Occlusion, Attention and Object Representations

Neil Taylor; Christo Panchev; Mathew Hartley; Statis Kasderidis; John G. Taylor

doi:10.1007/11840817_62

Occlusion, Attention and Object Representations

Neil Taylor, Christo Panchev, Mathew Hartley, Statis Kasderidis, John G. Taylor

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

5 Citations (Scopus)

Abstract

Occlusion is currently at the centre of analysis in machine vision. We present an approach to it that uses attention feedback to an occluded object to obtain its correct recognition. Various simulations are performed using a hierarchical visual attention feedback system, based on contrast gain (which we discuss as to its relation to possible hallucinations that could be caused by feedback). We then discuss implications of our results for object representations per se.

Original language	English
Title of host publication	Artificial Neural Networks – ICANN 2006
Subtitle of host publication	16th International Conference, Athens, Greece, September 10-14, 2006. Proceedings, Part 1
Editors	Stefanos D. Kollias, Andreas Stafylopatis, Włodzisław Duch, Erkki Oja
Place of Publication	Berlin
Publisher	Springer Verlag
Pages	592-601
Number of pages	10
ISBN (Electronic)	978-3-540-38627-8
ISBN (Print)	978-3-540-38625-4
DOIs	https://doi.org/10.1007/11840817_62
Publication status	Published - 2006
Externally published	Yes
Event	16th International Conference on Artificial Neural Networks - Athens, Greece Duration: 10 Sept 2006 → 14 Sept 2006 Conference number: 16

Publication series

Name	Lecture Notes in Computer Science
Volume	4131

Conference

Conference	16th International Conference on Artificial Neural Networks
Abbreviated title	ICANN 2006
Country/Territory	Greece
City	Athens
Period	10/09/06 → 14/09/06

Access to Document

10.1007/11840817_62

Cite this

Taylor, N., Panchev, C., Hartley, M., Kasderidis, S., & Taylor, J. G. (2006). Occlusion, Attention and Object Representations. In S. D. Kollias, A. Stafylopatis, W. Duch, & E. Oja (Eds.), Artificial Neural Networks – ICANN 2006: 16th International Conference, Athens, Greece, September 10-14, 2006. Proceedings, Part 1 (pp. 592-601). ( Lecture Notes in Computer Science ; Vol. 4131). Springer Verlag. https://doi.org/10.1007/11840817_62

Occlusion, Attention and Object Representations. / Taylor, Neil; Panchev, Christo; Hartley, Mathew et al.
Artificial Neural Networks – ICANN 2006: 16th International Conference, Athens, Greece, September 10-14, 2006. Proceedings, Part 1. ed. / Stefanos D. Kollias; Andreas Stafylopatis; Włodzisław Duch; Erkki Oja. Berlin: Springer Verlag, 2006. p. 592-601 ( Lecture Notes in Computer Science ; Vol. 4131).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Taylor, N, Panchev, C, Hartley, M, Kasderidis, S & Taylor, JG 2006, Occlusion, Attention and Object Representations. in SD Kollias, A Stafylopatis, W Duch & E Oja (eds), Artificial Neural Networks – ICANN 2006: 16th International Conference, Athens, Greece, September 10-14, 2006. Proceedings, Part 1. Lecture Notes in Computer Science , vol. 4131, Springer Verlag, Berlin, pp. 592-601, 16th International Conference on Artificial Neural Networks, Athens, Greece, 10/09/06. https://doi.org/10.1007/11840817_62

Taylor N, Panchev C, Hartley M, Kasderidis S, Taylor JG. Occlusion, Attention and Object Representations. In Kollias SD, Stafylopatis A, Duch W, Oja E, editors, Artificial Neural Networks – ICANN 2006: 16th International Conference, Athens, Greece, September 10-14, 2006. Proceedings, Part 1. Berlin: Springer Verlag. 2006. p. 592-601. ( Lecture Notes in Computer Science ). doi: 10.1007/11840817_62

Taylor, Neil ; Panchev, Christo ; Hartley, Mathew et al. / Occlusion, Attention and Object Representations. Artificial Neural Networks – ICANN 2006: 16th International Conference, Athens, Greece, September 10-14, 2006. Proceedings, Part 1. editor / Stefanos D. Kollias ; Andreas Stafylopatis ; Włodzisław Duch ; Erkki Oja. Berlin : Springer Verlag, 2006. pp. 592-601 ( Lecture Notes in Computer Science ).

@inproceedings{a89624dab3f949bb9b453d645e58de46,

title = "Occlusion, Attention and Object Representations",

abstract = "Occlusion is currently at the centre of analysis in machine vision. We present an approach to it that uses attention feedback to an occluded object to obtain its correct recognition. Various simulations are performed using a hierarchical visual attention feedback system, based on contrast gain (which we discuss as to its relation to possible hallucinations that could be caused by feedback). We then discuss implications of our results for object representations per se.",

author = "Neil Taylor and Christo Panchev and Mathew Hartley and Statis Kasderidis and Taylor, {John G.}",

year = "2006",

doi = "10.1007/11840817_62",

language = "English",

isbn = "978-3-540-38625-4",

series = " Lecture Notes in Computer Science ",

publisher = "Springer Verlag",

pages = "592--601",

editor = "Kollias, {Stefanos D. } and Stafylopatis, {Andreas } and Duch, {W{\l}odzis{\l}aw } and Oja, {Erkki }",

booktitle = "Artificial Neural Networks – ICANN 2006",

address = "Austria",

note = "16th International Conference on Artificial Neural Networks, ICANN 2006 ; Conference date: 10-09-2006 Through 14-09-2006",

}

TY - GEN

T1 - Occlusion, Attention and Object Representations

AU - Taylor, Neil

AU - Panchev, Christo

AU - Hartley, Mathew

AU - Kasderidis, Statis

AU - Taylor, John G.

N1 - Conference code: 16

PY - 2006

Y1 - 2006

N2 - Occlusion is currently at the centre of analysis in machine vision. We present an approach to it that uses attention feedback to an occluded object to obtain its correct recognition. Various simulations are performed using a hierarchical visual attention feedback system, based on contrast gain (which we discuss as to its relation to possible hallucinations that could be caused by feedback). We then discuss implications of our results for object representations per se.

AB - Occlusion is currently at the centre of analysis in machine vision. We present an approach to it that uses attention feedback to an occluded object to obtain its correct recognition. Various simulations are performed using a hierarchical visual attention feedback system, based on contrast gain (which we discuss as to its relation to possible hallucinations that could be caused by feedback). We then discuss implications of our results for object representations per se.

U2 - 10.1007/11840817_62

DO - 10.1007/11840817_62

M3 - Conference proceeding

SN - 978-3-540-38625-4

T3 - Lecture Notes in Computer Science

SP - 592

EP - 601

BT - Artificial Neural Networks – ICANN 2006

A2 - Kollias, Stefanos D.

A2 - Stafylopatis, Andreas

A2 - Duch, Włodzisław

A2 - Oja, Erkki

PB - Springer Verlag

CY - Berlin

T2 - 16th International Conference on Artificial Neural Networks

Y2 - 10 September 2006 through 14 September 2006

ER -

Occlusion, Attention and Object Representations

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this