Winner of Best Paper Awards sponsored by TrackMan:
ARTHuS: Adaptive Real-Time Human Segmentation in Sports through Online Distillation. Anthony Cioppa, Adrien Deliege, Maxime Istasse, Christophe De Vleeschouwer, and Marc Van Droogenbroeck

Program (June 17, 2019)
Room:
Presentations: Hyatt Shoreline A
Poster session: Pacific Arena Ballroom – main convention center, posters #222 – 235

8.30-8.40 Welcome
8.40-9.25 Invited talk by Eric Li, Intel Sports Group (see abstract and bio below)
9.25-10.00 Poster spotlight presentations
10.00-11.15 Poster session + coffee break
11.15-12.00 Invited talk by Fredrik Tuxen, TrackMan (see abstract and bio below)
12.00-12.15 Best paper award + closing remarks

Accepted papers

  • Early Detection of Injuries in MLB Pitchers from Video. AJ Piergiovanni and Michael Ryoo.
  • Fine-grained Visual Dribbling Style Analysis for Soccer Videos with Augmented Dribble Energy Image. Runze Li and Bir Bhanu
  • Investigation on Combining 3D Convolution of Image Data and Optical Flow to Generate Temporal Action Proposals. Patrick Schlosser, David Münch, and Michael Arens
  • Pose-Guided R-CNN for Jersey Number Recognition in Sports. Hengyue Liu and Bir Bhanu
  • Attentive Spatio-Temporal Representation Learning for Diving Classification. Gagan Kanojia, Sudhakar Kumawat, and Shanmuganathan Raman
  • Associative Embedding for Team Discrimination. Maxime Istasse, Julien Moreau, and Christophe De Vleeschouwer
  • Multi-person 3D Pose Estimation and Tracking in Sports. Lewis Bridgeman, Marco Volino, Jean-Yves Guillemaut, and Adrian Hilton
  • Sports Camera Calibration via Synthetic Data. Jianhui Chen and Jim Little
  • ARTHuS: Adaptive Real-Time Human Segmentation in Sports through Online Distillation. Anthony Cioppa, Adrien Deliege, Maxime Istasse, Christophe De Vleeschouwer, and Marc Van Droogenbroeck
  • Generation of Ball Possession Statistics in Soccer using Minimum-Cost Flow Network. Saikat Sarkar, Amlan Chakrabarti, and Dipti Prasad Mukherjee
  • Refining Joint Locations for Human Pose Tracking in Sports Videos. Dan Zecha, Moritz Einfalt, and Rainer Lienhart
  • Temporal Distance Matrices for Squat Classification. Ryoji Ogata, Edgar Simo-Serra, Satoshi Iizuka, and Hiroshi Ishikawa
  • Temporal Hockey Action Recognition via Pose and Optical Flows. Zixi Cai, Helmut Neher, Kanav Vats, David Clausi, and John Zelek
  • GolfDB: A Video Database for Golf Swing Sequencing. William McNally, Kanav Vats, Tyler Pinto, Chris Dulhanty, John McPhee, and Alexander Wong

Papers are available for download from CVF.

Presentation guidelines
Each paper has a 2-minute spotlight presentation and a poster presentation. For the spotlight presentation you must send your PowerPoint presentation (.ppt/.pptx format) to rg@create.aau.dk no later than Tuesday 11th of June. The slides will then be collected and presented from one computer to make this session run smoothly. Maximum 2 slides per paper (plus an optional title slide for your paper).
The maximum dimensions of posters are 8 feet wide by 4 feet high.

Best paper award
1000$ sponsored by TrackMan.


Invited speakers

Fredrik Tuxen, CTO @ TrackMan, http://www.trackman.com/
Abstract:
TrackMan has changed the way we understand and enjoy the games of golf and baseball. TrackMan is the ball tracking technology for all professional baseball games in the world incl generating data for STATCAST by MLB. TrackMan is used every week on the PGA Tour by both Tour Pro’s and broadcasters as well as thousands of instructors and coaches. TrackMan’s ball tracking technology is based on a unique combination of radar and vision tracking, and translates the flight of a ball and trajectory of a club or bat into insights that enable athletes and thought leaders to connect feel with facts. The masters of golf, baseball and other sports rely on TrackMan’s technology to understand their game, improve their performance and, eventually, unleash their full potential.
Bio:
Fredrik Tuxen is CTO and co-founder of TrackMan which was established in 2003. Fredrik is the inventor of the TrackMan technology and is heading an R&D group of 120 people. Fredrik holds a M.Sc. degree in electrical engineering from Denmark’s Technical University (DTU) from 1990 with specialty in radar and signal processing. Further, Fredrik is the inventor of more than 20 patents.

Eric Li, Intel Sports Group, https://www.intel.com/content/www/us/en/sports/sports-overview.html
Optical Player and Ball Tracking in Soccer
Abstract:
Intel Sports has a volumetric video capture technology that gives avid fans a new and immersive ways to engage with sports content. It allows fans to see every angle of the most amazing plays – even from the player’s perspective. High-resolution cameras and AI technologies are now deployed in stadiums and cloud around the world. You can experience amazing replays and highlights on TV, in the stadium, or on sports websites and apps (https://www.intel.com/content/www/us/en/sports/technology/true-view.html).
In this project, one complex task we need address is real-time player and ball tracking. This talk will cover how we do multi-camera player and ball tracking in soccer. Meanwhile, how we handle the difficulties in real production environment will also be discussed.
Bio:
Eric Li joined Intel in 2002. He is currently leading CV based player tracking technology development in Intel Sports. Prior to this, he has been working on high performance facial analysis technology development, which was used in several top messaging mobile applications. Earlier, he has been working on projects including multimedia and machine learning technology, algorithmic & architecture related parallelization and optimization. He received his B.S degree from Tsinghua Univ. in 1999, M.S degree in communication and information system from Tsinghua Univ. in 2002.

Motivation
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 has 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.

Computer vision algorithms have a huge potential in many aspects of sports ranging from automatic annotation of broadcast 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.

Call for papers
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:

– estimation of position and motion of cameras and participants in sports
– tracking people and objects in sports
– activity recognition in sports
– event detection in sports
– spectator monitoring
– annotation and indexing in sports
– graphical effects in sports
– analysis of injuries in sports
– performance assessment in sports
– alternative sensing in sports (beyond the visible spectrum)


Important dates

  • Submission deadline: March 10 March 14, 2019
  • Notification of acceptance: April 1 April 3, 2019
  • Camera ready version: April 8 April 17, 2019
  • Workshop date: June 17, 2019


Submission instructions
Guidelines (same as for CVPR): Link
Submission: Link

Accepted papers will be published in the CVPR workshop proceedings on IEEE Xplore.


Program committee:
Adrien Deliege, University of Liege, Belgium
AJ Piergiovanni, Indiana University, USA
Anastasios Doulamis, Technical University of Crete, Greece
Anuja Dharmaratne, Monash University, Malaysia
Arda Senocak, KAIST, Saudi Arabia
Bir Bhanu, UC Riverside, USA
Dan Mikami, NTT, Japan
Dan Zecha, University of Augsburg, Germnay
Francesco Setti, University of Verona, Italy
Gen Li, Bytedance.Inc, China
Hideo Saito, Keio University, Japan
Hyun Soo Park, The University of Minnesota, USA
Jesse Davis, KU Leuven, Belgium
Jianhui Chen, University of British Columbia, Canada
Jürgen Gall, University of Bonn, Germany
Kosuke Takahashi, NTT, Japan
Lei Li, ByteDance AI Lab, China
Marc Van Droogenbroeck, University of Liege, Belgium
Mariko Isogawa, NTT, Japan
Mohib Ullah, NTNU, Norway
Moritz Einfalt, University of Augsburg, Germany
Nicola Mosca, CNR ISSIA, Italy
Noel O’Connor, Dublin City University, Ireland
Noor Ul Huda, Aalborg University, Denmark
Parthipan Siva, SPORTLOGiQ, Canada
Pushkar Shukla, University of California Santa Brabara, USA
Rainer Lienhart, Universitat Augsburg, Germany
Rajkumar Theagarajan, University of California, Riverside, USA
Rama Chellappa, University of Maryland, USA
Sergio Escalera, Computer Vision Center (UAB) & University of Barcelona, Spain
Shikun Xu, Bytedance, China
Silvio Giancola, KAUST, Saudi Arabia
Simon Denman, Queensland University of Technology, Australia
Stuart Morgan, La Trobe University, Australia
Tomoya Kaichi, Keio University, Japan

Organizers
Thomas Moeslund, Aalborg University, Denmark
Graham Thomas, BBC, UK
Adrian Hilton, University of Surrey, UK
Jim Little, University of British Columbia, Canada
Rikke Gade, Aalborg University, Denmark


Previous activities related to computer vision in sports:


Overall Meeting Sponsors