Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/15971
Full metadata record
DC FieldValueLanguage
dc.contributor.authorRaj Kishore P.S.-
dc.contributor.authorKumar Bhunia A.-
dc.contributor.authorGhose S.-
dc.contributor.authorPratim Roy, Partha-
dc.date.accessioned2020-12-02T11:42:08Z-
dc.date.available2020-12-02T11:42:08Z-
dc.date.issued2019-
dc.identifier.citationProceedings of ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, (2019), 1677- 1681-
dc.identifier.isbn9.78148E+12-
dc.identifier.issn15206149-
dc.identifier.urihttps://doi.org/10.1109/ICASSP.2019.8683761-
dc.identifier.urihttp://repository.iitr.ac.in/handle/123456789/15971-
dc.description.abstractThumbnails are widely used all over the world as a preview for digital images. In this work we propose a deep neural framework to generate thumbnails of any size and aspect ratio, even for unseen values during training, with high accuracy and precision. We use Global Context Aggregation (GCA) and a modified Region Proposal Network (RPN) with adaptive convolutions to generate thumbnails in real time. GCA is used to selectively attend and aggregate the global context information from the entire image while the RPN is used to generate candidate bounding boxes for the thumbnail image. Adaptive convolution eliminates the difficulty of generating thumbnails of various aspect ratios by using filter weights dynamically generated from the aspect ratio information. The experimental results indicate the superior performance of the proposed model1 over existing state-of-the-art techniques. © 2019 IEEE.-
dc.description.sponsorshipThe Institute of Electrical and Electronics Engineers Signal Processing Society-
dc.language.isoen_US-
dc.publisherInstitute of Electrical and Electronics Engineers Inc.-
dc.relation.ispartofProceedings of ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing-
dc.subjectAdaptive Convolution-
dc.subjectaspect ratio-
dc.subjectGlobal Context Aggregation-
dc.subjectRegion Proposal Network-
dc.subjectThumbnail generation-
dc.titleUser Constrained Thumbnail Generation Using Adaptive Convolutions-
dc.typeConference Paper-
dc.scopusid57210110735-
dc.scopusid57210105939-
dc.scopusid57209826260-
dc.scopusid56880478500-
dc.affiliationRaj Kishore, P.S., Institute of Engineering Management, India-
dc.affiliationKumar Bhunia, A., Nanyang Technological University, Singapore, Singapore-
dc.affiliationGhose, S., Institute of Engineering Management, India-
dc.affiliationRoy, P.P., Indian Institute of Technology Roorkee, India-
dc.description.correspondingauthorKumar Bhunia, A.; Nanyang Technological UniversitySingapore; email: ayanbhunia@ntu.edu.sg-
dc.identifier.conferencedetails44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, 12-17 May 2019-
Appears in Collections:Conference Publications [CS]

Files in This Item:
There are no files associated with this item.
Show simple item record


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.