A Caltech Library Service

Attentional Selection for Object Recognition — A Gentle Way

Walther, Dirk B. and Itti, Laurent and Riesenhuber, Maximilian and Poggio, Tomaso and Koch, Christof (2002) Attentional Selection for Object Recognition — A Gentle Way. In: Biologically Motivated Computer Vision : Second International Workshop, BMCV 2002 Tübingen, Germany, November 22–24, 2002 Proceedings. Lecture Notes in Computer Science. No.2525. Springer , Berlin, pp. 472-479. ISBN 9783540001744.

PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Attentional selection of an object for recognition is often modeled using all-or-nothing switching of neuronal connection pathway from the attended region of the retinal input to the recognition units. However, there is little physiological evidence for such all-or-none modulation in early areas. We present a combined model for spatial attention and object recognition in which the recognition system monitors the entire visual field, but attentional modulation by as little as 20% at a high level is sufficient to recognize multiple objects. To determine the size and shape of the region to be modulated, a rough segmentation is performed, based on pre-attentive features already computed to guide attention. Testing with synthetic and natural stimuli demonstrates that our new approach to attentional selection for recognition yields encouraging results in addition to being biologically plausible.

Item Type:Book Section
Related URLs:
URLURL TypeDescription ReadCube access
Koch, Christof0000-0001-6482-8067
Additional Information:© Springer-Verlag Berlin Heidelberg 2002. This work was supported by NSF (ITR, ERC and KDI), NEI, NIMA, DARPA, the Zumberge Faculty Research and Innovation Fund (L.I.), the Charles Lee Powell Foundation, a McDonnell-Pew Award in Cognitive Neuroscience (M.R.), Eastman Kodak Company, Honda R&D Co., Ltd., ITRI, Komatsu Ltd., Siemens Corporate Research, Inc., Toyota Motor Corporation and The Whitaker Foundation.
Group:Koch Laboratory (KLAB)
Funding AgencyGrant Number
Defense Advanced Research Projects Agency (DARPA)UNSPECIFIED
Zumberge Faculty Research and Innovation FundUNSPECIFIED
Charles Lee Powell FoundationUNSPECIFIED
McDonnell-Pew Award in Cognitive NeuroscienceUNSPECIFIED
Eastman Kodak CompanyUNSPECIFIED
Siemens Corporate Research, Inc.UNSPECIFIED
Toyota Motor CorporationUNSPECIFIED
Whitaker FoundationUNSPECIFIED
Series Name:Lecture Notes in Computer Science
Issue or Number:2525
Record Number:CaltechAUTHORS:20130816-103235815
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:40539
Deposited By: KLAB Import
Deposited On:11 Jan 2008 23:38
Last Modified:09 Nov 2021 23:49

Repository Staff Only: item control page