R2D-RL: A RoboCup 2D Soccer Environment for Multi-Agent Reinforcement Learning

Robot soccer is a challenging testbed for multi-agent reinforcement learning because it combines partial observability, cooperative and adversarial interaction, sparse rewards, and long-horizon tactical behavior. RoboCup 2D Soccer Simulation (RCSS2D) provides a mature robot-soccer platform, but its competition-oriented server-client architecture is difficult to use directly with modern Python-based MARL workflows. We introduce R2D-RL, a reinforcement learning environment that connects RCSS2D and HELIOS-based player clients to a Python MARL interface through shared-memory communication and cycle-level synchronization. R2D-RL supports full-field and scenario-based training with configurable opponents, Base discrete and Hybrid parameterized action spaces, action masks, expected possession value (EPV)-based reward shaping, and parallel execution. We provide front-goal scenarios and an 11-vs-11 full-field benchmark, together with baseline results.

Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA

Recent advances in video multimodal models have significantly improved VideoQA performance. However, these systems often rely on spurious statistical correlations rather than answer-relevant causal evidence, resulting in unfaithful and brittle reasoning, especially in complex real-world scenarios. Existing methods either rely on cross-modality correlations, costly curated training resources, or insufficient causal assumptions and constraints, and typically operate at the time-interval level. As a result, they fail to explicitly disentangle causal visual cues from confounders and provide limited fine-grained evidence localization. To address this issue, we propose a Counterfactual Reasoning framework for fine-grained Evidence Disentanglement (CREDiT). CREDiT formulates the VideoQA process using a structural causal model and learns cross-modality representations that are explicitly decomposed into causal and non-causal components under independence and minimality constraints. To facilitate faithful disentanglement, we introduce feature-level causal interventions and construct counterfactual inputs that approximate causal effects while suppressing non-causal correlations. Extensive experiments on NExT-GQA, SportsQA, and SPORTU-video demonstrate that CREDiT consistently improves answer accuracy and reasoning reliability across both generic and complex sports scenarios, leading to more trustworthy VideoQA systems.

Mesh-Aware Epipolar Matching for Multi-View Multi-Person 3D Pose Estimation in Basketball

Multi-view multi-person 3D pose estimation in team sports scenarios remains challenging due to player occlusions, appearance similarity caused by team uniforms, and the scarcity of annotated multi-view data, all of which limit the effectiveness and generalization capability of learning-based methods. In contrast, the performance of training-free approaches is inherently constrained by the accuracy of 2D keypoint detection and the robustness of cross-view association. To address these challenges, we propose Mesh-Aware Epipolar Matching (MAEM), a training-free framework for multi-view multi-person 3D pose estimation. Our method employs a monocular 3D human mesh recovery model as the frontend and introduces a two-stage epipolar matching strategy based on the recovered mesh outputs. Specifically, the proposed framework combines disjoint-set-union-based clustering with per-joint triangulation to achieve robust cross-view association and accurate 3D pose reconstruction. Experiments on two public multi-view basketball datasets demonstrate that MAEM consistently outperforms existing training-free association baselines while achieving competitive RGB-only performance in both indoor and outdoor basketball scenarios. MAEM achieves MPJPE/PA-MPJPE scores of 59.8/40.7 mm on SportCenter EPFL and 74.0/51.8 mm on Human-M3 Basketball, highlighting the effectiveness of dense mesh geometry for cross-view association without requiring target-domain training or fine-tuning.

BFMD: A Full-Match Badminton Dense Dataset for Dense Shot Captioning

Understanding tactical dynamics in badminton requires analyzing entire matches rather than isolated clips. However, existing badminton datasets mainly focus on short clips or task-specific annotations and rarely provide full-match data with dense multimodal annotations. This limitation makes it difficult to generate accurate shot captions and perform match-level analysis. To address this limitation, we introduce the first Badminton Full Match Dense (BFMD) dataset, with 19 broadcast matches (including both singles and doubles) covering over 20 hours of play, comprising 1,687 rallies and 16,751 hit events, each annotated with a shot caption. The dataset provides hierarchical annotations including match segments, rally events, and dense rally-level multimodal annotations such as shot types, shuttle trajectories, player pose keypoints, and shot captions. We develop a VideoMAE-based multimodal captioning framework with a Semantic Feedback mechanism that leverages shot semantics to guide caption generation and improve semantic consistency. Experimental results demonstrate that multimodal modeling and semantic feedback improve shot caption quality over RGB-only baselines. We further showcase the potential of BFMD by analyzing the temporal evolution of tactical patterns across full matches.

Expandable Decision-Making States for Multi-Agent Deep Reinforcement Learning in Soccer Tactical Analysis

Invasion team sports such as soccer produce a high-dimensional, strongly coupled state space as many players continuously interact on a shared field, challenging quantitative tactical analysis. Traditional rule-based analyses are intuitive, while modern predictive machine learning models often perform pattern-matching without explicit agent representations. The problem we address is how to build player-level agent models from data, whose learned values and policies are both tactically interpretable and robust across heterogeneous data sources. Here, we propose Expandable Decision-Making States (EDMS), a semantically enriched state representation that augments raw positions and velocities with relational variables (e.g., scoring of space, pass, and score), combined with an action-masking scheme that gives on-ball and off-ball agents distinct decision sets. Compared to prior work, EDMS maps learned value functions and action policies to human-interpretable tactical concepts (e.g., marking pressure, passing lanes, ball accessibility) instead of raw coordinate features, and aligns agent choices with the rules of play. In the experiments, EDMS with action masking consistently reduced both action-prediction loss and temporal-difference (TD) error compared to the baseline. Qualitative case studies and Q-value visualizations further indicate that EDMS highlights high-risk, high-reward tactical patterns (e.g., fast counterattacks and defensive breakthroughs). We also integrated our approach into an open-source library and demonstrated compatibility with multiple commercial and open datasets, enabling cross-provider evaluation and reproducible experiments.

Evaluating Movement Initiation Timing in Ultimate Frisbee via Temporal Counterfactuals

Ultimate is a sport where points are scored by passing a disc and catching it in the opposing team's end zone. In Ultimate, the player holding the disc cannot move, making field dynamics primarily driven by other players' movements. However, current literature in team sports has ignored quantitative evaluations of when players initiate such unlabeled movements in game situations. In this paper, we propose a quantitative evaluation method for movement initiation timing in Ultimate Frisbee. First, game footage was recorded using a drone camera, and players' positional data was obtained, which will be published as UltimateTrack dataset. Next, players' movement initiations were detected, and temporal counterfactual scenarios were generated by shifting the timing of movements using rule-based approaches. These scenarios were analyzed using a space evaluation metric based on soccer's pitch control reflecting the unique rules of Ultimate. By comparing the spatial evaluation values across scenarios, the difference between actual play and the most favorable counterfactual scenario was used to quantitatively assess the impact of movement timing. We validated our method and show that sequences in which the disc was actually thrown to the receiver received higher evaluation scores than the sequences without a throw. In practical verifications, the higher-skill group displays a broader distribution of time offsets from the model's optimal initiation point. These findings demonstrate that the proposed metric provides an objective means of assessing movement initiation timing, which has been difficult to quantify in unlabeled team sport plays.

VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentation

Understanding human actions from videos plays a critical role across various domains, including sports analytics. In figure skating, accurately recognizing the type and timing of jumps a skater performs is essential for objective performance evaluation. However, this task typically requires expert-level knowledge due to the fine-grained and complex nature of jump procedures. While recent approaches have attempted to automate this task using Temporal Action Segmentation (TAS), there are two major limitations to TAS for figure skating: the annotated data is insufficient, and existing methods do not account for the inherent three-dimensional aspects and procedural structure of jump actions. In this work, we propose a new TAS framework for figure skating jumps that explicitly incorporates both the three-dimensional nature and the semantic procedure of jump movements. First, we propose a novel View-Invariant, Figure Skating-Specific pose representation learning approach (VIFSS) that combines contrastive learning as pre-training and action classification as fine-tuning. For view-invariant contrastive pre-training, we construct FS-Jump3D, the first publicly available 3D pose dataset specialized for figure skating jumps. Second, we introduce a fine-grained annotation scheme that marks the ``entry (preparation)'' and ``landing'' phases, enabling TAS models to learn the procedural structure of jumps. Extensive experiments demonstrate the effectiveness of our framework. Our method achieves over 92% F1@50 on element-level TAS, which requires recognizing both jump types and rotation levels. Furthermore, we show that view-invariant contrastive pre-training is particularly effective when fine-tuning data is limited, highlighting the practicality of our approach in real-world scenarios.

KASportsFormer: Kinematic Anatomy Enhanced Transformer for 3D Human Pose Estimation on Short Sports Scene Video

Recent transformer based approaches have demonstrated impressive performance in solving real-world 3D human pose estimation problems. Albeit these approaches achieve fruitful results on benchmark datasets, they tend to fall short of sports scenarios where human movements are more complicated than daily life actions, as being hindered by motion blur, occlusions, and domain shifts. Moreover, due to the fact that critical motions in a sports game often finish in moments of time (e.g., shooting), the ability to focus on momentary actions is becoming a crucial factor in sports analysis, where current methods appear to struggle with instantaneous scenarios. To overcome these limitations, we introduce KASportsFormer, a novel transformer based 3D pose estimation framework for sports that incorporates a kinematic anatomy-informed feature representation and integration module. In which the inherent kinematic motion information is extracted with the Bone Extractor (BoneExt) and Limb Fuser (LimbFus) modules and encoded in a multimodal manner. This improved the capability of comprehending sports poses in short videos. We evaluate our method through two representative sports scene datasets: SportsPose and WorldPose. Experimental results show that our proposed method achieves state-of-the-art results with MPJPE errors of 58.0mm and 34.3mm, respectively. Our code and models are available at: https://github.com/jw0r1n/KASportsFormer

Velocity Completion Task and Method for Event-based Player Positional Data in Soccer

In many real-world complex systems, the behavior can be observed as a collection of discrete events generated by multiple interacting agents. Analyzing the dynamics of these multi-agent systems, especially team sports, often relies on understanding the movement and interactions of individual agents. However, while providing valuable snapshots, event-based positional data typically lacks the continuous temporal information needed to directly calculate crucial properties such as velocity. This absence severely limits the depth of dynamic analysis, preventing a comprehensive understanding of individual agent behaviors and emergent team strategies. To address this challenge, we propose a new method to simultaneously complete the velocity of all agents using only the event-based positional data from team sports. Based on this completed velocity information, we investigate the applicability of existing team sports analysis and evaluation methods. Experiments using soccer event data demonstrate that neural network-based approaches outperformed rule-based methods regarding velocity completion error, considering the underlying temporal dependencies and graph structure of player-to-player or player-to-ball interaction. Moreover, the space evaluation results obtained using the completed velocity are closer to those derived from complete tracking data, highlighting our method's potential for enhanced team sports system analysis.

Automating quantum feature map design via large language models

Quantum feature maps are a key component of quantum machine learning, encoding classical data into quantum states to exploit the expressive power of high-dimensional Hilbert spaces. Despite their theoretical promise, designing quantum feature maps that offer practical advantages over classical methods remains an open challenge. In this work, we propose an agentic system that autonomously generates, evaluates, and refines quantum feature maps using large language models. The system consists of five component: Generation, Storage, Validation, Evaluation, and Review. Using these components, it iteratively improves quantum feature maps. Experiments on the MNIST dataset show that it can successfully discover and refine feature maps without human intervention. The best feature map generated outperforms existing quantum baselines and achieves competitive accuracy compared to classical kernels across MNIST, Fashion-MNIST, and CIFAR-10. Our approach provides a framework for exploring dataset-adaptive quantum features and highlights the potential of LLM-driven automation in quantum algorithm design.