SoccerNet 2023 Challenges Results
arXiv:2309.06006 · doi:10.1007/s12283-024-00466-4
Abstract
The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.
References in corpus (19)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- YOLOX: Exceeding YOLO Series in 2021
- Flamingo: a Visual Language Model for Few-Shot Learning
- HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
- SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos
- Body Part-Based Representation Learning for Occluded Person Re-Identification
- SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos
- SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries
- DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
- VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views
- SoccerNet 2022 Challenges Results
- CLIP-ReIdent: Contrastive Training for Player Re-Identification
- Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection
- Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking
- MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors
- SoccerNet 2023 Tracking Challenge -- 3rd place MOT4MOT Team Technical Report
- A Boosted Model Ensembling Approach to Ball Action Spotting in Videos: The Runner-Up Solution to CVPR'23 SoccerNet Challenge