Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/151862
Title: COMPUTATIONAL MULTIMEDIA ADVERTISEMENT
Authors: CHEN XIANG
Keywords: online advertising, real-time bidding, live streaming advertising, contextual relevance, multimedia, optimization
Issue Date: 24-Aug-2018
Citation: CHEN XIANG (2018-08-24). COMPUTATIONAL MULTIMEDIA ADVERTISEMENT. ScholarBank@NUS Repository.
Abstract: This thesis proposes to incorporate multimedia techniques to increase the effectiveness of existing online advertising strategies. First, we propose a novel multimodal framework which considers contextual relevance, visual saliency and image memorability, to select suitable ads for online videos. Second, we propose a two-stage framework which considers all stakeholders’ benefits in the ad selection. We introduce six metric variables to represent the stakeholders’ benefits, and design an algorithm to achieve the optimal trade-offs among all stakeholders in real-time bidding. Third, we describe a new research problem that brings online advertising to live streaming platforms. We propose a novel deep neural network model to determine the optimal timestamp to display an ad, and design an interactive strategy to display the ad in a non-intrusive manner. Extensive experiments on real-world datasets suggest that integrating multimedia techniques can improve existing adverting services.
URI: http://scholarbank.nus.edu.sg/handle/10635/151862
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
ChenX.pdf8.03 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

36
checked on Apr 21, 2019

Download(s)

13
checked on Apr 21, 2019

Google ScholarTM

Check


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