British Machine Vision Conference

Last updated

The British Machine Vision Conference (BMVC) is the British Machine Vision Association (BMVA) annual conference on machine vision, image processing, and pattern recognition. [1] It is one of the major international conferences on computer vision and related areas, held in the UK. [2] [3] Particularly, BMVC is ranked as A1 by Qualis, [4] B by ERA, and A by CORE. [3] The most recent 34th BMVC was hosted at P&J Live in November 2023. [5]

Contents

BMVC is a successor of the older British Alvey Vision Conference (AVC), which had run in the years 1985 (University of Sussex), 1987 (University of Cambridge), 1988 (University of Manchester) and 1989 (University of Reading). The British Machine Vision Conference replaced AVC in 1990, when BMVA was founded. Despite starting as a national conference, it is now a prestigious major international venue with a high level of foreign participation (in 2013, 84% of accepted papers were completely from outside the UK and another 4% with mixed authorships) and high stress on quality of publications (in 2013, the acceptance rate was only 30%). [6] BMVC is a mid-sized conference, with the number of accepted publications (and therefore number of talks and posters) being around 200. [6]

Usual programme

BMVC is a single-track conference held usually [7] [8] [9] over the course of one week in early September. On Monday, there are usually one or several tutorials, followed by the main conference in the following three days. A typical conference day consists of a keynote talk, two or three oral sessions and a poster session. Thursday's programme tends to be shorter. The conference usually includes a banquet and a reception. The main conference is followed by a one-day student workshop on Friday, which provides an opportunity for doctoral students to present their work and interact with their peers.

Awards

At BMVC, there are several awards given. Besides the Best Scientific Paper Award (formerly known as Science Prize), there is Best Industrial Paper Award (formerly known as Industry Prize), Best Poster Award and others. The awards recipients are tabulated below. Additionally, other BMVA prizes such as BMVA Distinguished Fellowship and Sullivan Prize are awarded during BMVC.

YearVenueBest Scientific PaperBest Industrial PaperBest Poster
1990 University of Oxford
1991 [10] Glasgow University Using projective invariants for constant time library indexing in model-based vision. C.A. Rothwell, A. Zisserman, D.A. Forsyth and J.L. Mundy.Detecting intruders in image sequences. P.L. Rosin and T.J. Ellis.Kalman filters in constrained model based tracking. R.F. Marslin, G.D. Sullivan and K.D. Baker.
1992 University of Leeds Training Models of Shape from Sets of Examples. T.F. Cootes, C.J. Taylor, D.H. Cooper and J. Graham. [11]
1993 University of Surrey Automatic Machine Learning of Decision Rule for Classification Problems in Image Analysis. P. Pudil, J. Novovičová and J. Kittler. [12]
1994 University of York Shared: Skewed Symmetry Detection Through Local Skewed Symmetries. T.-J. Cham and R. Cipolla. [13] and Image Registration Using Multi-Scale Texture Moments. J. Sato and R. Cipolla. [14] User Programmable Visual Inspection. J.J. Hunter, J. Graham and C.J. Taylor. [15]
1995 University of Birmingham Learning Spatiotemporal Models from Examples. A. Baumberg and D.C. Hogg. [16] Statistical Grey-Level Models for Object Location and Identification. T.F.Cootes, G.J.Page, C.B.Jackson, C.J.Taylor. [11]
1996 University of Edinburgh Monocular Reconstruction of 3D Bilateral Symmetrical Objects. T. Tan. [17]
1997 University of Essex Uncalibrated Reconstruction of Curved Surfaces. J. Sato and R. Cipolla. [14] Correspondence Using Distinct Points Based on Image Invariants. K.N.Walker, T.F.Cootes and C.J.Taylor. [11]
1998 [18] University of Southampton The precision of 3D reconstruction from uncalibrated views. E. Grossmann and J.S. Victor.Applying visual processing to GPS mapping of trackside structures. D. Nicholls and D. Murray.3D shape modelling through a constrained estimation of a bicubic B-spline surface. X. Shen and M. Spann.
1999 University of Nottingham Multi-view nonlinear active shape model using kernel PCA. S. Romdhani, S. Gong and A. Psarrou. [19] [20] Learning Behaviour Models of Human Activities. A. Galata, N. Johnson and D. Hogg. [21]
2000 [22] University of Bristol Robust Point Correspondence by Concave Minimization. J. Maciel and J. Costiera.Detecting Lameness in Livestock Using Re-sampling Condensation and Multi-stream Cyclic Hidden Markov Models. D.R. Magee and R.D. Boyle.A Statistical Consistency Check for the Space Carving Algorithm. A. Broadhurst and R. Cipolla.
2001 [23] University of Manchester Recognising trajectories of facial identities using kernel discriminant analysis. Y. Li, S. Gong, H. Liddell.Application of the active shape model in a commercial medical device for bone densitometry. H.H. Thodberg and A. Rosholm.Mathematical morphology in the HLS colour space. A. Hanbury and J. Serra.
2002 [24] University of Cardiff Robust Wide baseline Stereo from Maximally Stable Extremal Regions. J. Matas, M. Urban, O. Chum and T. Pajdla.Tightly Integrated Sensor Fusion for Robust Visual Tracking. G. Klein and T. Drummond.Invariant Features from Interest Point Groups. M. Brown and D. Lowe.
2003 [25] [26] University of East Anglia Synchronising image sequences of non-rigid objects. P.A. Tresadern and I. Reid.Video analysis for cartoon-like special effects. J.P. Collomosse, D. Rowntree and P.M. Hall.The art of scalespace. J.A. Bangham, S.E. Gibson and R. Harvey.
2004 [27] Kingston University Multi-modal tracking using texture changes. C. Kemp and T.W. Drummond.Shared: A Mid-Level Description of Video, with Application to Non-photorealistic Animation. J. Collomosse and P.M. Hall. and Minimal Training, Large Lexicon, Unconstrained Sign Language Recognition. T. Kadir, R. Bowden, E.J. Ong and A. Zisserman.An Image-Based System for Urban Navigation. D. Robertson and R. Cipolla.
2005 [28] Oxford Brookes University Sub-linear Indexing for Large Scale Object Recognition. S. Obdrzalek and J. Matas.A Single-Frame Visual Gyroscope. G. Klein and T. Drummond.Offline Generation of High Quality Background Subtraction Data. E. Grossmann, A. Kale, C. Jaynes and S.S. Cheung.
2006 [29] University of Edinburgh Feature Detection and Tracking with Constrained Local Models. D. Cristinacce and T.F.Cootes."Hello! My name is... Buffy" - Automatic naming of characters in TV video. M. Everingham, J. Sivic and A. Zisserman.Automatic video segmentation using spatiotemporal T-junctions. N. Apostoloff and A. Fitzgibbon.
2007 [30] [31] University of Warwick Sparse MRF appearance models forfast anatomical structure localisation. R. Donner, G. Langs and H. Bischof.(not awarded)Towards Real-Time Traffic Sign Recognition by Class-Specific Discriminative Features. A. Ruta, Y. Li and X. Liu.
2008 [32] [33] University of Leeds Globally Optimal O(n) Solution to the PnP Problem for General Camera Models. G. Schweighofer and A. Pinz.Minimizing the Multi-view Stereo Reprojection Error for Triangular Surface Meshes. A. Delaunoy, E. Prados, P. Gargallo, J.-P. Pons and P. Sturm.Geometric LDA: A Generative Model for Particular Object Discovery. J. Philbin, J. Sivic and A. Zisserman.
2009 [34] University College London&Queen Mary University of London Stochastic image denoising. F. Estrada, D. Fleet and A. Jepson.HMM based archive film defect detection with spatial and temporal constraints. X. Wang and M. Mirmehdi.Shared: Guiding visual surveillance by tracking human attention. B. Benfold and I. Reid. and Reconstruction from uncalibrated affine silhouettes. P. McIlroy and T. Drummond.
2010 [35] Aberystwyth University Joint Optimisation for Object Class Segmentation and Dense Stereo Reconstruction. Ĺ. Ladický, P. Sturgess, C. Russell, S. Sengupta, Y. Bastanlar, W. Clocksin, P. Torr.High Five: Recognising human interactions in TV shows. A. Patron, M. Marszalek, A. Zisserman, I. Reid.Action Detection in Crowd. P. Siva and T. Xiang.
2011 [36] University of Dundee Object and action classification with latent variables. H. Bilen, V. Namboodiri and L. Van Gool.Shared: Graph-based particle filter for human tracking with stylistic variations. J. Martínez del Rincón, J.-C. Nebel and D. Makris. and Hand detection using multiple proposals. by A. Mittal, A. Zisserman and P. Torr.
2012 [37] University of Surrey Detection and Tracking of Occluded People. S. Tang, M. Andriluka and B. Schiele.Real-time Learning and Detection of 3D Texture-less Objects: A Scalable Approach. D. Damen, P. Bunnun, A. Calway and W. Mayol-cuevas.
2013 [38] University of Bristol Metric Regression Forests for Human Pose Estimation. G. Pons-Moll, J. Taylor, J. Shotton, A. Hertzmann and A. Fitzgibbon.Multi-view Body Part Recognition with Random Forests. V. Kazemi, M. Burenius, H. Azizpour and J. Sullivan.Learning to approximate global shape priors for figure-ground segmentation. D. Kuettel and V. Ferrari.
2014 [39] University of Nottingham Return of the Devil in the Details: Delving Deep into Convolutional Nets. K. Chatfield, K. Simonyan, A. Vedaldi and A. Zisserman.Simultaneous Mosaicing and Tracking with an Event Camera. H. Kim, A. Handa, R. Benosman, S.-H. Ieng and A. Davison.Upper Body Pose Estimation with Temporal Sequential Forests. J. Charles, T. Pfister, D. Magee, D. Hogg and A. Zisserman.
2015 [40] Swansea University Sketch-a-Net that Beats Humans. Q. Yu, Y. Yang, Y. Song, T. Xiang and T. HospedalesDeep Perceptual Mapping for Thermal to Visible Face Recognition. M. S. Sarfraz and R. StiefelhagenRobust Global Motion Compensation in Presence of Predominant Foreground. S. M. Safdarnejad, X. Liu and L. Udpa
2016 [41] York University
2017 [42] Imperial College London
2018 [43] Northumbria University Non-smooth M-estimator for Maximum Consensus Estimation. Le, Huu, Anders Eriksson, Michael Milford, Thanh Toan Do, Tat Jun Chin, and David Suter.Automatic Semantic Content Removal by Learning to Neglect. Siyang Qin, Jiahui Wei, and Roberto Manduchi.
2019 [44] Cardiff University Tracking Holistic Object Representations. A. Sauer, E. Aljalbout and S. HaddadinContent and Colour Distillation for Learning Image Translations with the Spatial Profile Loss. S. Sarfraz, C. M. Seibold, H. Khalid and R. Stiefelhagen

Other awards

See also

Related Research Articles

Random sample consensus (RANSAC) is an iterative method to estimate parameters of a mathematical model from a set of observed data that contains outliers, when outliers are to be accorded no influence on the values of the estimates. Therefore, it also can be interpreted as an outlier detection method. It is a non-deterministic algorithm in the sense that it produces a reasonable result only with a certain probability, with this probability increasing as more iterations are allowed. The algorithm was first published by Fischler and Bolles at SRI International in 1981. They used RANSAC to solve the Location Determination Problem (LDP), where the goal is to determine the points in the space that project onto an image into a set of landmarks with known locations.

Michael Irwin Jordan is an American scientist, professor at the University of California, Berkeley and researcher in machine learning, statistics, and artificial intelligence.

The following outline is provided as an overview of and topical guide to computer vision:

Andrew Zisserman is a British computer scientist and a professor at the University of Oxford, and a researcher in computer vision. As of 2014 he is affiliated with DeepMind.

<span class="mw-page-title-main">Alan Bovik</span>

Alan Conrad Bovik is an American engineer, vision scientist, and educator. He is a professor at the University of Texas at Austin (UT-Austin), where he holds the Cockrell Family Regents Endowed Chair in the Cockrell School of Engineering and is Director of the Laboratory for Image and Video Engineering (LIVE). He is a faculty member in the UT-Austin Department of Electrical and Computer Engineering, the Machine Learning Laboratory, the Institute for Neuroscience, and the Wireless Networking and Communications Group.

The International Conference on Computer Vision (ICCV) is a research conference sponsored by the Institute of Electrical and Electronics Engineers (IEEE) held every other year. It is considered to be one of the top conferences in computer vision, alongside CVPR and ECCV, and it is held on years in which ECCV is not.

Maria Petrou FREng was a Greek-born British scientist who specialised in the fields of artificial intelligence and machine vision. She developed a number of novel image recognition techniques, taught at Surrey University and Imperial College London, and was a prolific author of scientific articles.

<span class="mw-page-title-main">John O'Keefe (neuroscientist)</span> American–British neuroscientist

John O'Keefe, is an American-British neuroscientist, psychologist and a professor at the Sainsbury Wellcome Centre for Neural Circuits and Behaviour and the Research Department of Cell and Developmental Biology at University College London. He discovered place cells in the hippocampus, and that they show a specific kind of temporal coding in the form of theta phase precession. He shared the Nobel Prize in Physiology or Medicine in 2014, together with May-Britt Moser and Edvard Moser; he has received several other awards. He has worked at University College London for his entire career, but also held a part-time chair at the Norwegian University of Science and Technology at the behest of his Norwegian collaborators, the Mosers.

<span class="mw-page-title-main">BMVA Summer School</span>

BMVA Summer School is an annual summer school on computer vision, organised by the British Machine Vision Association and Society for Pattern Recognition (BMVA). The course is residential, usually held over five days, and consists of lectures and practicals in topics in image processing, computer vision, pattern recognition. It is intended that the course will complement and extend the material in existing technical courses that many students/researchers will encounter in their early stage of postgraduate training or careers. It aims to broaden awareness of knowledge and techniques in Vision, Image Computing and Pattern Recognition, and to develop appropriate research skills, and for students to interact with their peers, and to make contacts among those who will be the active researchers of their own generation. It is open to students from both UK and non-UK universities. The registration fees vary based on time of registration and are in general slightly higher for non-UK students. The summer school has been hosted locally by various universities in UK that carry out Computer Vision research, e.g., Kingston University, the University of Manchester, Swansea University and University of Lincoln.

Medical Image Understanding and Analysis (MIUA) is a UK-based meeting for the communication of research related to image analysis and its application to medical imaging and biomedicine. The meetings provide an opportunity to present and discuss research in medical image understanding and analysis; a rapidly growing subject with ever increasing real-world applicability.

John D. Lafferty is an American scientist, Professor at Yale University and leading researcher in machine learning. He is best known for proposing the Conditional Random Fields with Andrew McCallum and Fernando C.N. Pereira.

Pushmeet Kohli is a computer scientist at Google DeepMind where he holds the position of Vice President of research for the "Secure and Reliable AI" and "AI for Science and Sustainability". Before joining DeepMind, he was partner scientist and director of research at Microsoft Research and a post-doctoral fellow at the University of Cambridge. Kohli's research investigates applications of machine learning and computer vision. He has also made contributions in game theory, discrete algorithms and psychometrics.

P. J. Narayanan is a professor at the International Institute of Information Technology, Hyderabad, and the institute's current director since April 2013. He is known for his work in computer vision, computer graphics, and parallel computing on the GPU.

<span class="mw-page-title-main">Pascal Vitali Fua</span>

Pascal Fua is a computer science professor at EPFL. He received an engineering degree from École Polytechnique, Paris, in 1984 and a Ph.D. in computer science from the University of Orsay in 1989. He joined EPFL in 1996. Before that, he worked at SRI International and at INRIA Sophia-Antipolis as a computer scientist.

Andrew Fitzgibbon FREng is an Irish researcher in computer vision. Since 2022, he has worked at Graphcore.

Michal Irani is a professor in the Department of Computer Science and Applied Mathematics at the Weizmann Institute of Science, Israel.

Lourdes de Agapito Vicente is British computer scientist and academic. She is Professor of 3D Vision in the department of computer science at University College London (UCL), where she leads a research group with a focus on 3D dynamic scene understanding from video. Agapito is the co-founder of the software company Synthesia, and an elected member of the Executive Committee of the British Machine Vision Association.

Tamara Lee Berg is a tenured associate professor at the University of North Carolina at Chapel Hill and a research scientist manager at Facebook AML/FAIR.

<span class="mw-page-title-main">Roberto Cipolla</span> British researcher in computer vision

Roberto Cipolla, FREng, is a British researcher in computer vision and Professor of Information Engineering at the University of Cambridge.

References

  1. ↑ "The British Machine Vision Conference (BMVC)". British Machine Vision Association.
  2. ↑ "BMVC". Conference Ranks. Retrieved 2014-12-15.
  3. 1 2 "CORE Conference Portal". Computing Research and Education Association of Australasia, CORE Inc. Retrieved 2023-12-01.
  4. ↑ "Qualis Conferências - Ciência da Computação - 2016" (PDF). Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES). Retrieved 2018-12-12.
  5. ↑ "The 34th British Machine Vision Conference 2023: Home" . Retrieved 2023-12-01.
  6. 1 2 "BMVC Statistics". BMVA. Archived from the original on 2019-03-27. Retrieved 2019-03-28.
  7. ↑ "BMVC 2012 Conference Programme". University of Surrey. Archived from the original on 2014-12-15. Retrieved 2014-12-15.
  8. ↑ "BMVC 2013 - Final Programme". University of Bristol . Retrieved 2014-12-15.
  9. ↑ "BMVC 2014 Programme" (PDF). University of Nottingham . Retrieved 2014-12-15.
  10. ↑ Pete Mowforth (1991). BMVC'91 - Chairman's report, BMVA News, Volume 2 Number 4
  11. 1 2 3 "Tim Cootes: Publications". University of Manchester . Retrieved 2014-12-15.
  12. ↑ "Jana Novovičová - Scientific Awards". Czech Academy of Sciences . Retrieved 2014-12-15.
  13. ↑ "Profile - Cham, Tat-Jen". Nanyang Technological University. Retrieved 2014-12-15.
  14. 1 2 Kazuki Kozuka, Cheng Wan and Jun Sato (2008). Rectification of 3D data obtained from moving range sensor by using extended projective multiple view geometry (section Biography of Jun Sato). International Journal of Automation and Computing, Volume 5, Issue 3, p. 275.
  15. ↑ Tony Lacey (1994). BMVC'94, BMVA News, Volume 5 Number 3
  16. ↑ "An Integrated Traffic and Pedestrian Vision System: Papers". University of Leeds. Archived from the original on 2015-09-24. Retrieved 2014-12-15.
  17. ↑ "Springer in China - TAN Tienu". Springer . Retrieved 2014-12-15.
  18. 1 2 Mark Nixon (1998). The Ninth British Machine Vision Conference, BMVA News, Volume 9 Number 2
  19. ↑ "Alexandra Psarrou - Publications". University of Westminster . Retrieved 2014-12-15.
  20. ↑ "Queen Mary Vision Group - Dynamic Face Models". Queen Mary University of London . Retrieved 2014-12-15.
  21. ↑ "Aphrodite Galata -- Publications". University of Manchester . Retrieved 2014-12-15.
  22. 1 2 Maria Petrou (2000). Prizes at BMVC 2000, BMVA News, Volume 11 Number 2
  23. 1 2 3 Maria Petrou (2001). Prizes at BMVC 2001, BMVA News, Volume 12 Number 1
  24. 1 2 3 4 Maria Petrou (2002). Prizes at BMVC 2002, BMVA News, Volume 13 Number 1
  25. 1 2 3 Richard Harvey (2003). Report on BMVC 2003, BMVA News, Volume 14 Number 1
  26. ↑ "BMVC Best Paper Awards". VisionWang: Computer Vision Expert Blog. Retrieved 2014-12-15.
  27. 1 2 3 T.J. Ellis (2003). BMVC 2004 Prizes and Awards, BMVA News, Volume 15 Number 1
  28. ↑ Andrew Fitzgibbon (2005). BMVC Prizes, BMVA News, Volume 16 Number 1
  29. ↑ Mike Chantler (2006). Prizes awarded at BMVC 2006, BMVA News, Volume 17 Number 1
  30. 1 2 Majid Mirmehdi (2007). Prizes and Awards, BMVA News, Volume 18 Number 1
  31. 1 2 "BMVC2007 Warwick - Prizes and Awards". University of Warwick . Retrieved 2014-12-15.
  32. 1 2 3 Mark Everingham (2008). Prizes and Awards at BMVC 2008, BMVA News, Volume 19 Number 1
  33. 1 2 3 "BMVC 2008 - Awards and Prizes". University of Leeds . Retrieved 2014-12-15.
  34. ↑ Simon J.D. Prince (2009). Summary of Prizes Presented at BMVC 2009, BMVA News, Volume 20 Number 1
  35. 1 2 3 Roy Davies (2010). Prizes and Awards at BMVC 2010, BMVA News, Volume 21 Number 1
  36. 1 2 3 4 Stephen McKenna (2011). Prizes and Awards at BMVC 2011, BMVA News, Volume 22 Number 1
  37. 1 2 3 4 5 Krystian Mikolajczyk (2012). Prizes and Awards at BMVC 2012, BMVA News, Volume 23 Number 1
  38. 1 2 Dima Damen (2013). Prizes and Awards at BMVC 2013, BMVA News, Volume 24 Number 1
  39. 1 2 "BMVC 2014 - British Machine Vision Conference". University of Nottingham . Retrieved 2014-12-15.
  40. ↑ "26th British Machine Vision Conference". Swansea University . Retrieved 2016-08-05.
  41. ↑ "BMVC 2016" . Retrieved 2016-08-05.
  42. ↑ "BMVC 2017" . Retrieved 2017-10-24.
  43. ↑ "BMVC 2018" . Retrieved 2018-09-03.
  44. ↑ "BMVC 2019" . Retrieved 2019-04-04.
  45. ↑ Tim Cootes (2001). BMVC 2001 Presentation Prize, BMVA News, Volume 12 Number 2
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.