Occlusion, attention and object representations

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

doi:10.3233/ICA-2007-14402

Occlusion, attention and object representations

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

King's College London
University of Sunderland
Institute of Computer Science - FORTH

Research output: Contribution to journal › Article › 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
Pages (from-to)	283-306
Number of pages	10
Journal	Integrated Computer-Aided Engineering
Volume	14
Issue number	4
DOIs	https://doi.org/10.3233/ICA-2007-14402
Publication status	Published - 19 Jul 2007
Externally published	Yes

Access to Document

10.3233/ICA-2007-14402

Cite this

@article{e15fc1823cdb41b2a3b228019626ce77,

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 = "2007",

month = jul,

day = "19",

doi = "10.3233/ICA-2007-14402",

language = "English",

volume = "14",

pages = "283--306",

journal = "Integrated Computer-Aided Engineering",

issn = "1069-2509",

publisher = "SAGE Publications",

number = "4",

}

TY - JOUR

T1 - Occlusion, attention and object representations

AU - Taylor, Neil

AU - Panchev, Christo

AU - Hartley, Mathew

AU - Kasderidis, Statis

AU - Taylor, John G.

PY - 2007/7/19

Y1 - 2007/7/19

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 - 10.3233/ICA-2007-14402

DO - 10.3233/ICA-2007-14402

M3 - Article

SN - 1069-2509

VL - 14

SP - 283

EP - 306

JO - Integrated Computer-Aided Engineering

JF - Integrated Computer-Aided Engineering

IS - 4

ER -

Occlusion, attention and object representations

Abstract

Access to Document

Fingerprint

Cite this