Welcome to the BMVC2013 Student Workshop website. This year the workshop will take place on Friday 13th, September 2013, the day after the main conference. The workshop has become a regular feature of BMVC (previous editions: 2012, 2011, 2010). It provides an excellent opportunity for postgraduate students in computer vision to present their ongoing research, to network and start collaborations with other students. Furthermore, students have the opportunity to attend key-note sessions about hot topics in the field presented by experienced researchers. The workshop will be single track containing both oral and poster presentations.


PhD and Master students in UK institutions are invited to submit full-length high-quality papers of which the main author is a student. All papers will be reviewed and selected for either oral or poster presentation. All accepted papers for the workshop will be digitally published on the USB stick provided at the conference and on-line at the BMVA website.




Important Dates


  • Paper Submission (incl supplementary material): 15 July, New deadline: 20 July 23:59 UTC
  • Author Notification: 03 August
  • Camera Ready Submission: 12 August
  • Students' Workshop: 13 September



Workshop Programme


The full workshop programme is now available here



Keynote Speakers



Gabriel Brostow

If Only We Had Tracked Something Like This Before


A picture of Gabriel Brostow

Abstract: We want algorithms that can tell us what went where in a video. Tracking is hard because each situation is different, featuring a different camera operator, and subject(s) whose appearance, motion, and setting are in a novel configuration. While each video may be pixel-wise unique, we hypothesize that the observed motions are quite similar, at least for tracking purposes. We propose that better tracking can be achieved by learning to automatically associate different videos (or parts) with different algorithms. Instead of seeking an elusive one-size-fits-all tracking strategy (often in the form of an energy function), we advocate keeping multiple strategies, but recognizing when/where to use each. We demonstrate this approach for the problems of optical flow and interest-point tracking.




Edward Rosten

Optimized Corner and Object Detection: a Completely Non Unified Approach


A picture of Edward Rosten

Abstract: Many problems in computer vision involve optimization. Choosing what to optimize can be difficult; firstly because optimization of the appropriate objective may be intractably difficult and secondly because even the correct choice of objective may not be clear. This talk is about optimization in three areas of computer vision: corner detection, object detection and biological optical microscopy.

A corner detector should repeatable detect the same corners between images, and ideally should operate efficiently. These objectives can be quantified, and I demonstrate a method for generating optimized corner detectors.

In object detection, the definition of a detection versus a misdetection or missed detection is not obvious. On this subject, I will present an object detection system for detecting small objects. This system introduces a new family of features, and detectors optimized for several different definitions of what a detection really is.

The third part of this talk is about about using factorial hidden Markov model analysis as an object detection strategy to break the resolution barrier in biological optical microscopy. By optimizing the correct model--an ensemble of fluorescent protein positions---a resolution of up to four times higher than the theoretical resolution limit for this technique can be achieved.






Workshop chair:

Dr. Jose Martinez-Carranza


Workshop assistants

Adeline Paiement

Osian Haines



Andrew Gee Qualcommm
Carlos Arteta University of Oxford
Osian Haines Univeristy of Bristol
David Hanwell University of Bristol
Javier Orozco Imperial College London
Rob Frampton Univeristy of Bristol
Jack Greenhalgh University of Bristol
Lucilio Cordero-Grande University of Valladolid
Mark Hansen University West of England
Pablo Alcantarilla Georgia Institute of Technology
Philip Tresadern University of Manchester
Rui Hu University of Surrey
Violet Snell University of Surrey
Wenbin Li University of Bath
Adeline Paiement University of Bristol






As with the main BMVC conference topics include, but are not limited to:

  • Statistics and machine learning for vision
  • Stereo, calibration and geometry
  • Person, face and gesture tracking
  • Motion, optic flow and tracking
  • Segmentation and features
  • Biomedical applications
  • Model-based vision
  • Image processing techniques and methods
  • Texture, shape and colour
  • Video analysis
  • Document processing and recognition
  • Vision for visualization and graphics


Workshop Registration


  • Workshop registration is free for all UK students and BMVC2013 registered participants.
  • If you plan to attend the main BMVC2013 conference and stay on for the workshop, please register via the main conference registration site.
  • If you want to attend the workshop ONLY and you are a UK student, please send an email to with the subject: "BMVW13 Registration". Please, use your official University email address. In the body of the email provide your name and institution.
  • If you are an academic in a UK institution who wants to attend the workshop but not BMVC, please email to with the subject: "BMVW13 Registration: Non-Student". Please, in the body of the email provide your academic affiliation details.


Call for papers


Download here the call for papers


Submissions about ongoing work are welcome, but novelty is required. By submitting a manuscript to the workshop, the authors guarantee that it has not been published previously (nor accepted for publication) in substantially similar form. Violation of any of these conditions will lead to rejection. We also require that the first author of the paper be a student at a British institution. As with the main conference, paper submission is double-blind, so please ensure you do not identify yourself or your institution in any way (see the BMVC submission guidelines for more information).


Submissions of papers are handled by CMT:



Instructions for Authors


Authors should follow the same format as required for a full BMVC2013 conference paper. Please note that for the workshop, we do not require a one-page abstract.

Please, go to to submit your paper.



Supplementary Material

Authors can optionally submit supplementary material limited to 10MB or cite the URL of their own webpages for downloading of larger files. Supplementary material may include:

  • videos to showcase results/demo of the proposed approach/system,
  • images and other results in addition to the ones in the paper,
  • related submissions to conferences and journals,
  • appendices or technical reports containing extended proofs and mathematical derivations that are not essential to the understanding of the submitted paper.

Videos should preferably be encoded using an MP4 codec such as DivX. Please include a README text file with each video specifying the exact codec used and a URL where the codec can be downloaded.


The authors should refer to the contents of the supplementary material appropriately in the paper.


Instructions for Presenters


Oral presentations will be 20 minutes long including questions (15 mins for talk, 5 mins for questions). A computer will be available for those presenters without their own laptops.


Posters should normally be A0 (landscape). Velcro pads and pins will be provided for affixing posters to the display boards.





BMVC2013 Student Workshop Logo




For further information please contact the Workshop Chair, Dr. Jose Martinez-Carranza







15 July, 23:59 UCT