Visual and Textual Jointly Enhanced Interpretable Fashion Recommendation

With the rapid development of online shopping, interpretable personalized fashion recommendation using image has attracted increasing attention in recent years. The current work has been able to capture the user's preferences for visible features and provide visual explanations. However, they i...

Full description

Bibliographic Details
Main Authors: Qianqian Wu, Pengpeng Zhao, Zhiming Cui
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9046774/
id doaj-43d087d115494489b033a573ac626787
record_format Article
spelling doaj-43d087d115494489b033a573ac6267872021-03-30T01:46:54ZengIEEEIEEE Access2169-35362020-01-018687366874610.1109/ACCESS.2020.29782729046774Visual and Textual Jointly Enhanced Interpretable Fashion RecommendationQianqian Wu0https://orcid.org/0000-0001-5154-5578Pengpeng Zhao1Zhiming Cui2School of Computer Science and Technology, Institute of Artificial Intelligence, Soochow University, Suzhou, ChinaSchool of Computer Science and Technology, Institute of Artificial Intelligence, Soochow University, Suzhou, ChinaSchool of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou, ChinaWith the rapid development of online shopping, interpretable personalized fashion recommendation using image has attracted increasing attention in recent years. The current work has been able to capture the user's preferences for visible features and provide visual explanations. However, they ignored the invisible features, such as the material and quality of the clothes, and failed to offer textual explanations. To this end, we propose a Visual and Textual Jointly Enhanced Interpretable (VTJEI) model for fashion recommendations based on the product image and historical review. The VTJEI can provide more accurate recommendations and visual and textual explanations through the joint enhancement of textual information and visual information. Specifically, we design a bidirectional two-layer adaptive attention review model to capture the user's visible and invisible preferences to the target product and provide textual explanations by highlighting some words. Moreover, we propose a review-driven visual attention model to get a more personalized image representation driven by the user's preference obtained from the historical review. In this way, we not only realize the joint enhancement of visual information and textual information but also provide a visual explanation by highlighting some regions. Finally, we performed extensive experiments on real datasets to confirm the superiority of our model on Top-N recommendations. We also built a labeled dataset for evaluating our provided visible and invisible explanations quantitatively. The result shows that we can not only provide more accurate recommendations but also can provide both visual and textual explanations.https://ieeexplore.ieee.org/document/9046774/Explainable recommendationfashion recommendationvisual and textual explanations
collection DOAJ
language English
format Article
sources DOAJ
author Qianqian Wu
Pengpeng Zhao
Zhiming Cui
spellingShingle Qianqian Wu
Pengpeng Zhao
Zhiming Cui
Visual and Textual Jointly Enhanced Interpretable Fashion Recommendation
IEEE Access
Explainable recommendation
fashion recommendation
visual and textual explanations
author_facet Qianqian Wu
Pengpeng Zhao
Zhiming Cui
author_sort Qianqian Wu
title Visual and Textual Jointly Enhanced Interpretable Fashion Recommendation
title_short Visual and Textual Jointly Enhanced Interpretable Fashion Recommendation
title_full Visual and Textual Jointly Enhanced Interpretable Fashion Recommendation
title_fullStr Visual and Textual Jointly Enhanced Interpretable Fashion Recommendation
title_full_unstemmed Visual and Textual Jointly Enhanced Interpretable Fashion Recommendation
title_sort visual and textual jointly enhanced interpretable fashion recommendation
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2020-01-01
description With the rapid development of online shopping, interpretable personalized fashion recommendation using image has attracted increasing attention in recent years. The current work has been able to capture the user's preferences for visible features and provide visual explanations. However, they ignored the invisible features, such as the material and quality of the clothes, and failed to offer textual explanations. To this end, we propose a Visual and Textual Jointly Enhanced Interpretable (VTJEI) model for fashion recommendations based on the product image and historical review. The VTJEI can provide more accurate recommendations and visual and textual explanations through the joint enhancement of textual information and visual information. Specifically, we design a bidirectional two-layer adaptive attention review model to capture the user's visible and invisible preferences to the target product and provide textual explanations by highlighting some words. Moreover, we propose a review-driven visual attention model to get a more personalized image representation driven by the user's preference obtained from the historical review. In this way, we not only realize the joint enhancement of visual information and textual information but also provide a visual explanation by highlighting some regions. Finally, we performed extensive experiments on real datasets to confirm the superiority of our model on Top-N recommendations. We also built a labeled dataset for evaluating our provided visible and invisible explanations quantitatively. The result shows that we can not only provide more accurate recommendations but also can provide both visual and textual explanations.
topic Explainable recommendation
fashion recommendation
visual and textual explanations
url https://ieeexplore.ieee.org/document/9046774/
work_keys_str_mv AT qianqianwu visualandtextualjointlyenhancedinterpretablefashionrecommendation
AT pengpengzhao visualandtextualjointlyenhancedinterpretablefashionrecommendation
AT zhimingcui visualandtextualjointlyenhancedinterpretablefashionrecommendation
_version_ 1724186425810747392