June 4. Room: 503.
| 6.00-7.00 Optional | 5-10 km run around Denver | Join the WhatsApp group for more information: https://chat.whatsapp.com/F50JX2E8XWl0BbsRCIP4bW?mode=gi_t | CVsports organizers |
| 9.00-9.05 | Welcome | CVsports organizers | |
| 9.05-9.45 | Invited talk | Analyzing Soccer Actions and Tactics by Learning and Reasoning | Maaike van Roy, KU Leuven |
| 9.45-10.00 | Oral presentation | BFMD: A Full-Match Badminton Dense Dataset for Dense Shot Captioning | Ning Ding |
| 10.00-10.15 | Oral presentation | BlurBall: Joint Ball and Motion Blur Estimation for Table Tennis Ball Tracking | Thomas Gossard |
| 10.15-10.30 | Oral presentation | Beyond Pedestrians: Caption-Guided CLIP Framework for High-Difficulty Video-based Person Re-Identification | Shogo Hamano |
| 10.30-10.50 | Coffee break | ||
| 10.50-11.30 | Invited talk | When Sports CV Leaves the Lab: Lessons on Bridging Academia and Industry | Atom Scott, Playbox Inc |
| 11.30-11.45 | Oral presentation | Game Context-Aware 3D Human Mesh Recovery in Ice Hockey | Zhibo Wang |
| 11.45-12.00 | Oral presentation | Transition-Constrained Sequence Modeling for Fine-Grained Skating Action Recognition | Maria Koshkina |
| 12.00-13.10 | Lunch break | ||
| 13.10-13.50 | Invited talk | From Tracking to Understanding: The Next Decade of Computer Vision in Sports | Christina Chase, MIT |
| 13.50-14.20 | Poster spotlights | 1.5 min. each | See table below for paper titles |
| 14.20-15.55 | Poster session + coffee | Poster boards 81-94 in Exhibit Hall A | See table below |
| 16.00-16.40 | Invited talk | FIFA Research – Case Studies and Research Highlights | Johsan Billingham, FIFA |
| 16.40-17.15 | SoccerNet | Results and talks from SoccerNet challenges 2026 | SoccerNet organizers and authors |
| 17.15-17.30 | Best paper award and closing remarks | Best paper award sponsored by FIFA | CVsports organizers |
Accepted peer-reviewed papers:
NB: Each poster board is shared by two posters.
| Graph-based Association for Multi-View Multiple Player 3D Tracking in Volleyball Videos | Yu-Hsiang Chen, Wei-Ta Chu, Takeo Kanade | Poster #81 + spotlight |
| Pole-Arina: A Privacy-Preserving Dataset and Benchmark for Static Pole Tricks | Diana Marin, Katharina Scheucher, Peter Kán | Poster #81 + spotlight |
| BFMD: A Full-Match Badminton Dense Dataset for Dense Shot Captioning | Ning Ding, Keisuke Fujii, Toru Tamaki | Oral + poster #82 |
| BlurBall: Joint Ball and Motion Blur Estimation for Table Tennis Ball Tracking | Thomas Gossard, Andreas Ziegler, Filip Radovic, Andreas Zell | Oral + poster #82 |
| BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports | Jing-Yuan Chang | Poster #83 + spotlight |
| Beyond Pedestrians: Caption-Guided CLIP Framework for High-Difficulty Video-based Person Re-Identification | Shogo Hamano, Shunya Wakasugi, Tatsuhito Sato, Sayaka Nakamura | Oral + poster #83 |
| GRAZE: Grounded Refinement and Motion-Aware Zero-Shot Event Localization | Syed Ahsan Masud Zaidi, Lior Shamir, William Hsu, Scott Dietrich, Talha Zaidi | Poster #84 + spotlight |
| PlayGen-MoG: Framework for Diverse Multi-Agent Play Generation via Mixture-of-Gaussians Trajectory Prediction | Kevin Changhun Song | Poster #84 + spotlight |
| Pixels or Positions? Benchmarking Modalities in Group Activity Recognition | Drishya Karki, Merey Ramazanova, Anthony Cioppa, Silvio Giancola, Bernard Ghanem | Poster #85 + spotlight |
| LTPI: A Benchmark for Long-term Player Identification from Single-Camera Football Video | Murad Dusov, Vasiliy Chelpanov, Andrey Sakhovskiy, Vadim Linkov, Oleg Durygin, Mikhail Moiseev, Isupov Matvey, Konstantin Mitin, Semen Budennyy | Poster #85 + spotlight |
| SetPieceRAG: Domain-Specific RAG for Knowledge-Intensive Soccer VQA with Large Language Models | Youngseon Kim, Jongmin Lee | Poster #86 + spotlight |
| 3D Reconstruction of American Football Game Situations from Handheld Monocular Video | Kanta Sawafuji, Rintaro Otsubo, Dan Mikami, Hideo Saito | Poster #86 + spotlight |
| SAMIDARE: Advanced Tracking-by-Segmentation for Dense Scenarios | Shozaburo Hirano, Norimichi Ukita | Poster #87 + spotlight |
| Direct Measurement of Human Joint Positions under Clothing using Coaxial RGB–Infrared Imaging | Daishi Kitano, Seiji Matsumura, Naoki Saijo, Makio Kashino, Dan Mikami | Poster # 87 + spotlight |
| CADDIE: Compact Adaptive Detection-Driven Inference for Real-Time Golf Club Pose Estimation | Changsoo Jung, Fan Yang, Nathaniel Blanchard, Hon Yung Wong | Poster #88 + spotlight |
| Unified Sports Field Registration with Lens Distortion Modeling | Jonas Theiner, Eric Müller-Budack, Ralph Ewerth | Poster #88 + spotlight |
| Monte Carlo Pass Search: Using Trajectory Generation for 3D Counterfactual Pass Evaluation in Football | Andrew Kang, Priya Narasimhan | Poster #89 + spotlight |
| Non-Intrusive Monocular 3D Ball Tracking via Infrared Shadow Geometry for Practical Sports Applications | Hiro Horino, Daishi Kitano, Dan Mikami | Poster #89 + spotlight |
| CausalMAT: Counterfactual Trajectory Reasoning in Multi-Agent Sports | Ben Jenkins | Poster #90 + spotlight |
| Physics-Based 3D Ball Trajectory Reconstruction from Monocular Soccer Video: A Multi-Model Benchmark | Łukasz Grad, Krzysztof M. Czajkowski, Aliaksandr Varashylau | Poster #90 + spotlight |
| Towards Athlete Fatigue Assessment from Association Football Videos | Xavier Bou, Nathan Correger, Alexandre Cloots, Gavage Cédric, Silvio Giancola, Cédric Schwartz, François Delvaux, Rudi Cloots, Marc Van Droogenbroeck, Anthony Cioppa | Poster #91 + spotlight |
| Scalable Injury-Risk Screening in Baseball Pitching From Broadcast Video | Jerrin Bright, Justin Mende, John S. Zelek | Poster #92 + spotlight |
| Interpretable Pre-Release Baseball Pitch Type Anticipation from Broadcast 3D Kinematics | Jerrin Bright, Michelle Lu, John S. Zelek | Poster #92 + spotlight |
| Game Context-Aware 3D Human Mesh Recovery in Ice Hockey | Zhibo Wang, Amir Nazemi, Sirisha Rambhatla, Yuhao Chen, David A. Clausi | Oral + poster #91 |
| Transition-Constrained Sequence Modeling for Fine-Grained Skating Action Recognition | Maria Koshkina, Tanmay Pilla, Amir Nazemi, Yuhao Chen, John S. Zelek, David A. Clausi | Oral + poster #93 |
Nectar track posters – papers accepted for CVPR main conference:
| SkillSight: Efficient First-Person Skill Assessment with Gaze | Chi Hsuan Wu, Kumar Ashutosh, Kristen Grauman | Poster #93 |
| AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting | Artur Xarles, Sergio Escalera, Thomas B. Moeslund, Albert Clapés | Poster #94 |
| VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition | Tanush Yadav, Reza Salehi, Jae Sung Park, Vivek Ramanujan, Hannaneh Hajishirzi, Yejin Choi, Ali Farhadi, Rohun Tripathi, Ranjay Krishna | Poster #94 |