Interpretable partitioned embedding for intelligent multi-item fashion outfit composition

Zunlei Feng, Zhenyun Yu, Yongcheng Jing, Sai Wu, Mingli Song, Yezhou Yang, Junxiao Jiang

Research output: Contribution to journalArticle

Abstract

Intelligent fashion outfit composition has become more popular in recent years. Some deep-learning-based approaches reveal competitive composition. However, the uninterpretable characteristic makes such a deep-learning-based approach fail to meet the businesses', designers', and consumers' urges to comprehend the importance of different attributes in an outfit composition. To realize interpretable and intelligent multi-item fashion outfit compositions, we propose a partitioned embedding network to learn interpretable embeddings from clothing items. The network contains two vital components: attribute partition module and partition adversarial module. In the attribute partition module, multiple attribute labels are adopted to ensure that different parts of the overall embedding correspond to different attributes. In the partition adversarial module, adversarial operations are adopted to achieve the independence of different parts. With the interpretable and partitioned embedding, we then construct an outfit-composition graph and an attribute matching map. Extensive experiments demonstrate that (1) the partitioned embedding have unmingled parts that correspond to different attributes and (2) outfits recommended by our model are more desirable in comparison with the existing methods.

Original languageEnglish (US)
Article number61
JournalACM Transactions on Multimedia Computing, Communications and Applications
Volume15
Issue number2s
DOIs
StatePublished - Aug 2019

Fingerprint

Chemical analysis
Labels
Industry
Experiments
Deep learning

Keywords

  • Adversarial
  • Embedding
  • Interpretable
  • Outfit composition

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Interpretable partitioned embedding for intelligent multi-item fashion outfit composition. / Feng, Zunlei; Yu, Zhenyun; Jing, Yongcheng; Wu, Sai; Song, Mingli; Yang, Yezhou; Jiang, Junxiao.

In: ACM Transactions on Multimedia Computing, Communications and Applications, Vol. 15, No. 2s, 61, 08.2019.

Research output: Contribution to journalArticle

Feng, Zunlei ; Yu, Zhenyun ; Jing, Yongcheng ; Wu, Sai ; Song, Mingli ; Yang, Yezhou ; Jiang, Junxiao. / Interpretable partitioned embedding for intelligent multi-item fashion outfit composition. In: ACM Transactions on Multimedia Computing, Communications and Applications. 2019 ; Vol. 15, No. 2s.
@article{01bd33f9e07c473ea442cacce2a24e84,
title = "Interpretable partitioned embedding for intelligent multi-item fashion outfit composition",
abstract = "Intelligent fashion outfit composition has become more popular in recent years. Some deep-learning-based approaches reveal competitive composition. However, the uninterpretable characteristic makes such a deep-learning-based approach fail to meet the businesses', designers', and consumers' urges to comprehend the importance of different attributes in an outfit composition. To realize interpretable and intelligent multi-item fashion outfit compositions, we propose a partitioned embedding network to learn interpretable embeddings from clothing items. The network contains two vital components: attribute partition module and partition adversarial module. In the attribute partition module, multiple attribute labels are adopted to ensure that different parts of the overall embedding correspond to different attributes. In the partition adversarial module, adversarial operations are adopted to achieve the independence of different parts. With the interpretable and partitioned embedding, we then construct an outfit-composition graph and an attribute matching map. Extensive experiments demonstrate that (1) the partitioned embedding have unmingled parts that correspond to different attributes and (2) outfits recommended by our model are more desirable in comparison with the existing methods.",
keywords = "Adversarial, Embedding, Interpretable, Outfit composition",
author = "Zunlei Feng and Zhenyun Yu and Yongcheng Jing and Sai Wu and Mingli Song and Yezhou Yang and Junxiao Jiang",
year = "2019",
month = "8",
doi = "10.1145/3326332",
language = "English (US)",
volume = "15",
journal = "ACM Transactions on Multimedia Computing, Communications and Applications",
issn = "1551-6857",
publisher = "Association for Computing Machinery (ACM)",
number = "2s",

}

TY - JOUR

T1 - Interpretable partitioned embedding for intelligent multi-item fashion outfit composition

AU - Feng, Zunlei

AU - Yu, Zhenyun

AU - Jing, Yongcheng

AU - Wu, Sai

AU - Song, Mingli

AU - Yang, Yezhou

AU - Jiang, Junxiao

PY - 2019/8

Y1 - 2019/8

N2 - Intelligent fashion outfit composition has become more popular in recent years. Some deep-learning-based approaches reveal competitive composition. However, the uninterpretable characteristic makes such a deep-learning-based approach fail to meet the businesses', designers', and consumers' urges to comprehend the importance of different attributes in an outfit composition. To realize interpretable and intelligent multi-item fashion outfit compositions, we propose a partitioned embedding network to learn interpretable embeddings from clothing items. The network contains two vital components: attribute partition module and partition adversarial module. In the attribute partition module, multiple attribute labels are adopted to ensure that different parts of the overall embedding correspond to different attributes. In the partition adversarial module, adversarial operations are adopted to achieve the independence of different parts. With the interpretable and partitioned embedding, we then construct an outfit-composition graph and an attribute matching map. Extensive experiments demonstrate that (1) the partitioned embedding have unmingled parts that correspond to different attributes and (2) outfits recommended by our model are more desirable in comparison with the existing methods.

AB - Intelligent fashion outfit composition has become more popular in recent years. Some deep-learning-based approaches reveal competitive composition. However, the uninterpretable characteristic makes such a deep-learning-based approach fail to meet the businesses', designers', and consumers' urges to comprehend the importance of different attributes in an outfit composition. To realize interpretable and intelligent multi-item fashion outfit compositions, we propose a partitioned embedding network to learn interpretable embeddings from clothing items. The network contains two vital components: attribute partition module and partition adversarial module. In the attribute partition module, multiple attribute labels are adopted to ensure that different parts of the overall embedding correspond to different attributes. In the partition adversarial module, adversarial operations are adopted to achieve the independence of different parts. With the interpretable and partitioned embedding, we then construct an outfit-composition graph and an attribute matching map. Extensive experiments demonstrate that (1) the partitioned embedding have unmingled parts that correspond to different attributes and (2) outfits recommended by our model are more desirable in comparison with the existing methods.

KW - Adversarial

KW - Embedding

KW - Interpretable

KW - Outfit composition

UR - http://www.scopus.com/inward/record.url?scp=85071081381&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071081381&partnerID=8YFLogxK

U2 - 10.1145/3326332

DO - 10.1145/3326332

M3 - Article

AN - SCOPUS:85071081381

VL - 15

JO - ACM Transactions on Multimedia Computing, Communications and Applications

JF - ACM Transactions on Multimedia Computing, Communications and Applications

SN - 1551-6857

IS - 2s

M1 - 61

ER -