Skip to main navigation Skip to search Skip to main content

Supervised Disentangled Graph Learning for OCM

  • Monash University
  • Shandong University
  • University of Technology Sydney
  • Harbin Institute of Technology Shenzhen

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

In Chap. 4, we studied the fine-grained outfit compatibility modeling, where the hidden factors affecting the outfit compatibility are jointly considered. One key limitation is that it only investigates the visual content of fashion items while overlooking the items’ semantic attributes. The item attribute labels usually contain rich information that characterizes the key item parts, which can be adopted to supervise the attribute-level representation learning, and hence promote the model’s performance as well as interpretability. Thus, in this chapter, we aim to fulfill the fine-grained outfit compatibility modeling by incorporating the semantic attributes of fashion items.

Original languageEnglish
Title of host publicationSynthesis Lectures on Information Concepts, Retrieval, and Services
PublisherSpringer Nature
Pages67-87
Number of pages21
DOIs
StatePublished - 2022
Externally publishedYes

Publication series

NameSynthesis Lectures on Information Concepts, Retrieval, and Services
ISSN (Print)1947-945X
ISSN (Electronic)1947-9468

Fingerprint

Dive into the research topics of 'Supervised Disentangled Graph Learning for OCM'. Together they form a unique fingerprint.

Cite this