DiffAds: An Interactive Platform for Personalized Visual Advertisement Generation

Ling Lo, Yi Yao, Hsiu Hua Chou, Rou An Chen, Yu Hsuan Huang, Chien Chih Chiu, Wan Hsin Hsueh, Shih Chieh Huang, Hong Han Shuai, Wen Huang Cheng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Deep understanding of the customer journey followed with the provision of dynamic personalization has been considered to be one of the most effective digital marketing strategies. In this demonstration, based on text-to-image diffusion models, we present DiffAds, an interactive platform for personalized visual advertisement generation. To simulate the process of personalized advertising in digital marketing channels, DiffAds consists of three main stages including style preference discovery, personalized advertising image generation, and user feedback collection. The first stage presents representative images of different visual styles for the user to choose from and the second stage creates the advertising images of a commercial product tailored to user preference. Finally, the third stage allows the user to explicitly rank the generated images as the preference feedback for updating the generative models. The advertising technique behind DiffAds has been practiced in real advertising campaigns of FamilyMart Taiwan (Taiwan's major convenience store chain).

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages514-515
Number of pages2
ISBN (Electronic)9798350313154
DOIs
StatePublished - 2023
Event2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023 - Brisbane, Australia
Duration: 10 Jul 202314 Jul 2023

Publication series

NameProceedings - 2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023

Conference

Conference2023 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2023
Country/TerritoryAustralia
CityBrisbane
Period10/07/2314/07/23

Keywords

  • diffusion models
  • image generation
  • Personalized visual advertisement

Fingerprint

Dive into the research topics of 'DiffAds: An Interactive Platform for Personalized Visual Advertisement Generation'. Together they form a unique fingerprint.

Cite this