- SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap, CVPRW'24 [Paper]
- Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking, ACM MMSports'23 [Paper]
- SoccerNet 2022 Challenges Results, ACM MMSports'22 [Paper]
- DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations, ACM MMSports'22 [Paper]
- LoL-V2T: Large-Scale Esports Video Description Dataset, CVPRW'21 [Paper]
- Contrastive Learning for Sports Video: Unsupervised Player Classification, CVPRW'21 [Paper]
- Automated Tackle Injury Risk Assessment in Contact-Based Sports - A Rugby Union Example, CVPRW'21 [Paper]
- Toward Improving the Visual Characterization of Sport Activities With Abstracted Scene Graphs, CVPRW'21 [Paper]
- Detecting and Matching Related Objects With One Proposal Multiple Predictions, CVPRW'21 [Paper]
- SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos, CVPRW'21 [Paper]
- Table Tennis Stroke Recognition Using Two-Dimensional Human Pose Estimation, CVPRW'21 [Paper]
- Puck Localization and Multi-Task Event Recognition in Broadcast Hockey Videos, CVPRW'21 [Paper]
- Automatic Play Segmentation of Hockey Videos, CVPRW'21 [Paper]
- DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts Using a Single Camera, CVPRW'21 [Paper]
- Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of Their Representations for Action Spotting, CVPRW'21 [Paper]
-
Actor-Transformers for Group Activity Recognition, CVPR'20 [Paper]
-
Progressive Relation Learning for Group Activity Recognition, CVPR'20 [Paper]
-
Group Activity Detection from Trajectory and Video Data in Soccer, CVPRW'20 [Paper]
-
FALCONS: FAst Learner-grader for CONtorted poses in Sports, CVPRW'20 [Paper]
-
As Seen on TV: Automatic Basketball Video Production using Gaussian-based Actionness and Game States Recognition, CVPRW'20 [Paper]
-
Decoupling Video and Human Motion: Towards Practical Event Detection in Athlete Recordings, CVPRW'20 [Paper]
-
Utilizing Mask R-CNN for Waterline Detection in Canoe Sprint Video Analysis, CVPRW'20 [Paper]
-
TTNet: Real-time temporal and spatial video analysis of table tennis, CVPRW'20 [Paper]
- Learning Actor Relation Graphs for Group Activity Recognition, CVPR'19 [Paper]
-
Soccer on Your Tabletop, CVPR'18 [Paper]
-
Egocentric Basketball Motion Planning From a Single First-Person Image, CVPR'18 [Paper]
-
Towards Structured Analysis of Broadcast Badminton Videos, WACV'18 [Paper]
-
Fine-grained Activity Recognition in Baseball Videos, CVPRW'18 [Paper]
-
Where Will They Go? Predicting Fine-Grained Adversarial Multi-Agent Motion using Conditional Variational Autoencoders, ECCV'18 [Paper]
-
Fine-grained Video Captioning for Sports Narrative, ECCV'18 [Paper]
-
What will Happen Next? Forecasting Player Moves in Sports Videos, ICCV'17 [Paper]
-
Not all passes are created equal: Objectively measuring the risk and reward of passes in soccer from tracking data, SIGKDD'17 [Paper]
-
SmartTennisTV: An automatic indexing system for tennis, NCVPRIPG'17 [Paper]
-
Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition, CVPR'17 [Paper]
-
Coordinated Multi-Agent Imitation Learning, ICML'17 [Paper]
-
Chalkboarding: A new spatiotemporal query paradigm for sports play retrieval, ACM IUI'16 [Paper]
-
What players do with the ball: a physically constrained interaction modeling, CVPR'16 [Paper]
-
Generating long-term trajectories using deep hierarchical networks, NIPS'16 [Paper]
-
Detecting Events and Key Actors in Multi-Person Videos, CVPR'16 [Paper]
-
Mimicking human camera operators, WACV'15 [Paper]
-
Quality vs Quantity”- Improved Shot Prediction in Soccer using Strategic Features from Spatiotemporal Data-Paper, MIT Sloan Sports Analytics Conference'15 [Paper]
- How to get an open shot: Analyzing team movement in basketball using tracking data, MIT SLOAN'14 [Paper]
-
Take your eyes off the ball: Improving ball-tracking by focusing on team play, CVIU'13 [Paper]
-
Detecting and tracking sports players with random forests and context-conditioned motion models, CVPR'13 [Paper]
-
Representing and discovering adversarial team behaviors using player roles, CVPR'13 [Paper]
-
Recognising team activities from noisy data, CVPRW'13 [Paper]
- Point-less calibration: Camera parameters from gradient-based alignment to edge images, WACV'12 [Paper]
[1] Volleyball Dataset [Link]