mlsanityData to 7 Oct 2026

TOTNet: Occlusion-Aware Temporal Tracking for Robust Ball Detection in Sports Videos

arXiv 2508.09650 ↗First posted 13 Aug 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Robust ball tracking under occlusion remains a key challenge in sports video analysis, affecting tasks like event detection and officiating. We present TOTNet, a Temporal Occlusion Tracking Network that leverages 3D convolutions, visibility-weighted loss, and occlusion augmentation to improve performance under partial and full occlusions. Developed in collaboration with Paralympics Australia, TOTNet is designed for real-world sports analytics. We introduce TTA, a new occlusion-rich table tennis dataset collected from professional-level Paralympic matches, comprising 9,159 samples with 1,996 occlusion cases. Evaluated on four datasets across tennis, badminton, and table tennis, TOTNet significantly outperforms prior state-of-the-art methods, reducing RMSE from 37.30 to 7.19 and improving accuracy on fully occluded frames from 0.63 to 0.80. These results demonstrate TOTNets effectiveness for offline sports analytics in fast-paced scenarios. Code and data access:hrefhttps://github.com/AugustRushG/TOTNetAugustRushG/TOTNet.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 13 Aug 2025.

Builds on

24 of 40 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  7. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  8. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  9. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  10. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 504
  11. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  12. 2016Amodal Instance Segmentationcited by 63
12 more
  1. 2020Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusioncited by 47
  2. 2017A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detectioncited by 43
  3. 2020TTNet: Real-time temporal and spatial video analysis of table tenniscited by 35
  4. 2019TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applicationscited by 33
  5. 2015Spatio-temporal video autoencoder with differentiable memorycited by 32
  6. 2021Occlusion Handling in Generic Object Detection: A Reviewcited by 25
  7. 2022MonoTrack: Shuttle trajectory reconstruction from monocular badminton videocited by 24
  8. 2022A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directionscited by 21
  9. 2019DeepBall: Deep Neural-Network Ball Detectorcited by 11
  10. 2023Widely Applicable Strong Baseline for Sports Ball Detection and Trackingcited by 9
  11. 2024Basketball-SORT: An Association Method for Complex Multi-object Occlusion Problems in Basketball Multi-object Trackingcited by 4
  12. 2019Utilizing Temporal Information in Deep Convolutional Network for Efficient Soccer Ball Detection and Trackingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2026Improving Robustness of Vision-Language-Action Models by Restoring Corrupted Visual Inputscited by 3
  2. 2025TrackNetV5: Residual-Driven Spatio-Temporal Refinement and Motion Direction Decoupling for Fast Object Trackingcited by 0