Large scale visual recommendations from street fashion images

By Vignesh Jagadeesh, Robinson Piramuthu, Anurag Bhardwaj, Wei Di, Neel Sundaresan. 2014

143 citations recorded by the source corpus.

We describe a completely automated large scale visual recommendation system for fashion. Our focus is to efficiently harness the availability of large quantities of online fashion images and their rich meta-data. Specifically, we propose two classes of data driven models in the Deterministic Fashion Recommenders (DFR) and Stochastic Fashion Recommenders (SFR) for solving this problem. We analyze relative merits and pitfalls of these algorithms through extensive experimentation on a large-scale data set and baseline them against existing ideas from color science. We also illustrate key fashion insights learned through these experiments and show how they can be employed to design better recommendation systems. The industrial applicability of proposed models is in the context of mobile fashion shopping. Finally, we also outline a large-scale annotated data set of fashion images Fashion-136K) that can be exploited for future research in data driven visual fashion.

Subfields: Computer Vision and Pattern Recognition, Social Psychology, Recommender Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Social Psychology

In Recommender Systems

Citations in the corpus

Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering (2016, background): “Previous models have considered either visual [12, 14] or temporal data [5, 19, 23, 39] in isolation, though few have modeled both aspects simultaneously as we do here.”
VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback (2015, methodology): “r the purpose of ‘in-style’ image retrieval has been previously proposed. For example, Simo-Serra et al. (2014) predict the fashionability of a person in a photograph and suggest subtle improvements. Jagadeesh et al. (2014) use a street fashion dataset with detailed annotations to identify accessori”
Image-Based Recommendations on Styles and Substitutes (2015, background): “The system shares these characteristics with more common forms of recommender system, but does so on the basis of the appearance of the object, rather than metadata, reviews, or similar.”
Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network (2015, methodology): “Due to the huge impact for e-commerce applications, there is a growing interest in methods for clothing retrieval [20, 33, 31, 44] and outfit recommendation [18].”
MMALFM (2018, background): “For example, Refs [34] and [36] consider visual features specifically for the task of clothing recommendation.”
Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation (2018, methodology): “Existing fashion datasets include WoW [2], Exact Street2Shop [45], Fashion-136K [7], and FashionVC [4] datasets.”