TY - GEN
T1 - Interpretable partitioned embedding for customized multi-item fashion outfit composition
AU - Feng, Zunlei
AU - Yu, Zhenyun
AU - Yang, Yezhou
AU - Jing, Yongcheng
AU - Jiang, Junxiao
AU - Song, Mingli
N1 - Funding Information:
This work is supported by National Key Research and Development Program (2016YFB1200203), National Natural Science Foundation of China (61572428,U1509206), Fundamental Research Funds for the Central Universities (2017FZA5014) and Key Research and Development Program of Zhejiang Province (2018C01004).
Publisher Copyright:
© 2018 ACM.
PY - 2018/6/5
Y1 - 2018/6/5
N2 - Intelligent fashion outfit composition becomes more and more popular in these years. Some deep learning based approaches reveal competitive composition recently. However, the uninterpretable characteristic makes such deep learning based approach cannot meet the designers, businesses and consumers' urge to comprehend the importance of different attributes in an outfit composition. To realize interpretable and customized multi-item fashion outfit compositions, we propose a partitioned embedding network to learn interpretable embeddings from clothing items. The network consists of 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 which corresponding to different attributes and 2) outfits recommended by our model are more desirable in comparison with the existing methods.
AB - Intelligent fashion outfit composition becomes more and more popular in these years. Some deep learning based approaches reveal competitive composition recently. However, the uninterpretable characteristic makes such deep learning based approach cannot meet the designers, businesses and consumers' urge to comprehend the importance of different attributes in an outfit composition. To realize interpretable and customized multi-item fashion outfit compositions, we propose a partitioned embedding network to learn interpretable embeddings from clothing items. The network consists of 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 which corresponding 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=85053923132&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85053923132&partnerID=8YFLogxK
U2 - 10.1145/3206025.3206048
DO - 10.1145/3206025.3206048
M3 - Conference contribution
AN - SCOPUS:85053923132
SN - 9781450350464
T3 - ICMR 2018 - Proceedings of the 2018 ACM International Conference on Multimedia Retrieval
SP - 143
EP - 151
BT - ICMR 2018 - Proceedings of the 2018 ACM International Conference on Multimedia Retrieval
PB - Association for Computing Machinery, Inc
T2 - 8th ACM International Conference on Multimedia Retrieval, ICMR 2018
Y2 - 11 June 2018 through 14 June 2018
ER -