Bottom-Up Attention Guidance for Recurrent Image Recognition

Hamed Rezazadegan Tavakoli, Ali Borji, Rao Anwer, Esa Rahtu, Juho Kannala

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

2 Citations (Scopus)

Abstract

This paper presents a recurrent neural network architecture, guided by the bottom-up attention, for the recognition task. The proposed architecture processes an input image as a sequence of selectively chosen patches. The patches are chosen from the salient regions of the input image. Using human driven saliency maps from gaze, the benefit of such a selection process is first shown. Next, the performance of computational models of bottom-up attention are assessed as alternative to human attention.
Original languageEnglish
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE
Pages3004-3008
Number of pages5
ISBN (Electronic)9781479970612
DOIs
Publication statusPublished - 2018
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Image Processing - Athens, Greece
Duration: 7 Oct 201810 Oct 2018
Conference number: 25

Conference

ConferenceIEEE International Conference on Image Processing
Abbreviated titleICIP
Country/TerritoryGreece
CityAthens
Period07/10/201810/10/2018

Keywords

  • Recurrent neural networks
  • deep neural networks
  • gaze
  • saliency
  • image recognition

Fingerprint

Dive into the research topics of 'Bottom-Up Attention Guidance for Recurrent Image Recognition'. Together they form a unique fingerprint.

Cite this