SoccerNet 2025 Challenges Results

The SoccerNet 2025 Challenges mark the fifth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in football video understanding. This year's challenges span four vision-based tasks: (1) Team Ball Action Spotting, focused on detecting ball-related actions in football broadcasts and assigning actions to teams; (2) Monocular Depth Estimation, targeting the recovery of scene geometry from single-camera broadcast clips through relative depth estimation for each pixel; (3) Multi-View Foul Recognition, requiring the analysis of multiple synchronized camera views to classify fouls and their severity; and (4) Game State Reconstruction, aimed at localizing and identifying all players from a broadcast video to reconstruct the game state on a 2D top-view of the field. Across all tasks, participants were provided with large-scale annotated datasets, unified evaluation protocols, and strong baselines as starting points. This report presents the results of each challenge, highlights the top-performing solutions, and provides insights into the progress made by the community. The SoccerNet Challenges continue to serve as a driving force for reproducible, open research at the intersection of computer vision, artificial intelligence, and sports. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet.

Utilizing Reinforcement Learning for Bottom-Up part-wise Reconstruction of 2D Wire-Frame Projections

This work concerns itself with the task of reconstructing all edges of an arbitrary 3D wire-frame model projected to an image plane. We explore a bottom-up part-wise procedure undertaken by an RL agent to segment and reconstruct these 2D multipart objects. The environment's state is represented as a four-colour image, where different colours correspond to background, a target edge, a reconstruction line, and the overlap of both. At each step, the agent can transform the reconstruction line within a four-dimensional action space or terminate the episode using a specific termination action. To investigate the impact of reward function formulations, we tested episodic and incremental rewards, as well as combined approaches. Empirical results demonstrated that the latter yielded the most effective training performance. To further enhance efficiency and stability, we introduce curriculum learning strategies. First, an action-based curriculum was implemented, where the agent was initially restricted to a reduced action space, being able to only perform three of the five possible actions, before progressing to the full action space. Second, we test a task-based curriculum, where the agent first solves a simplified version of the problem before being presented with the full, more complex task. This second approach produced promising results, as the agent not only successfully transitioned from learning the simplified task to mastering the full task, but in doing so gained significant performance. This study demonstrates the potential of an iterative RL wire-frame reconstruction in two dimensions. By combining optimized reward function formulations with curriculum learning strategies, we achieved significant improvements in training success. The proposed methodology provides an effective framework for solving similar tasks and represents a promising direction for future research in the field.

Using deep neural networks to detect non-analytically defined expert event labels in canoe sprint force sensor signals

Assessing an athlete's performance in canoe sprint is often established by measuring a variety of kinematic parameters during training sessions. Many of these parameters are related to single or multiple paddle stroke cycles. Determining on- and offset of these cycles in force sensor signals is usually not straightforward and requires human interaction. This paper explores convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in terms of their ability to automatically predict these events. In addition, our work proposes an extension to the recently published SoftED metric for event detection in order to properly assess the model performance on time windows. In our results, an RNN based on bidirectional gated recurrent units (BGRUs) turned out to be the most suitable model for paddle stroke detection.

Assessment of deep learning based blood pressure prediction from PPG and rPPG signals

Exploiting photoplethysmography signals (PPG) for non-invasive blood pressure (BP) measurement is interesting for various reasons. First, PPG can easily be measured using fingerclip sensors. Second, camera-based approaches allow to derive remote PPG (rPPG) signals similar to PPG and therefore provide the opportunity for non-invasive measurements of BP. Various methods relying on machine learning techniques have recently been published. Performances are often reported as the mean average error (MAE) on the data which is problematic. This work aims to analyze the PPG- and rPPG-based BP prediction error with respect to the underlying data distribution. First, we train established neural network (NN) architectures and derive an appropriate parameterization of input segments drawn from continuous PPG signals. Second, we apply this parameterization to a larger PPG dataset and train NNs to predict BP. The resulting prediction errors increase towards less frequent BP values. Third, we use transfer learning to train the NNs for rPPG based BP prediction. The resulting performances are similar to the PPG-only case. Finally, we apply a personalization technique and retrain our NNs with subject-specific data. This slightly reduces the prediction errors.

Utilizing Mask R-CNN for Waterline Detection in Canoe Sprint Video Analysis

Determining a waterline in images recorded in canoe sprint training is an important component for the kinematic parameter analysis to assess an athlete's performance. Here, we propose an approach for the automated waterline detection. First, we utilized a pre-trained Mask R-CNN by means of transfer learning for canoe segmentation. Second, we developed a multi-stage approach to estimate a waterline from the outline of the segments. It consists of two linear regression stages and the systematic selection of canoe parts. We then introduced a parameterization of the waterline as a basis for further evaluations. Next, we conducted a study among several experts to estimate the ground truth waterlines. This not only included an average waterline drawn from the individual experts annotations but, more importantly, a measure for the uncertainty between individual results. Finally, we assessed our method with respect to the question whether the predicted waterlines are in accordance with the experts annotations. Our method demonstrated a high performance and provides opportunities for new applications in the field of automated video analysis in canoe sprint.