Coder Social home page Coder Social logo

fashionaicontest's Introduction

Intro:

Upgrades in consumption patterns mean that there is significant room for potential growth in the fashion industry. According to official statistics from different countries, the market value of the global apparel market is worth over USD 3 trillion. Although artificial intelligence (AI) technology has been evolving along with the fashion industry, there are still different challenges in different areas that need to be addressed.

The Vision & Beauty Team, Alibaba Group and Institute of Textile & Clothing, The Hong Kong Polytechnic University are pleased to announce that they are co-organizing the FashionAI Global Challenge 2018, which will jointly launch a revolutionary dataset which integrates both professional fashion knowledge and machine learning formulation. The world's first FashionAI Global Challenge offers RMB 1.34 million prize pool, inviting you to solve the imminent issues on the application of AI in fashion.

Description

Key Points Detection of Apparel

The analysis of apparel with computers could be easily affected by the dimension and shape of the apparel, distance and angle of shooting, or even how the apparel is displayed or the model is posing. Contestants are invited to design algorithms to detect key points of apparel images. This task can help to improve the performance of applications such as alignment, recognition of the local attributes and auto-editing of the images of apparel.

Attributes Recognition of Apparel

Apparel attributes are the basic knowledge of fashion field, which are large and complex. We constructed a hierarchical attributes tree as a structured classification target, to describe the cognitive process of apparel. Contestants are invited to design algorithms to recognize attributes of apparel images. This task might be widely applied for apparel image searching, navigating tagging, mix-and-match recommendation, etc.

TimeLine:

  1. Application: 02.01-04.21
  2. Preliminary: 03.01-04.21
  3. Semi-final: 04.26-05.24
  4. Final and Award Presentation: 07.05

The challenge consists of a preliminary and a semi-final competition online. Interested individuals can download the data, design the algorithms and carry out debugging, and then submit the results online. The final is an offline competition, which requires candidates to perform live roadshows and take part in debates. All times mentioned above are UTC+8.

Eligibility

The FashionAI Global Challenge 2018 is open to the public. Interested individuals, researchers/developers of tertiary education, research institutes or organizations from different sectors and fields are welcome to take part independently or as a team. Note: Employees of the co-organizers and supporting organizations who have access to the related data are not allowed to take part in the FashionAI Global Challenge 2018.

Application

  1. Application start date: 1 February 2018(UTC +8)
  2. Deadline for application and changes to team members: 21 April 2018 at 12:00 pm (UTC +8)
  3. Team size: Up to 8 members. Each individual can only be part of one team
  4. The organizers reserve the right to disqualify participants if the information provided on the application is inaccurate or misleading

Group Rule:

  1. Team members share codes here
  2. Every person creates his/her own folder and put codes there.
  3. Do not uploading training or testing datasets.
  4. All the datasets must be moved to a folder with name "data"
  5. All the executable files must be moved to a folder with name "apps”

Discussion paper

Google Colab free GPU tutorial

fashionaicontest's People

Contributors

pkugoodspeed avatar pkuitachi avatar

Watchers

 avatar

Forkers

nocharger

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.