policy.
758kB |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20110901-160517067
Abstract
A key problem in learning multiple objects from unlabeled
images is that it is a priori impossible to tell which
part of the image corresponds to each individual object,
and which part is irrelevant clutter which is not associated
to the objects. We investigate empirically to what extent
pure bottom-up attention can extract useful information
about the location, size and shape of objects from images
and demonstrate how this information can be utilized
to enable unsupervised learning of objects from unlabeled
images. Our experiments demonstrate that the proposed approach to using bottom-up attention is indeed useful for a
variety of applications.
| Item Type: | Book Section |
|---|
| Related URLs: | |
|---|
| ORCID: | |
|---|
| Additional Information: | © 2004 IEEE. Issue Date: 27 June-2 July 2004. Date of Current Version: 19 July 2004. This project was funded by the NSF Engineering Research Center for Neuromorphic Systems Engineering at Caltech, by an NSF-ITR award, the NIH and the Keck Foundation. The shape estimation code was developed by the authors as part of the ”iNVT“ community effort (http://ilab.usc.edu/toolkit).
We would like to thank Evolution Robotics for making their
robotic vision software development kit available to us. High-resolution background images were provided by TNO Human Factors Research Institute, the Netherlands. |
|---|
| Group: | Koch Laboratory (KLAB) |
|---|
| Funders: | | Funding Agency | Grant Number |
|---|
| Center for Neuromorphic Systems Engineering, Caltech | UNSPECIFIED | | NSF | UNSPECIFIED | | NIH | UNSPECIFIED | | W. M. Keck Foundation | UNSPECIFIED |
|
|---|
| Other Numbering System: | | Other Numbering System Name | Other Numbering System ID |
|---|
| INSPEC Accession Number | 8161487 |
|
|---|
| Series Name: | Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
|---|
| Record Number: | CaltechAUTHORS:20110901-160517067 |
|---|
| Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20110901-160517067 |
|---|
| Official Citation: | Rutishauser, U.; Walther, D.; Koch, C.; Perona, P.; , "Is bottom-up attention useful for object recognition?," Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on , vol.2, no., pp. II-37- II-44 Vol.2, 27 June-2 July 2004
doi: 10.1109/CVPR.2004.1315142
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1315142&isnumber=29134 |
|---|
| Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. |
|---|
| ID Code: | 25202 |
|---|
| Collection: | CaltechAUTHORS |
|---|
| Deposited By: |
Tony Diaz
|
|---|
| Deposited On: | 06 Sep 2011 23:01 |
|---|
| Last Modified: | 03 Mar 2020 13:01 |
|---|
Repository Staff Only: item control page
