Fixation Prediction in Videos using Unsupervised Hierarchical Features

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

5 Sitaatiot (Scopus)

Abstrakti

This paper presents a framework for saliency estimation and fixation prediction in videos. The proposed framework is based on a hierarchical feature representation obtained by stacking convolutional layers of independent subspace analysis (ISA) filters. The feature learning is thus unsupervised and independent of the task. To compute the saliency, we then employ a multiresolution saliency architecture that exploits both local and global saliency. That is, for a given image, an image pyramid is initially built. After that, for each resolution, both local and global saliency measures are computed to obtain a saliency map. The integration of saliency maps over the image pyramid provides the final video saliency. We first show that combining local and global saliency improves the results. We then compare the proposed model with several video saliency models and demonstrate that the proposed framework is capable of predicting video saliency effectively, outperforming all the other models.
AlkuperäiskieliEnglanti
OtsikkoProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
KustantajaIEEE
Sivut2225-2232
Sivumäärä8
ISBN (elektroninen)9781538607336
DOI - pysyväislinkit
TilaJulkaistu - 22 elokuuta 2017
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE Conference on Computer Vision and Pattern Recognition - Hawaii Convention Center, Honolulu, Yhdysvallat
Kesto: 21 heinäkuuta 201726 heinäkuuta 2017
Konferenssinumero: 30

Julkaisusarja

NimiIEEE Computer Society Conference on Computer Vision and Pattern Recognition workshops
KustantajaIEEE
ISSN (elektroninen)2160-7516

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition
LyhennettäCVPR
MaaYhdysvallat
KaupunkiHonolulu
Ajanjakso21/07/201726/07/2017

Siteeraa tätä