Co-chairs

Ted Briscoe
Darren Cosker
Frank Keller
William Smith

Dates (all 2013)

Submission: March 17th
Submission deadline extended to March 24th
Notification: April 24th
Camera ready: May 1st
Workshop: June 23rd

Proceedings

Accepted papers will appear in CVPR proceedings and on IEEE Xplore

A workshop of CVPR 2013

Call For Papers

Fragments of natural language, in the form of tags, captions, subtitles, surrounding text or audio, can aid the interpretation of image and video data by adding context or disambiguating visual appearance. In addition, labelled images are essential for training object or activity classifiers. For this reason, there is a growing interest in exploiting language understanding in order to help solve problems in computer vision.

The EPSRC Network on Vision and Language (V&L Net) has been set up to foster collaborative work in this area. It is a forum for researchers from the fields of Computer Vision and Natural Language Processing to meet, exchange ideas, expertise and technology, and form new partnerships. The aim is to create a lasting interdisciplinary research community situated at the language-vision interface, jointly working towards solutions for some of today's most challenging computational challenges, including image and video search, description of visual content and text-to-image generation.

Papers are invited that describe novel research in which language is used to help solve a vision problem or where using language and vision together offers improved performance over using one alone. We also welcome papers describing new datasets or benchmarks for language-assisted computer vision.

Topics

Topics of interest include (but are not limited to):

  • Image and video labelling and annotation
  • Image and video description
  • Computational modelling of human vision and language
  • Image and video retrieval
  • Multimodal human-computer communication
  • Automatic text illustration
  • Language-driven animation
  • Facial animation from speech
  • Assistive methodologies
  • Text-to-image generation

Submission Policy

Papers must describe high-quality, original research. Submission format will be as for CVPR with a page limit of 6 pages (with the option to purchase up to 2 additional pages).
 

 
For all enquiries contact: william.smith@york.ac.uk