4th International Workshop on Computer Vision in Sports (CVsports) at CVPR 2018

Best paper award of 500$ sponsored by Second Spectrum went to:
A bottom-up approach based on semantics for the interpretation of the main camera stream in soccer games. Anthony Cioppa, Adrien Deliege, Marc Van Droogenbroeck

20180622_164002 20180622_164017

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.


Program (June 22 2018):

8.30 – 8.40: Welcome
8.40 – 9.25: Invited talk 1: Computational Video for Sports: Challenges for Large Scale Video Analysis. Irfan Essa, Georgia Tech
9.25 – 9.45: Oral presentation: SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos. Silvio Giancola, Mohieddine Amine, Tarek Dghaily, Bernard Ghanem.
9.45 – 10.05: Oral presentation: Deep Decision Trees for Discriminative Dictionary Learning with Adversarial Multi-Agent Trajectories. Tharindu Fernando, Sridha Sridharan, Clinton Fookes, Simon Denman.
10.05 – 10.35: BREAK
10.35 – 10.55: Oral presentation: Part-based Player Identification using Deep Convolutional Representation and Multi-scale Pooling. Arda Senocak, Tae-Hyun Oh, Junsik Kim, In Kweon.
10.55 – 11.15: Oral presentation: Fine-grained Activity Recognition in Baseball Videos. AJ Piergiovanni, Michael Ryoo.
11.15 – 12.00: Invited talk 2: Applications and open challenges for computer vision in high performance sport. Stuart Morgan, La Trobe University.
12.00 – 13.30: LUNCH
13.30 – 14.15: Invited talk 3: Invited talk: Watching with the eye of an NBA coach – insights from tracking a full season. Ken Siebert and Andres Hasfura, Second Spectrum
14.15 – 14.35: Poster spotlights
14.35 – 16.30: Poster session

  • Soccer: Who Has The Ball? Generating Visual Analytics and Player Statistics. Rajkumar Theagarajan, Federico Pala, Xiu Zhang, Bir Bhanu.
  • Convolutional Neural Networks based ball detection in tennis games. Vito Renò, Nicola Mosca, Roberto Marani, Massimiliano Nitti, Tiziana D’orazio, Ettore Stella.
  • A bottom-up approach based on semantics for the interpretation of the main camera stream in soccer games. Anthony Cioppa, Adrien Deliege, Marc Van Droogenbroeck.
  • Human Pose as Calibration Pattern; 3D Human Pose Estimation with Multiple Unsynchronized and Uncalibrated Cameras. Kosuke Takahashi, Dan Mikami, Mariko Isogawa, Hideaki Kimata.
  • Jersey Number Recognition with Semi-Supervised Spatial Transformer Network. Gen Li, Shikun Xu, Xiang Liu, Lei Li, Changhu Wang.
  • Kinematic Pose Rectification for Performance Analysis and Retrieval in Sports. Dan Zecha, Moritz Einfalt, Christian Eggert, Rainer Lienhart.
  • Automatic Cricket Highlight generation using Event-Driven and Excitement-Based features. Pushkar Shukla, Hemant Sadana, Apaar Bansal, Deepak Verma, Carlos Elmadjian, R Balasubramanian, Matthew Turk.
  • Estimation of Center of Mass for Sports Scene Using Weighted Visual hull. Tomoya Kaichi, Shohei Mori, Hideo Saito, Kosuke Takahashi, Dan Mikami, Mariko Isogawa, Hideaki Kimata.
  • A Directed Sparse Graphical Model for Multi-Target Tracking. Mohib Ullah, Faouzi Alaya-Chekh.
  • Estimating the Number of Soccer Players using Simulation-based Occlusion Handling. Noor Ul Huda, Kasper Halkjær Jensen, Rikke Gade, Thomas B. Moeslund.

15.30 – 16.00: BREAK (posters continued)
16.30 – 16.45: Best paper award & closing remarks

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

Best paper award
500$ sponsored by Second Spectrum.


Important dates

  • Submission deadline: March 10 2018 March 17 2018
  • Notification of acceptance: April 1 2018 April 6 2018
  • Camera ready version: April 18 2018
  • Workshop date: June 22, 2018


Invited speakers


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 (tentative):

Chellapa R., Univ. of Maryland, USA
Cinbiş N., Hacettepe Üniversitesi, Turkey
Dharmaratne A., Monash University, Malaysia
Doulamis A.D., Technical University of Crete, Greece
Escalera S., Univ. Of Barcelona, Spain
Feris R., IBM Research, USA
Ferryman J., Univ. Reading, UK
Gall J., Max Planck Inst., Germany
Gong S., Queen Mary Univ. of London, UK
Gonzalez J., UAB- CVC, Catalonia, Spain
Ikizler-cinbis N., Univ. Boston, USA
Joshi D., IBM Research, USA
Lucey P., Disney Research, Pittsburgh, USA
Merler M., IBM Research, USA
Prati A., Univ. Iuav di Venezia, Italy
Setti F., Iniv. of Verona, Italy

Organizers
Thomas Moeslund, Aalborg University, Denmark
Graham Thomas, BBC, UK
Adrian Hilton, University of Surrey, UK
Peter Carr, Disney Research, Pittsburgh, USA
Rikke Gade, Aalborg University, Denmark


Previous activities related to computer vision in sports:


Overall Meeting Sponsors