AI for fashion

The third international workshop on fashion and KDD

20 August 2018, London, United Kingdom

Background

Fashion is a multi-billion-dollar industry with social and economic implications worldwide. The fashion industry has traditionally placed high value on human creativity and has been slower to realize the potential of data analytics. With the advent of modern cognitive computing technologies (data mining and knowledge discovery, machine learning, deep learning, computer vision, natural language understanding etc.) and vast amounts of (structured and unstructured) fashion data the impact on fashion industry could be transformational. Already fashion e-commerce portals are using data to be branded as not just an online warehouse, but also as a fashion destination. Luxury fashion houses are planning to recreate physical in-store experience for their virtual channels, and a slew of technology startups are providing trending, forecasting, and styling services to fashion industry.

The third international workshop on fashion and KDD will be hosted at KDD 2018 in London, United Kingdom on 20th August, 2018. The goal of this workshop is to gather people from academia, industry, and startups working at the intersection of fashion and data mining and knowledge discovery to further the technology and its adoption. The first two installments of this workshop were also held at KDD, in 2016 and 2017. It has become the premier venue for presenting works that are solving problems related to fashion using artificial intelligence, machine learning and data mining.

Topics of Interest

This is a new developing area for the KDD community and we hope this workshop will bring together all the researchers, practitioners, and interested audiences to explore the open problems, applications, and future directions in this field. We believe that the fashion industry introduces a number of interesting data analytics problems that are either not studied or scarcely studied in the past and can attract great interest in the general KDD community given their practical implications. Suggested topics include (but not limited to):

  • Detect and forecast fashion trends and cycles
  • Big data for fast fashion
  • Deep learning for fashion
  • Visual search for fashion e-commerce
  • Fashion image understanding and auto-tagging of apparel
  • Novel search mechanisms for large fashion catalogs
  • Virtual personal fashion assistants
  • Recommendation engines and cognitive stylists for fashion
  • Balancing art and science in fashion recommendation algorithms
  • Personal styling with humans and machines: recommendations with humans in the loop
  • Assembling outfit recommendations: interactions and serendipity
  • Algorithmic clothing: design by data
  • Predicting fashionability scores
  • Social networking for fashion
  • Fashion retail analytics
  • Interactive textiles
  • Digital wardrobe
  • Mining style rules
  • Assessing fashion personality (from social media platforms)
  • Virtual trial rooms
  • Plagiarism detection in fashion
  • Fashion and wearable computing
  • Technology in fashion weeks
  • AI tools for buyers and merchandisers
  • AI tools for fashion designers
  • Creative AI for fashion

We also invite submissions in other retail domains where design, trends, styling, recommendations are important (for example, jewelry, furniture etc.).

Workshop Schedule

20th August, 2018 ( 8:00AM - 12:00PM ) @ ICC London Suite Room 4


8:00 - 8:30 am - Introduction
    Welcome and Invited Talk by Michael Ferraro on Improving the Fashion Value Chain with AI

8:30 - 9:30 am - Oral Paper Presentations
  • 8:30 - 8:50 am - Outfit Generation and Style Extraction via Bidirectional LSTM and Autoencoder
  • 8:50 - 9:10 am - Styling with Attention to Details
  • 9:10 - 9:30 am - Footwear Size Recommendation System

9:30 - 10:00 am - Coffee break & Poster/Demo Session

10:00 - 10:30 am - Invited talk
Invited talk by Gerard Pons-Moll on How 3D digital humans can help fashion

10:30 - 11:30 am - Oral Paper Presentations
  • 10:30 - 10:50 am - How To Extract Fashion Trends From Social Media?
  • 10:50 - 11:10 am - Disentangling Multiple Conditional Inputs in GANs
  • 11:10 - 11:30 am - A Unified Model with Structured Output for Fashion Images Classification

11:30 - 12:00 - Invited talk and Closing
Invited talk by Roger Mitchell on Broader AI use cases in Luxury Fashion followed by an optional Open House.

Invited Speakers

Michael Ferraro
Executive Director, FIT/Infor Design and Tech Lab, Fashion Institute of Technology, NYC
Mr. Ferraro is the Executive Director of the FIT/Infor Design and Technology Lab (DTech) at the Fashion Institute of Technology in NYC. Creative technologist, researcher, artist and educator, Mr. Ferraro’s career spans the worlds of software development, virtual reality media production, fine art, commercial entertainment and higher education. He came to FIT from Lehman College/CUNY where he spent 12 years as an associate professor in the digital media program of the art department. In 2015, working with students, he won a NY Emmy for Graphics and Animation Supervision for a series of PSA’s entitled “Best of the Bronx”. In 1996, Mr. Ferraro co-founded PossibleWorlds, Inc, where he invented the innovative real-time animation technology known as Kabuki™, which has been used by media outlets such as Cartoon Network, Disney TV, MTV and Warner Brothers. In 1986, Mr. Ferraro co-founded Blue Sky Studios, a feature length computer animation studio where he was VP System Architect. Prior to Blue Sky, Mr. Ferraro was part of the R&D team at MAGI/Synthavision. Mr. Ferraro earned his MFA from the University of Massachusetts, Amherst and his BFA from Syracuse University. He resides with his family in New York City.

Gerard Pons-Moll
Research Group Leader, Max Planck for Informatics
Gerard Pons-Moll is the head of the research group "Real Virtual Humans" at the Max Planck for Informatics (MPII) in Saarbrücken, Germany. His research lies at the intersection between computer vision, computer graphics and machine learning -- with special focus on analyzing people in videos, and creating virtual human models by "looking" at real ones. His research has produced the most advanced statistical human body models of pose, shape, soft-tissue and clothing (which are currently used for a number of applications in industry and research), as well as pioneering algorithms to track and reconstruct 3D people models from images, video, depth, and IMUs. His work has been published at the major computer vision and computer graphics conferences and journals including Siggraph, Siggraph Asia, CVPR, ICCV, BMVC (Best Paper Award 2013), Eurographics (Best Paper Award 2017), IJCV and TPAMI. He co-organized workshops and tutorials on capturing and learning digital models of humans at SIGGRAPH'16, ICCV'11, ICCV'15 and ECCV'18, and gave numerous invited talks on the subject at international research institutions.

Roger Mitchell
Group Product and Platform Director, Yoox Net-A-Porter Group
As Platform and Product Director, Roger is responsible for delivering the technology platform transformation for YOOX NET-A-PORTER GROUP (YNAP), the world’s leading online luxury fashion retailer. The unified, global platform will allow YNAP to deliver an unparalleled customer experience for its 27 million monthly unique visitors across more than 180 countries.

Accepted Papers/Posters





Organizers

Program Committee Members

  • Sebastian Heinz, Zalando Research
  • Kashif Rasul, Zalando Research
  • Saboor Sheikh, Zalando Research
  • Roland Vollgraf, Zalando Research
  • Anoop Rajgopal, Data Sciences, Myntra
  • Aruna Rajan, Data Sciences, Myntra
  • Ruining He, Research Scientist, Pinterest
  • Priyanka Agrawal, Research Engineer, IBM Research
  • Abhishek Bansal, Research Engineer, IBM Research
  • Wang-Cheng Kang, Doctoral Student, University of California, San Diego
  • Zheng zheng Xing, Senior Applied Scientist, Amazon
  • Ashwani Rao, Applied Scientist, Amazon

Submission Guidelines

We solicit submission of papers of papers of 4 to 10 pages representing reports of original research, preliminary research results, case studies, proposals for new work and position papers. We also seek poster submissions based on recently published work (please indicate the conference published).

All papers will be peer reviewed, single blind (i.e. author names and affiliations should be listed). If accepted, at least one of the authors must attend the workshop to present the work. The submitted papers must be written in English and formatted in the double column standard according to the ACM Proceedings Template, Tighter Alternate style. The papers should be in PDF format and submitted via the EasyChair submission site. The workshop website will archive the published papers.

For more information or any clarifications please email aiforfashion.kdd@

  • Paper Submission Deadline: May 8, 2018 extended May 27, 2018
  • Acceptance Notifications: June 8, 2018 extended June 13, 2018
  • Camera-Ready Submission Date: Jun 25, 2018
  • Workshop date: August 20, 2018

All deadlines are at 11:59 PM Pacific Standard Time.

Submit