Bikash Kumar Badatya

Rahul Kumar, Vipul Baghel, Sudhanshu Singh et al.

Accurate analysis of combat sports using computer vision has gained traction in recent years, yet the development of robust datasets remains a major bottleneck due to the dynamic, unstructured nature of actions and variations in recording environments. In this work, we present a comprehensive, well-annotated video dataset tailored for punch detection and classification in boxing. The dataset comprises 6,915 high-quality punch clips categorized into six distinct punch types, extracted from 20 publicly available YouTube sparring sessions and involving 18 different athletes. Each clip is manually segmented and labeled to ensure precise temporal boundaries and class consistency, capturing a wide range of motion styles, camera angles, and athlete physiques. This dataset is specifically curated to support research in real-time vision-based action recognition, especially in low-resource and unconstrained environments. By providing a rich benchmark with diverse punch examples, this contribution aims to accelerate progress in movement analysis, automated coaching, and performance assessment within boxing and related domains.

Bikash Kumar Badatya, Vipul Baghel, Jyotirmoy Amin et al.

Precise analysis of athletic motion is central to sports analytics, particularly in disciplines where nuanced biomechanical phases directly impact performance outcomes. Traditional analytics techniques rely on manual annotation or laboratory-based instrumentation, which are time-consuming, costly, and lack scalability. Automatic extraction of relevant kinetic variables requires a robust and contextually appropriate temporal segmentation. Considering the specific case of elite javelin-throw, we present a novel unsupervised framework for such a contextually aware segmentation, which applies the structured optimal transport (SOT) concept to augment the well-known Attention-based Spatio-Temporal Graph Convolutional Network (ASTGCN). This enables the identification of motion phase transitions without requiring expensive manual labeling. Extensive experiments demonstrate that our approach outperforms state-of-the-art unsupervised methods, achieving 71.02% mean average precision (mAP) and 74.61% F1-score on test data, substantially higher than competing baselines. We also release a new dataset of 211 manually annotated professional javelin-throw videos with frame-level annotations, covering key biomechanical phases: approach steps, drive, throw, and recovery.

Bikash Kumar Badatya, Vipul Baghel, Ravi Hegde

Fine-grained action localization in untrimmed sports videos presents a significant challenge due to rapid and subtle motion transitions over short durations. Existing supervised and weakly supervised solutions often rely on extensive annotated datasets and high-capacity models, making them computationally intensive and less adaptable to real-world scenarios. In this work, we introduce a lightweight and unsupervised skeleton-based action localization pipeline that leverages spatio-temporal graph neural representations. Our approach pre-trains an Attention-based Spatio-Temporal Graph Convolutional Network (ASTGCN) on a pose-sequence denoising task with blockwise partitions, enabling it to learn intrinsic motion dynamics without any manual labeling. At inference, we define a novel Action Dynamics Metric (ADM), computed directly from low-dimensional ASTGCN embeddings, which detects motion boundaries by identifying inflection points in its curvature profile. Our method achieves a mean Average Precision (mAP) of 82.66% and average localization latency of 29.09 ms on the DSV Diving dataset, matching state-of-the-art supervised performance while maintaining computational efficiency. Furthermore, it generalizes robustly to unseen, in-the-wild diving footage without retraining, demonstrating its practical applicability for lightweight, real-time action analysis systems in embedded or dynamic environments.