The Elements of Fashion Style

Vaccaro, Kristen; Shivakumar, Sunaya; Ding, Ziqiao; Karahalios, Karrie; Kumar, Ranjitha

doi:10.1145/2984511.2984573

Cited by 40 publications

(29 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Vaccaro et al . [32] trained a topic model over outfits in order to learn latent fashion concepts. Others have identified clothing styles using meta-data labels [28] or learning a topic model over a bag of visual attributes [15].…”

Section: Related Workmentioning

confidence: 99%

Learning Type-Aware Embeddings for Fashion Compatibility

Vasileva

Plummer

Dusad

et al. 2018

Computer Vision – ECCV 2018

Self Cite

176

237

View full text Add to dashboard Cite

Outfits in online fashion data are composed of items of many different types (e.g. top, bottom, shoes) that share some stylistic relationship with one another. A representation for building outfits requires a method that can learn both notions of similarity (for example, when two tops are interchangeable) and compatibility (items of possibly different type that can go together in an outfit). This paper presents an approach to learning an image embedding that respects item type, and jointly learns notions of item similarity and compatibility in an end-toend model. To evaluate the learned representation, we crawled 68,306 outfits created by users on the Polyvore website. Our approach obtains 3-5% improvement over the state-of-the-art on outfit compatibility prediction and fill-in-the-blank tasks using our dataset, as well as an established smaller dataset, while supporting a variety of useful queries 1 .

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Type-Aware Embeddings for Fashion Compatibility

Vasileva

Plummer

Dusad

et al. 2018

Computer Vision – ECCV 2018

Self Cite

176

237

View full text Add to dashboard Cite

show abstract

“…Other example of fashion trend spotting on Google is using multiple markets focusing on apparel trends to enable a better understanding of how trends spread and behaviors emerge across markets 32 . Other ideas can extend the work of [21] as well as our illustrated examples (poster 33 ). Interestingly, the work in [21] uses translational topic coherence among some crowd-sourcing tasks in order to translate (abstract) style-language into (concrete) element-language and, in this way, generate recommendations from natural language requests or subjective description notes.…”

Section: Future Workmentioning

confidence: 78%

“…Other ideas can extend the work of [21] as well as our illustrated examples (poster 33 ). Interestingly, the work in [21] uses translational topic coherence among some crowd-sourcing tasks in order to translate (abstract) style-language into (concrete) element-language and, in this way, generate recommendations from natural language requests or subjective description notes. This is a step that, against Stitch Fix's philosophy, has as target to achieve a fully digital stylist (without the human in the loop).…”

Section: Future Workmentioning

confidence: 78%

Extending Knowledge Graphs with Subjective Influence Networks for Personalized Fashion

Bollacker¹,

Díaz-Rodríguez²,

Li³

2018

Designing Cognitive Cities

View full text Add to dashboard Cite

This chapter shows Stitch Fix's industry case as an applied fashion application in cognitive cities. Fashion goes hand in hand with the economic development of better methods in smart and cognitive cities, leisure activities and consumption. However, extracting knowledge and actionable insights from fashion data still presents challenges due to the intrinsic subjectivity needed to effectively model the domain. Fashion ontologies help address this, but most existing such ontologies are "clothing" ontologies, which consider only the physical attributes of garments or people and often model subjective judgements only as opaque categorizations of entities. We address this by proposing a supplementary ontological approach in the fashion domain based on subjective influence networks. We enumerate a set of use cases this approach is intended to address and discuss possible classes of prediction questions and machine learning experiments that could be executed to validate or refute the model. We also present a case study on business models and monetization strategies for digital fashion, a domain that is fast-changing and gaining the battle in the digital domain.

show abstract

“…The well-known topic model Latent Dirichlet Allocation (LDA) [3] and its polylingual extension [29] use multinomial distributions to represent the generation of documents comprised of words. Polylingual topic models are applied to Web fashion data in [35] to discover links between textual design elemen meta-data and textual style meta-data, with no computer vision. Early uses of topic models in vision relied on "visual words" (quantized image patches) to discover representations for scene recognition [10] or perform object category discovery in unlabeled images [34].…”

Section: Related Workmentioning

confidence: 99%

Learning the Latent “Look”: Unsupervised Discovery of a Style-Coherent Embedding from Fashion Images

Hsiao

Grauman

2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

What defines a visual style? Fashion styles emerge organically from how people assemble outfits of clothing, making them difficult to pin down with a computational model. Low-level visual similarity can be too specific to detect stylistically similar images, while manually crafted style categories can be too abstract to capture subtle style differences. We propose an unsupervised approach to learn a style-coherent representation. Our method leverages probabilistic polylingual topic models based on visual attributes to discover a set of latent style factors. Given a collection of unlabeled fashion images, our approach mines for the latent styles, then summarizes outfits by how they mix those styles. Our approach can organize galleries of outfits by style without requiring any style labels. Experiments on over 100K images demonstrate its promise for retrieving, mixing, and summarizing fashion images by their style.

show abstract

The Elements of Fashion Style

Cited by 40 publications

References 26 publications

Learning Type-Aware Embeddings for Fashion Compatibility

Learning Type-Aware Embeddings for Fashion Compatibility

Extending Knowledge Graphs with Subjective Influence Networks for Personalized Fashion

Learning the Latent “Look”: Unsupervised Discovery of a Style-Coherent Embedding from Fashion Images

Contact Info

Product

Resources

About