Diverse Image Annotation

Handle URI:
http://hdl.handle.net/10754/626228
Title:
Diverse Image Annotation
Authors:
Wu, Baoyuan ( 0000-0003-2183-5990 ) ; Jia, Fan; Liu, Wei; Ghanem, Bernard ( 0000-0002-5534-587X )
Abstract:
In this work we study the task of image annotation, of which the goal is to describe an image using a few tags. Instead of predicting the full list of tags, here we target for providing a short list of tags under a limited number (e.g., 3), to cover as much information as possible of the image. The tags in such a short list should be representative and diverse. It means they are required to be not only corresponding to the contents of the image, but also be different to each other. To this end, we treat the image annotation as a subset selection problem based on the conditional determinantal point process (DPP) model, which formulates the representation and diversity jointly. We further explore the semantic hierarchy and synonyms among the candidate tags, and require that two tags in a semantic hierarchy or in a pair of synonyms should not be selected simultaneously. This requirement is then embedded into the sampling algorithm according to the learned conditional DPP model. Besides, we find that traditional metrics for image annotation (e.g., precision, recall and F1 score) only consider the representation, but ignore the diversity. Thus we propose new metrics to evaluate the quality of the selected subset (i.e., the tag list), based on the semantic hierarchy and synonyms. Human study through Amazon Mechanical Turk verifies that the proposed metrics are more close to the humans judgment than traditional metrics. Experiments on two benchmark datasets show that the proposed method can produce more representative and diverse tags, compared with existing image annotation methods.
KAUST Department:
Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program
Citation:
Wu B, Jia F, Liu W, Ghanem B (2017) Diverse Image Annotation. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/cvpr.2017.656.
Publisher:
IEEE
Journal:
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Issue Date:
9-Nov-2017
DOI:
10.1109/cvpr.2017.656
Type:
Conference Paper
Sponsors:
This work is supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research. Baoyuan Wu is partially supported by Tencent AI Lab. We thank Fabian Caba for his help in conducting the online subject studies.
Additional Links:
http://ieeexplore.ieee.org/document/8100139/
Appears in Collections:
Conference Papers; Electrical Engineering Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorWu, Baoyuanen
dc.contributor.authorJia, Fanen
dc.contributor.authorLiu, Weien
dc.contributor.authorGhanem, Bernarden
dc.date.accessioned2017-11-29T11:13:55Z-
dc.date.available2017-11-29T11:13:55Z-
dc.date.issued2017-11-09en
dc.identifier.citationWu B, Jia F, Liu W, Ghanem B (2017) Diverse Image Annotation. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/cvpr.2017.656.en
dc.identifier.doi10.1109/cvpr.2017.656en
dc.identifier.urihttp://hdl.handle.net/10754/626228-
dc.description.abstractIn this work we study the task of image annotation, of which the goal is to describe an image using a few tags. Instead of predicting the full list of tags, here we target for providing a short list of tags under a limited number (e.g., 3), to cover as much information as possible of the image. The tags in such a short list should be representative and diverse. It means they are required to be not only corresponding to the contents of the image, but also be different to each other. To this end, we treat the image annotation as a subset selection problem based on the conditional determinantal point process (DPP) model, which formulates the representation and diversity jointly. We further explore the semantic hierarchy and synonyms among the candidate tags, and require that two tags in a semantic hierarchy or in a pair of synonyms should not be selected simultaneously. This requirement is then embedded into the sampling algorithm according to the learned conditional DPP model. Besides, we find that traditional metrics for image annotation (e.g., precision, recall and F1 score) only consider the representation, but ignore the diversity. Thus we propose new metrics to evaluate the quality of the selected subset (i.e., the tag list), based on the semantic hierarchy and synonyms. Human study through Amazon Mechanical Turk verifies that the proposed metrics are more close to the humans judgment than traditional metrics. Experiments on two benchmark datasets show that the proposed method can produce more representative and diverse tags, compared with existing image annotation methods.en
dc.description.sponsorshipThis work is supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research. Baoyuan Wu is partially supported by Tencent AI Lab. We thank Fabian Caba for his help in conducting the online subject studies.en
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/document/8100139/en
dc.rights(c) 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.en
dc.titleDiverse Image Annotationen
dc.typeConference Paperen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentElectrical Engineering Programen
dc.identifier.journal2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)en
dc.eprint.versionPost-printen
dc.contributor.institutionTencent AI Lab, Shenzhen, Chinaen
kaust.authorWu, Baoyuanen
kaust.authorJia, Fanen
kaust.authorGhanem, Bernarden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.