Welcome to the 1st Workshop on Developer-Centred Computer Vision in association with the 2012 Asian Conference on Computer Vision. This workshop aims to bring together researchers from academia and industry to discuss issues related to developer access to computer vision. The specific topics we plan to cover are listed opposite, and we hope to include work from low-level hardware interfaces to high-level APIs and visual development environments. The workshop will take place on the 5th November in Daejeon, South Korea, and the proceedings will be published with the ACCV 2012 proceedings in the Springer LNCS. The workshop has a 24% acceptance rate. Topics covered by the DCCV workshop:

  • Higher-level abstractions of vision algorithms
  • Algorithm/Task/User level API design
  • Automatic/interactive algorithm selection based on human input
  • Automatic/interactive task selection based on human input
  • Interpretation of user input such as descriptions, sketches, images or video
  • Case-studies on developer-centred computer vision
  • Visual development environments for vision system construction
  • Evaluation of vision interfaces (e.g. through user studies)

Paper Submission

Papers for DCCV 2012 should be submitted electronically through CMT at https://cmt.research.microsoft.com/DCCV2012/ before 2300 PDT 31st August 2012. Please add "cmt@microsoft.com" to your e-mail program's white-list to prevent important email announcements from being blocked by spam filters.

Abstract Submission

Please submit your paper's title, authors, abstract, and list of topic areas to the online submission website one week prior to the paper deadline in order to allow us to start the process of assigning reviewers while you finish polishing the paper. This step is optional and the site will continue to accept new submissions, but registering your paper early will help the review process.

Paper Preparation

All submissions to DCCV must follow the ACCV guidelines (except the maximum paper length for DCCV is 12 pages, not 14). Using the ACCV 2012 Author Kit (zip) is recommended.

A complete paper should be submitted in camera-ready format, except for author names and affiliation, using the Springer LNCS formatting guidelines. All reviews are double-blind, so please be careful not to include any identifying information. All papers should be submitted as PDF files (10 MB maximum), and be a maximum of 12 pages. The abstract should have a maximum of 300 words.

Supplemental Materials

You may also submit supplemental materials to assist with the review. These may include videos, additional images or other results, or appendices. Reviewers are not required to view the supplemental material, so please ensure the submitted paper is as self-contained as possible; the supplemental material should complement not complete the content of the paper.

All supplemental materials must be zipped into a single file, or you may submit a single PDF file for non-video materials. In either case, the maximum file size for the supplemental materials is 10 MB.

Other Policies

All papers submitted for DCCV must represent original, unpublished work.

Dual submission to other venues except for ACCV is not permitted.

All work submitted to DCCV is considered confidential until the papers appear at the workshop.