Call for Submissions

Important Dates 

Submission Date: 13.03.2024, 11:59 PM PST

Notification Date:  09.04.2024

Camera-Ready Date: 14.04.2024

Workshop: 17-18.06.2024

Background

Creative domains, such as fashion, art and design, are a significant part of modern society, and much effort centers around the creation, consumption and analytics of creative visual content. In recent years, there has been an explosion of research in applying machine learning and computer vision algorithms to various aspects of the creative domains, including generating, analyzing and processing visual content.

Our Computer Vision for Fashion, Art, and Design (CVFAD) workshop in its 7th edition aims to build on the success of the previous versions, and on the increased interest witnessed over time, to create a space for collaboration between artists, professionals in creative industries and computer vision scientists.

Call for Submissions

The workshop will provide 3 keynotes with diverse backgrounds to encourage interdisciplinary discussions and idea sharing, as well as a paper track.

For the paper track, we solicit papers on developing and applying computer vision techniques that are valuable in the creative domains, with an emphasis on fashion, art and design. These submissions will undergo a peer-review process. To provide rich opportunities to share opinions and experience in such an emerging field, we will accept paper submissions on established and novel ideas, as well as workshop challenges.

Topics of papers include but are not limited to:

• 3D content generation for design and style: virtual fitting rooms, interior design etc.

• Style and product recommendation: suggests fashion articles or outfits which complement the style of a particular article or according to the user’s preference,

• Cross-domain visual search for fashion: robust visual search between different domains, such as street-style photos, catalog images and art/design sketches,

• Visual size and fit advice: automatically provide generic or personalized visual size and fit advice to assist users in their shopping journey.

• Virtual try-on/wardrobe: projects fashion articles onto humans/avatars in order to visualize the style and fit of an outfit, generative models for 3D,

• Body Shape Prediction: infer users’ body shape or measurements based on single or multiple images, as well as RGB-D data,

• Automatic article tagging: automatically tag articles with visual features which enables fast inventory logging,

• Trend analysis and forecasting: automated visual style discovery and trend analysis and forecasting from social media data with weak supervision,

• Personal shopping assistants: multi-modal interaction between the user and an intelligent agent which aims to assist the shopper’s experience, such as style discovery and accurate product search,

• Efficient methods for fashion search: retrieves images of fashion items that match the online user’s query (the query itself can take many forms),

• Fashion analysis in videos: fashion outfits parsing and retrieval in videos,

• Design with humans in the loop: generative design algorithms which aim to explore systems that can augment human’s creative process, with new approaches to human algorithm interaction,

• Creative visual Content generation for fashion or art: generating high-quality fashion or artistic images via automated approaches,

• Clothing landmark estimation: predicting landmarks for each detected clothing item in fashion images,

• Influence and style propagation modeling: inferring influence relations and style propagation patterns in fashion.

Accepted papers will be part of the workshop proceedings and be displayed on our website. The top papers will also be invited to present orally during the workshop. Submitted papers should follow the CVPR 2024 paper template. The page limit is less than four pages, excluding references. Submitted work can be shorter versions (extended abstract) of work presented at the main conference or work in progress which may (or may not) be submitted to a different conference at a later date. The accepted papers will be linked at the workshop webpage. Papers will be peer reviewed under double-blind policy, and must be submitted online through the CMT submission system at 

https://cmt3.research.microsoft.com/CVFAD2024

Authors can choose to include their paper as part of the CVPR Workshop Proceedings if the paper is not the shorter version of an accepted work in the CVPR 2024 proceedings. Papers which exceed the page limit (four pages excluding references) will result in rejection.

Thanks to the 4-pages limitations, submitting to our workshop will not prevent you from submitting to conferences.