![\"\"](\"https:\/\/vap.aau.dk\/cvsports\/wp-content\/uploads\/sites\/5\/2020\/05\/image-3.png\")
<\/p>\n<\/p>\n
Motivation Computer vision algorithms have a huge potential in many aspects of sports ranging from automatic annotation of broadcasted footage, through to better understand of sport injuries, and enhanced viewing. So far the use of computer vision in sports has been scattered between different disciplines.<\/p>\n 9.15 – 9.25: Welcome 12.00 – 13.30: LUNCH 15.25 – 15.55: BREAK 17.35 – 17.50: Closing remarks<\/p>\n <\/p>\n <\/p>\n Call for papers – estimation of position and motion of cameras and participants in sports<\/p>\n – tracking people and objects in sports<\/p>\n – activity recognition in sports<\/p>\n – event detection in sports<\/p>\n – spectator monitoring<\/p>\n – annotation and indexing in sports<\/p>\n – graphical effects in sports<\/p>\n – analysis of injuries in sports<\/p>\n – performance assessment in sports<\/p>\n <\/p>\n Important dates<\/strong><\/p>\n <\/p>\n \u00a0<\/strong><\/p>\n Organizers <\/p>\n
\n<\/strong>Sports is said to be the social glue of society. It allows people to interact irrespective of their social status, age etc. With the rise of the mass media a significant quantity of resources have been channeled into sports in order to improve understanding, performance and presentation. For example, areas like performance assessment, which were previously mainly of interest to coaches and sports scientists are now finding applications in broadcast and other media, driven by the increasing use of on-line sports viewing which provides a way of making all sorts of performance statistics available to viewers. Computer vision has recently started to play an important role in sports as seen in for example football where computer vision-based graphics in real-time enhances different aspects of the game.<\/p>\n
\nProgram (June 28):
\n<\/strong><\/p>\n
\n9.25 – 10.15: Keynote 1: Computer Vision for sports coverage on television. Graham Thomas, BBC<\/strong> (abstract below)
\n10.15 – 10.45: BREAK
\n10.45 – 12.00: Oral session 1<\/p>\n\n
\n13.30 – 14.10: Keynote 2: Actions in the Eye: From Hollywood to Sports. Cristian Sminchisescu, Lund University<\/strong> (abstract below)
\n14.10 – 15.25: Oral session 2<\/p>\n\n
\n15.55 – 17.35: Oral session 3<\/p>\n\n
\nKeynotes<\/strong><\/p>\n\n
\nTitle:<\/span> Computer Vision for sports coverage on television
\nAbstract:<\/span>
\nSports coverage on TV can be significantly enhanced by the use of computer vision and 3D graphics, to help analyse an event so that the programme presenters can give a clear and visually-compelling presentation to viewers.\u00a0 BBC Research & Development has been working closely with BBC Sport for many years to develop new algorithms to meet production requirements, and working with commercial graphics companies to turn these into products.\u00a0 This talk will tell some of the stories behind this work, including real-time camera tracking, segmentation and 3D reconstruction. The difficulties that have to be overcome in converting an algorithm that works in the lab to something fit for live use in a TV production environment will be discussed.<\/li>\n<\/ul>\n\n
\nTitle:<\/span> Actions in the Eye: From Hollywood to Sports
\nAbstract:<\/span>
\nSystems based on bag-of-words models operating on image features\u00a0collected at maxima of sparse interest point operators have been\u00a0successful for both computer-based visual object and action\u00a0recognition tasks. While the sparse, interest-point based approach to\u00a0recognition is not inconsistent with visual processing in biological\u00a0systems that operate in \u201dsaccade and fixate\u201d regimes, the knowledge,\u00a0methodology, and emphasis in the human and the computer vision\u00a0communities remains sharply distinct. Here, we make several\u00a0contributions aiming to bridge this gap. First, we complement existing\u00a0state-of-the art large-scale dynamic computer vision datasets like\u00a0Hollywood-2 and UCF Sports with human eye movements collected under\u00a0the ecological constraints of the visual action recognition task. To\u00a0our knowledge these are the first human eye tracking datasets of\u00a0significant size to be collected for video (497,107 frames, each\u00a0viewed by 16 subjects), unique in terms of their (a) large scale and\u00a0computer vision relevance, (b) dynamic, video stimuli, (c) task\u00a0control, as opposed to free-viewing. Second, we introduce novel\u00a0dynamic consistency and alignment models, which underline the\u00a0remarkable stability of patterns of visual search among subjects.\u00a0Third, we leverage the large amounts of collected data in order to\u00a0pursue studies and build automatic, end-to-end trainable computer\u00a0vision systems based on human eye movements. Our studies not only shed\u00a0light on the differences between computer vision spatio-temporal\u00a0interest point image sampling strategies and human fixations, as well\u00a0as their impact for visual recognition performance, but also\u00a0demonstrate that human fixations can be accurately predicted, and when\u00a0used in an end-to end automatic system, leveraging some of the most\u00a0advanced computer vision practice, can lead to state of the art\u00a0results. The dataset and related papers are available online at:\u00a0http:\/\/vision.imar.ro\/eyetracking\/.This<\/a>\u00a0is joint work at the Institute\u00a0of Mathematics (IMAR) with Stefan Mathe.<\/li>\n<\/ul>\n
\n<\/strong>The ambition of this workshop is to bring together practitioners and researchers from different disciplines to share ideas and methods on current and future use of computer vision in sports. To this end we welcome computer vision-based research contributions as well as best-practice contributions focusing on the following (and similar) topics:<\/p>\n\n
\nSubmission instructions
\n<\/strong>Same as for CVPR: Link<\/a>
\nPaper submission: Link<\/a><\/p>\n
\nProgram committee:
\n<\/strong>Ahuja N., Univ. of Illinois at Urbana-Champaign, USA
\nChellapa R., Univ. of Maryland, USA
\nChristmas B., Univ. of Surrey, UK
\nCucchiara R., Univ. Modena Reg. Emilia, Italy
\nLarry Davis, Univ. of Maryland, USA
\nDawes R., BBC R&D, UK
\nDoulamis A.D., Technical University of Crete, Greece
\nEscalera S., Univ. Of Barcelona, Spain
\nFerryman J., Univ. Reading, UK
\nGall J., Max Planck Inst., Germany
\nGhanem B., ADSC, Singapore
\nGrau, O, Intel Visual Computing Institute
\nGuan L., Ryerson Univ., Toronto, Canada
\nGong S., Queen Mary Univ. of London, UK
\nGonzalez J., UAB- CVC, Catalonia, Spain
\nHan J., Univ. of Technology Eindhoven, The Netherlands
\nHilton A., Univ. of Surrey, UK
\nIkizler-cinbis N., Univ. Boston, USA
\nKopf S., Univ. of Mannheim, Germany
\nMaybank S., Birkbeck Univ. of London, UK
\nPerales F., Univ. de les Illes Balears, Spain
\nPrati A., Univ. Iuav di Venezia, Italy
\nQingming H., Chinese Academy of Sciences, Beijing, China
\nSigal L., Disney Reseach, USA
\nSminchisescu C., Lund Univ., Sweden<\/p>\n
\n<\/strong>Thomas Moeslund<\/a>, Aalborg University, Denmark
\nGraham Thomas<\/a>, BBC, UK<\/p>\n
![\"CVF](\"https:\/\/vap.aau.dk\/cvsports\/wp-content\/uploads\/sites\/5\/2020\/05\/image.png\")
\u00a0\u00a0\u00a0\u00a0\u00a0 ![\"IEEE](\"https:\/\/vap.aau.dk\/cvsports\/wp-content\/uploads\/sites\/5\/2020\/05\/image-1.png\")
<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"