A Comparative Study of Outfit Recommendation Methods with a Focus on Attention-based Fusion

作者：

Highlights：

• Outfit recommender systems based on multimodal item representations work best.

• Outfit recommendation needs effective fusion of shared and complementary features.

• Unimodal attention mechanisms can focus on fine-grained and complementary features.

• Deep learning based recommender system for outfit recommendation.

摘要

•Outfit recommender systems based on multimodal item representations work best.•Outfit recommendation needs effective fusion of shared and complementary features.•Unimodal attention mechanisms can focus on fine-grained and complementary features.•Deep learning based recommender system for outfit recommendation.

论文关键词：Outfit recommendation,Outfit recommender system,Fashion e-commerce,Semantic item representation,Attention,Attention-based fusion

论文评审过程：Received 12 November 2019, Revised 27 May 2020, Accepted 29 May 2020, Available online 24 June 2020, Version of Record 24 June 2020.

论文官网地址：https://doi.org/10.1016/j.ipm.2020.102316