Please use this identifier to cite or link to this item:
Title: Beyond ranking loss : deep holographic networks for multi-label video search
Authors: Chen, Zhuo
Lin, Jie
Wang, Zhe
Chandrasekhar, Vijay
Lin, Weisi
Keywords: Engineering::Computer science and engineering
Issue Date: 2019
Source: Chen, Z., Lin, J., Wang, Z., Chandrasekhar, V., & Lin, W. (2019). Beyond ranking loss : deep holographic networks for multi-label video search. 2019 IEEE International Conference on Image Processing (ICIP), 879-883. doi:10.1109/ICIP.2019.8802944
Abstract: In this paper, we propose Deep Holographic Networks (DHN) to learn similarity metrics of videos for multi-label video search. DHN introduces a holographic composition layer to explicitly encode similarity metrics at intermediate layer of the network, instead of conventional deep metric learning approaches driven by ranking losses. The holographic composition layer is parameter-free and enables less memory footprint compared with state-of-the-art. Towards multi-label video search at large scale, we present a new video benchmark built upon the YouTube-8M dataset. Extensive evaluations on this dataset demonstrate that DHN performs better than traditional deep metric learning approaches as well as other compositional networks.
ISBN: 978-1-5386-6249-6
DOI: 10.1109/ICIP.2019.8802944
Rights: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, 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 component of this work in other works. The published version is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
2439_camera_ready.pdf367.58 kBAdobe PDFView/Open

Page view(s)

Updated on Jan 26, 2021


Updated on Jan 26, 2021

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.