Show simple item record

dc.contributor.authorWu, Baoyuan
dc.contributor.authorChen, Weidong
dc.contributor.authorSun, Peng
dc.contributor.authorLiu, Wei
dc.contributor.authorGhanem, Bernard
dc.contributor.authorLyu, Siwei
dc.identifier.citationWu, B., Chen, W., Sun, P., Liu, W., Ghanem, B., & Lyu, S. (2018). Tagging Like Humans: Diverse and Distinct Image Annotation. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. doi:10.1109/cvpr.2018.00831
dc.description.abstractIn this work we propose a new automatic image annotation model, dubbed diverse and distinct image annotation (D2IA). The generative model D2IA is inspired by the ensemble of human annotations, which create semantically relevant, yet distinct and diverse tags. In D2IA, we generate a relevant and distinct tag subset, in which the tags are relevant to the image contents and semantically distinct to each other, using sequential sampling from a determinantal point process (DPP) model. Multiple such tag subsets that cover diverse semantic aspects or diverse semantic levels of the image contents are generated by randomly perturbing the DPP sampling process. We leverage a generative adversarial network (GAN) model to train D2IA. Extensive experiments including quantitative and qualitative comparisons, as well as human subject studies, on two benchmark datasets demonstrate that the proposed model can produce more diverse and distinct tags than the state-of-the-arts.
dc.description.sponsorshipThis work is supported by Tencent AI Lab. The participation of Bernard Ghanem is supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research. The participation of Siwei Lyu is partially supported by National Science Foundation National Robotics Initiative (NRI) Grant (IIS-1537257) and National Science Foundation of China Project Number 61771341.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.rightsArchived with thanks to 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
dc.titleTagging Like Humans: Diverse and Distinct Image Annotation
dc.typeConference Paper
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.conference.date2018-06-18 to 2018-06-22
dc.conference.name31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
dc.conference.locationSalt Lake City, UT, USA
dc.contributor.institutionTencent AI Lab, United States
dc.contributor.institutionUniversity at Albany, SUNY, United States
kaust.personGhanem, Bernard
kaust.acknowledged.supportUnitOffice of Sponsored Research

Files in this item

Tagging-Like-Humans-CVPR2018 (1).pdf
Accepted manuscript

This item appears in the following Collection(s)

Show simple item record


*Selected version