Bottom-up Fixation Prediction Using Unsupervised Hierarchical Models

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

22 Sitaatiot (Scopus)

Abstrakti

Fixation prediction, also known as saliency modelling, has been a subject undergoing intense study in various contexts. In the context of assistive vision technologies, saliency modelling can be used for development of simulated prosthetic vision as part of the saliency-based cueing algorithms. In this paper, we present an unsupervised multi-scale hierarchical saliency model, which utilizes both local and global saliency pipelines. Motivated by bio-inspired vision findings, we employ features from image statistics. Contrary to previous research, which utilizes one-layer equivalent networks such as independent component analysis (ICA) or principle component analysis (PCA), we adopt independent subspace analysis (ISA), which is equivalent to a two-layer neural architecture. The advantage of ISA over ICA and PCA is robustness towards translation meanwhile being selective to frequency and rotation. We extended the ISA networks by stacking them together, as done in deep models, in order to obtain a hierarchical representation. Making a long story short, (1) we define a framework for unsupervised fixation prediction, exploiting local and global saliency concept which easily generalizes to a hierarchy of any depth. (2) we assess the usefulness of the hierarchical unsupervised features, (3) we adapt the framework for exploiting the features provided by pre-trained deep neural networks, (4) we compare the performance of different features and existing fixation prediction models on MIT1003, (5) we provide the benchmark results of our model on MIT300.
AlkuperäiskieliEnglanti
OtsikkoComputer Vision – ACCV 2016 Workshops
AlaotsikkoACCV 2016 International Workshops, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part I
ToimittajatChu-Song Chen, Lu Jiwen, Kai-Kuang Ma
Sivut287–302
Sivumäärä16
ISBN (elektroninen)978-3-319-54407-6
DOI - pysyväislinkit
TilaJulkaistu - 2016
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaAsian Conference on Computer Vision - Taipei, Taiwan
Kesto: 20 marraskuuta 201624 marraskuuta 2016
Konferenssinumero: 13

Julkaisusarja

NimiLecture Notes in Computer Science
KustantajaSpringer
Vuosikerta10116
ISSN (painettu)0302-9743

Conference

ConferenceAsian Conference on Computer Vision
LyhennettäACCV
MaaTaiwan
KaupunkiTaipei
Ajanjakso20/11/201624/11/2016

Sormenjälki Sukella tutkimusaiheisiin 'Bottom-up Fixation Prediction Using Unsupervised Hierarchical Models'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

  • Projektit

    • 1 Päättynyt

    Suomalainen laskennallisen päättelyn huippuyksikkö

    Xu, Y., Rezazadegan Tavakoli, H., Pesonen, H., Puranen, S., Rintanen, J., Kaski, S., Anwer, R., Parviainen, P., Soare, M., Weinzierl, A. & Vuollekoski, H.

    01/01/201528/02/2018

    Projekti: Academy of Finland: Other research funding

    Laitteet

    Science-IT

    Mikko Hakala (Manager)

    Perustieteiden korkeakoulu

    Laitteistot/tilat: Facility

  • Siteeraa tätä

    Rezazadegan Tavakoli, H., & Laaksonen, J. (2016). Bottom-up Fixation Prediction Using Unsupervised Hierarchical Models. teoksessa C-S. Chen, L. Jiwen, & K-K. Ma (Toimittajat), Computer Vision – ACCV 2016 Workshops: ACCV 2016 International Workshops, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part I (Sivut 287–302). (Lecture Notes in Computer Science; Vuosikerta 10116). https://doi.org/10.1007/978-3-319-54407-6_19