Scholarlink

<p>Human action recognition in close-contact sports is hindered by mutual occlusion, rapid pose changes, and distracting backgrounds. We study freestyle wrestling—a representative close-contact setting with sustained physical interaction—and present the Open FSW dataset of 210 trimmed clips covering seven techniques (30 clips per class), sourced from both controlled training sessions and broadcast footage. We introduce a foreground-aware RGB pipeline that segments athletes with a fine-tuned DeepLabV3+ model, extracts per-frame features using CNN backbones (VGG16, InceptionV3, EfficientNet-B7), and aggregates them with a bidirectional LSTM to produce clip-level predictions. Under a group-aware six-fold cross-validation protocol stratified by match/session ID to reduce train–test contamination across related sequences, the best configuration (DeepLabV3+ (foreground) + EfficientNet-B7 + Bi-LSTM) attains 82.9% top-1 accuracy. Ablation results quantify the added value of foregrounding, showing consistent gains for the strongest backbone and the largest improvements on high-occlusion techniques, at the cost of additional inference latency due to segmentation. Due to the modest dataset size, we mitigate overfitting via transfer learning and extensive augmentation, and we frame conclusions as domain-specific to freestyle wrestling. The dataset and code are released. To comply with copyright constraints, the controlled subset is provided as processed clips, while the broadcast subset is released as annotations and clip metadata to enable reconstruction.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A CNN–Bi-LSTM pipeline and open FSW dataset for freestyle wrestling action recognition

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月23日

查看全文
  • Milad Rostamian,
  • Ali Mottaghi,
  • Mohsen Soryani

摘要

Human action recognition in close-contact sports is hindered by mutual occlusion, rapid pose changes, and distracting backgrounds. We study freestyle wrestling—a representative close-contact setting with sustained physical interaction—and present the Open FSW dataset of 210 trimmed clips covering seven techniques (30 clips per class), sourced from both controlled training sessions and broadcast footage. We introduce a foreground-aware RGB pipeline that segments athletes with a fine-tuned DeepLabV3+ model, extracts per-frame features using CNN backbones (VGG16, InceptionV3, EfficientNet-B7), and aggregates them with a bidirectional LSTM to produce clip-level predictions. Under a group-aware six-fold cross-validation protocol stratified by match/session ID to reduce train–test contamination across related sequences, the best configuration (DeepLabV3+ (foreground) + EfficientNet-B7 + Bi-LSTM) attains 82.9% top-1 accuracy. Ablation results quantify the added value of foregrounding, showing consistent gains for the strongest backbone and the largest improvements on high-occlusion techniques, at the cost of additional inference latency due to segmentation. Due to the modest dataset size, we mitigate overfitting via transfer learning and extensive augmentation, and we frame conclusions as domain-specific to freestyle wrestling. The dataset and code are released. To comply with copyright constraints, the controlled subset is provided as processed clips, while the broadcast subset is released as annotations and clip metadata to enable reconstruction.