11th International Workshop on Computer Vision in Sports (CVsports) at CVPR 2025

Program

Date and time: June 12, 2025, 1pm-5.15pm (local time in Nashville)

1.00-1.10pmWelcome to CVsportsThomas Moeslund, Anthony Cioppa, Silvio Giancola
1.10-1.40pmInvited talkRoland Memisevic, Qualcomm
1.40-2.40pmOral presentations5 papers of 12 minutes each (8 min. pres. + 4 min. questions), see papers in table below
2.40-4.15pmPoster session + coffee breakAll papers, see list of papers in table below
4.15-4.45pmInvited talkKatie Mills, FIFA & Sheffield Hallam University
4.45-5.00pmSoccerNet challenge resultsAnthony Cioppa, Silvio Giancola
5.00-5.15pmBest paper award and closing wordsThomas Moeslund, Anthony Cioppa, Silvio Giancola

Keynote speakers:

  • Roland Memisevic, Senior Director at Qualcomm
    • Talk: Live fitness coaching as a testbed for real-world conversational AI 
    • Abstract: Despite the immense recent progress in multi-modal language models, building AI systems that can have a real-world conversation about what is happening in front of the camera remains an extremely ambitious open problem. One reason is that existing models are trained to respond to prompts, instead of having a free-flowing live conversation. Another is that a natural real-world interaction can branch into many unforeseen directions at any point in time, making it hard to collect training data with sufficient coverage for models to generalize. In this talk I will argue that live fitness coaching is not only a highly useful task to solve. It also provides a perfect testbed for building AI models that see, hear and interact with a user in real time: on the one hand it requires a model to see and hear events as they happen, so it can respond appropriately. On the other hand, it is a highly constrained experience, much like a real-world “game”, consisting of a sequence of timed exercises and a strict definition of what counts as a correct or less correct action.  As such, fitness coaching comes with clear expectations and guardrails, within which otherwise free-form interactions can be defined and collected as training data. I will discuss in detail our work in recent years towards building real-world streaming models that can coach you in real time. This includes the collection of large-scale training data and the exploration of efficient multi-modal streaming architectures. I will also discuss open problems, such as challenges in state tracking and multi-modal fusion.
  • Katie Mills, Football Research Consultant at FIFA & Research Fellow at Sheffield Hallam University
    • Talk: Advancing Football Through Research on a Global Stage
    • Abstract:  At FIFA, research and innovation are at the heart of the game’s evolution. The FIFA Research Programme fosters collaboration between academia, industry and football stakeholders to develop and validate innovations that enhance the game’s integrity, performance, and accessibility. Our work provides the empirical foundation to tackle some of football’s biggest technological challenges – from improving match officiating with semi-automated offside technologies, to enabling deeper tactical and performance analysis through advanced tracking systems. We’re also exploring alternative, lower-cost solutions to make these tools available across all levels of the game. By sharing what we learn and working openly with the global research community, we’re helping make football more accessible, data-driven, and ready for the future.

Accepted papers:

Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real TransferDaniel Kienzle (University of Augsburg)
Robin Schön (University of Augsburg)
Rainer Lienhart (University of Augsburg)
Shin’ichi Satoh (National Institute of Informatics)
Oral + poster
Action Anticipation from SoccerNet Football Video BroadcastsMohamad Dalal (Aalborg Universitet)
Artur Xarles (Universitat de Barcelona)
Anthony Cioppa (University of Liège)
Silvio Giancola (King Abdullah University of Science and Technology (KAUST))
Marc Van Droogenbroeck (University of Liège)
Bernard Ghanem (King Abdullah University of Science and Technology (KAUST))
Albert Clapés (Universitat de Barcelona)
Sergio Escalera (Universitat de Barcelona)
Thomas B. Moeslund (Aalborg Universitet)
Oral + poster
Multi-person Physics-based Pose Estimation for Combat SportsHossein Feizollah Zadeh Khoiee (École de technologie supérieure)
David Labbe (École de technologie supérieure)
Thomas Romeas (Université de Montréal )
Jocelyn faubert (Université de Montréal)
Sheldon Andrews (École de technologie supérieure)
Oral + poster
Human Mesh Reconstruction of Sports Players with Multiple Dynamic CamerasYamato Hokari (Keio University)
Ryosuke Hori (Keio University)
Hideo Saito (Keio University)
Oral + poster
SportMamba: Adaptive Non-Linear Multi-Object Tracking with State Space Models for Team SportsDheeraj Khanna (University of Waterloo)
Jerrin Bright (University of Waterloo)
Yuhao Chen (University of Waterloo)
John Zelek (University of Waterloo)
Oral + poster
TT3D: Table Tennis 3D ReconstructionThomas Gossard (Cognitive systems – University Tuebingen)
Andreas Ziegler (Cognitive systems – University Tuebingen)
Andreas Zell (Cognitive systems – University Tuebingen)
Poster
Efficient 2D to Full 3D Human Pose Uplifting including Joint RotationsKatja Ludwig (University of Augsburg)
Yuliia Oksymets (University of Augsburg)
Robin Schön (University of Augsburg)
Daniel Kienzle (University of Augsburg)
Rainer Lienhart (University of Augsburg)
Poster
Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body ShapesKatja Ludwig (University of Augsburg)
Julian Lorenz (University of Augsburg)
Daniel Kienzle (University of Augsburg)
Tuan Bui (University of Augsburg)
Rainer Lienhart (University of Augsburg)
Poster
VNL-STES: A Benchmark Dataset and Model for Spatiotemporal Event Spotting in Volleyball AnalyticsHoang Nguyen (University of Science and Technology)
Ankhzaya Jamsrandorj (Korea Institute of Science and Technology)
Vanyi Chao (University of Science and Technology)
Yin May Oo (University of Science and Technology)
Muhammad Amrulloh Robbani (University of Science and Technology)
Kyung-Ryoul Mun (Korea Institute of Science and Technology)
Jinwook Kim (Korea Institute of Science and Technology)
Poster
An End-to-End Pipeline for Virtual Banner Replacement in Football BroadcastsVictor Gaspar ( University of Liege)
Anthony Cioppa (University of Liège)
Jan Held (University of Liège)
Silvio Giancola (King Abdullah University of Science and technology (KAUST))
Marc Braham (University of Liège)
Adrien Deliège (University of Liège)
Bernard Ghanem (KAUST)
Marc Van Droogenbroeck (University of Liège)
Poster
FieldMOT: A Field-Registered Multi-Object Tracking for Sports VideosHong-Qi Chen (National Yang Ming Chiao Tung University)
Chao-Chi Liao (National Yang Ming Chiao Tung University)*
Yuan-Heng Sun (National Yang Ming Chiao Tung University)
Cheng-Kuan Lin (National Yang Ming Chiao Tung University)
Yu-Chee Tseng (National Yang Ming Chiao Tung University)
Poster
From Beats to Scores: A Multi-Modal Framework for Comprehensive Figure Skating AssessmentFengshun Wang (Institution of Artificial Intelligence in Sport in the Capital University of Physical Education and Sport)
Giurui Wang (Institution of Artificial Intelligence in Sport in the Capital University of Physical Education and Sport)
Dan Chen (School of Winter Sport in the Capital University of Physical Education and Sport)
Poster
Two Views Are Better than One: Monocular 3D Pose Estimation with Multiview ConsistencyChristian Ingwersen (TrackMan)
Rasmus Tirsgaard (Technical University of Denmark)
Rasmus Nylander (Trackman )
Janus Jensen (3Shape)
Anders Dahl (Technical University of Denmark)
Morten Hannemose (Technical University of Denmark)
Poster
Virtual Pose Coach: A Motion-Retargeting Approach for Pose TrainingTzu-Chun Chiu (National Yang Ming Chiao Tung University)
Ming-Han Lee (National Yang Ming Chiao Tung University)
Kun-Ru Wu (National Yang Ming Chiao Tung University)
Yu-Shuen Wang (National Yang Ming Chiao Tung University)
Yu-Chee Tseng (National Yang Ming Chiao Tung University)
Poster
Jump-Aware: Player Position Rectification and Identification in Dynamic Sports Using Jump Event SpottingYin May Oo (Korea Institute of Science and Technology)
Ankhzaya Jamsrandorj (Korea Institute of Science and Technology)
Vanyi Chao (Korea Institute of Science and Technology)
Hoang Quoc Nguyen ( Korea Institute of Science and Technology)
Yewon Hwang (Korea Institute of Science and Technology)
Kyung-Ryoul Mun (Korea Institute of Science and Technology)
Jinwook Kim (Korea Institute of Science and Technology)
Poster

AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements
Calvin Yeung (Nagoya University)
Tomohiro Suzuki (Nagoya University)
Ryota Tanaka (Nagoya University)
Zhuoer Yin (Nagoya University)
Keisuke Fujii (Nagoya University)
Poster
Towards fine-grained spatial control for soccer game image generationAmadou SANGARE (Télécom Paris, Institut Polytechnique de Paris)
Adrien MAGLO (CEA-List)
Baptiste ENGEL (CEA-List)
Mohamed CHAOUCH (CEA-List)
Poster
Skor-xG: SKeleton-ORiented Expected Goal Estimation in SoccerYizhou Xu (KTH Royal Institute of Technology)
Lars Bretzner (Tracab)
Tiesheng Wang (Tracab)
Atsuto Maki (KTH Royal Institute of Technology)
Poster
SoccerNet-v3D: Leveraging Sports Broadcast Replays for 3D Scene UnderstandingMarc Gutiérrez (Institut de Robòtica i Informàtica Industrial, CSIC-UPC)
Antonio Agudo (Institut de Robòtica i Informàtica Industrial, CSIC-UPC)
Poster
CaddieSet: A Golf Swing Dataset with Human Joint Features and Ball InformationSeunghyeon Jung (Dongguk University)
Seoyoung Hong (Kimcaddie Inc)
Jiwoo Jeong (Dongguk University)
Seungwon Jeong (Dongguk University)
Jaerim Choi (Kimcaddie Inc)
Hoki Kim (Chung-Ang University)
Woojin Lee (Dongguk University)
Poster
Sport Field Calibration with NeRF-guided Camera Optimization from a Single ImageLiang Fan (Loughborough University)
Xiaoqian Liu (Beijing Jiaotong University)
Malcolm Roberts (Irish Football Association)
Poster
GST: Precise 3D Human Body from a Single Image with Gaussian Splatting TransformersLorenza Prospero (University of Oxford)
Abdullah Hamdi (University of Oxford)
Joao Henriques (University of Oxford)
Christian Rupprecht (University of Oxford)
Poster
FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality AssessmentRuisheng Han (Department of Computer Science, Durham University)
Kanglei Zhou (Beihang University )
Amir Atapour-Abarghouei (Department of Computer Science, Durham University)
Xiaohui Liang (Beihang University)
Hubert Shum (Department of Computer Science, Durham University)
Poster
From Broadcast to Minimap: Achieving State-of-the-Art SoccerNet Game State ReconstructionVladimir Golovkin (Constructor Tech)
Nikolay Nemtsev (Constructor Tech)
Vasyl Shandyba (Constructor Tech)
Oleg Udin (Constructor Tech)
Nikita Kasatkin (Constructor Tech)
Pavel Kononov (Constructor Tech)
Anton Afanasiev (Constructor Tech)
Sergey Ulasen (Constructor Tech)
Andrei Boiarov (Constructor Tech)
Poster
No Train Yet Gain: Towards Generic Multi-Object Tracking in Sports and BeyondTomasz Stanczyk (Inria)
Seongro Yoon (Inria)
Francois Bremond (Inria)
Poster
Ice Hockey Puck Localization Using Contextual CuesLiam Salass (University of Waterloo)
Jerrin Bright (University of Waterloo)
Amir Nazemi (University of Waterloo)
Yuhao Chen (University of Waterloo)
John Zelek (University of Waterloo)
David Clausi (University of Waterloo)
Poster
Can Geometry Save Central Views for Sports Field Registration?Floriane Magera (EVS Broadcast Equipment)
Thomas Hoyoux (EVS Broadcast Equipment)
Martin Castin (EVS Broadcast Equipment)
Olivier Barnich (EVS Broadcast Equipment)
Anthony Cioppa (University of Liege)
Marc Van Droogenbroeck (University of Liege)
Poster
Pose-to-Pose: A New Task and Benchmark for Human Pose Transition in YogaBhat Dittakavi (Indian Institute of Technology, Hyderabad)
Swarnim Maheshwari (IIT Hyderabad)
Vineeth N Balasubramanian (Indian Institute of Technology, Hyderabad)
Poster
Single-Stage Uncertainty-Aware Jersey Number Recognition in SoccerŁukasz Grad (University of Warsaw)Poster
Domain Adaptation of VLM for Soccer Video UnderstandingTiancheng Jiang (Massachusetts Institute of Technology)
Henry Wang (Amazon Web Services)
Sirajus Salekin (Amazon Web Services)
Shinan Zhang (Amazon Web Services)
Parmida Atighehchian (Amazon Web Services)
Poster
Where Is The Ball: 3D Ball Trajectory Estimation From 2D Monocular TrackingPuntawat Ponglertnapakorn (Vidyasirimedhi Institute of Science and Technology)
Supasorn Suwajanakorn (VISTEC: Vidyasirimedhi Institute of Science and Technology)
Poster
Action Valuation in Sports: A SurveyArtur Xarles (Universitat de Barcelona)
Sergio Escalera (Universitat de Barcelona)
Thomas B. Moeslund (Aalborg University)
Albert Clapés (Universitat de Barcelona)
Poster
Polar Coordinate-Based 2D Pose Prior with Neural Distance FieldQi Gan (Télécom Paris)
Sao Mai Nguyen (ENSTA Paris)
Eric Fenaux (Ef-e-science)
Stephan Clémençon (Télécom Paris)
Mounim EL YACOUBI (Télécom SudParis)
Poster
The Way Up: A Dataset for Hold Usage Detection in Sport ClimbingAnna Maschek (University of Applied Sciences Upper Austria)
David Schedl (University of Applied Sciences Upper Austria)
Poster
Towards Unconstrained 2D Pose Estimation of the Human SpineMuhammad Saif Ullah Khan (Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI))
Stephan Krauß (Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI))
Didier Stricker (DeutschesForschungszentrum für Künstliche Intelligenz (DFKI))
Poster

Call for Papers

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 understanding of sport injuries, coaching, and enhanced viewing. So far, the use of computer vision in sports has been scattered between different disciplines.
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)
  • tactics analysis in sports
  • automatic narration and captioning in sports
  • training assistance in sports
  • augmented/virtual reality in sports
  • datasets in sports
  • bias in sports
  • XAI in sports
  • ethics & algorithms in sports

Important dates

Submission deadline: March 5 Extended: March 11, 2025 (Anywhere on Earth)

Notification: March 25 27, 2025

Camera ready deadline: April 5 14, 2025 (hard deadline)

Submission

Paper submission: https://cmt3.research.microsoft.com/CVsports2025/

Author guidelines: Please follow the guidelines from CVPR main conference: https://cvpr.thecvf.com/Conferences/2025/AuthorGuidelines

Please note the following: Papers that are not properly anonymized, or do not use the template, or have more than eight pages (excluding references) will be rejected without review

Competition – SoccerNet

Participate in our 2025 SoccerNet challenges and explore research in sports video analysis!

This year’s tasks include: Ball action spotting, Game state reconstruction, Multi-view foul recognition, Monocular depth estimation.

Read more about the challenges: https://www.soccer-net.org/challenges/2025

Sponsors:

Organizers

Previous editions of CVsports