Skip navigation
Please use this identifier to cite or link to this item:
Title: User Constrained Thumbnail Generation Using Adaptive Convolutions
Authors: Raj Kishore P.S.
Kumar Bhunia A.
Ghose S.
Pratim Roy, Partha
Published in: Proceedings of ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
Abstract: Thumbnails 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.
Citation: Proceedings of ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, (2019), 1677- 1681
Issue Date: 2019
Publisher: Institute of Electrical and Electronics Engineers Inc.
Keywords: Adaptive Convolution
aspect ratio
Global Context Aggregation
Region Proposal Network
Thumbnail generation
ISBN: 9.78148E+12
ISSN: 15206149
Author Scopus IDs: 57210110735
Author Affiliations: Raj Kishore, P.S., Institute of Engineering Management, India
Kumar Bhunia, A., Nanyang Technological University, Singapore, Singapore
Ghose, S., Institute of Engineering Management, India
Roy, P.P., Indian Institute of Technology Roorkee, India
Corresponding Author: Kumar Bhunia, A.; Nanyang Technological UniversitySingapore; email:
Appears in Collections:Conference Publications [CS]

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

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