mlsanityData to 7 Oct 2026

Spotting Temporally Precise, Fine-Grained Events in Video

arXiv 2207.10213 ↗First posted 20 Jul 2022cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

We introduce the task of spotting temporally precise, fine-grained events in video (detecting the precise moment in time events occur). Precise spotting requires models to reason globally about the full-time scale of actions and locally to identify subtle frame-to-frame appearance and motion differences that identify events during these actions. Surprisingly, we find that top performing solutions to prior video understanding tasks such as action detection and segmentation do not simultaneously meet both requirements. In response, we propose E2E-Spot, a compact, end-to-end model that performs well on the precise spotting task and can be trained quickly on a single GPU. We demonstrate that E2E-Spot significantly outperforms recent baselines adapted from the video action detection, segmentation, and spotting literature to the precise spotting task. Finally, we contribute new annotations and splits to several fine-grained sports action datasets to make these datasets suitable for future work on precise spotting.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 56 of its 83 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

56 of 83 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2022A ConvNet for the 2020scited by 3,545
  7. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  8. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  9. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  10. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  11. 2017The Kinetics Human Action Video Datasetcited by 1,894
  12. 2018SlowFast Networks for Video Recognitioncited by 1,862
38 more
  1. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  2. 2020Designing Network Design Spacescited by 954
  3. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  4. 2021Multiscale Vision Transformerscited by 896
  5. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  6. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  7. 2016Hollywood in Homes: Crowdsourcing Data Collection for Activity Understandingcited by 535
  8. 2019MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentationcited by 370
  9. 2019BMN: Boundary-Matching Network for Temporal Action Proposal Generationcited by 327
  10. 2017Temporal Relational Reasoning in Videoscited by 324
  11. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 308
  12. 2018BSN: Boundary Sensitive Network for Temporal Action Proposal Generationcited by 271
  13. 2019G-TAD: Sub-Graph Localization for Temporal Action Detectioncited by 248
  14. 2020FineGym: A Hierarchical Video Dataset for Fine-grained Action Understandingcited by 232
  15. 2019Graph Convolutional Networks for Temporal Action Localizationcited by 208
  16. 2021ASFormer: Transformer for Action Segmentationcited by 166
  17. 2021Learning Salient Boundary Feature for Anchor-free Temporal Action Localizationcited by 156
  18. 2020SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videoscited by 129
  19. 2022FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessmentcited by 106
  20. 2020Video Self-Stitching Graph Network for Temporal Action Localizationcited by 104
  21. 2015Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videoscited by 93
  22. 2016Hierarchical Deep Temporal Models for Group Activity Recognitioncited by 89
  23. 2020Alleviating Over-segmentation Errors by Detecting Action Boundariescited by 86
  24. 2020The AVA-Kinetics Localized Human Actions Video Datasetcited by 82
  25. 2021MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actionscited by 82
  26. 2020TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Taskscited by 77
  27. 2019Gate-Shift Networks for Video Action Recognitioncited by 76
  28. 2019A Context-Aware Loss Function for Action Spotting in Soccer Videoscited by 56
  29. 2020Multi-shot Temporal Event Localization: a Benchmarkcited by 52
  30. 2020Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detectioncited by 42
  31. 2022An Empirical Study of End-to-End Temporal Action Detectioncited by 40
  32. 2021Modeling Multi-Label Action Dependencies for Temporal Action Localizationcited by 32
  33. 2021PyTorchVideo: A Deep Learning Library for Video Understandingcited by 32
  34. 2020Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Playerscited by 30
  35. 2021Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcastscited by 30
  36. 2021Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognitioncited by 29
  37. 2021Coarse to Fine Multi-Resolution Temporal Convolutional Networkcited by 28
  38. 2021Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detectioncited by 27

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 11; 2025: 11; 2026: 10.

40 papers.

Sort:

By area:

  1. 2023SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentariescited by 57
  2. 2023VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Viewscited by 38
  3. 2024SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimapcited by 34
  4. 2024X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Modelcited by 22
  5. 2024T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videoscited by 21
  6. 2023SoccerNet 2023 Challenges Resultscited by 20
  7. 2023COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformerscited by 17
  8. 2024ASTRA: An Action Spotting TRAnsformer for Soccer Videoscited by 16
  9. 2023Towards Active Learning for Action Spotting in Association Football Videoscited by 14
  10. 2023A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decisioncited by 11
  11. 2024Efficient Temporal Action Segmentation via Boundary-aware Query Votingcited by 10
  12. 2025Action Anticipation from SoccerNet Football Video Broadcastscited by 9
28 more
  1. 2024Unifying Global and Local Scene Entities Modelling for Precise Action Spottingcited by 8
  2. 2024Towards AI-Powered Video Assistant Referee System (VARS) for Association Footballcited by 8
  3. 2023Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectivescited by 7
  4. 20243D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approachcited by 7
  5. 2024Deep learning for action spotting in association football videoscited by 7
  6. 2025F3Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videoscited by 7
  7. 2025Game State and Spatio-temporal Action Detection in Soccer using Graph Neural Networks and 3D Convolutional Networkscited by 6
  8. 2025Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalancecited by 6
  9. 2025FOOTPASS: A Multi-Modal Multi-Agent Tactical Context Dataset for Play-by-Play Action Spotting in Soccer Broadcast Videoscited by 5
  10. 2023A Boosted Model Ensembling Approach to Ball Action Spotting in Videos: The Runner-Up Solution to CVPR'23 SoccerNet Challengecited by 4
  11. 2025Deep Learning for Sports Video Event Detection: Tasks, Datasets, Methods, and Challengescited by 3
  12. 2024OSL-ActionSpotting: A Unified Library for Action Spotting in Sports Videoscited by 2
  13. 2026AdaSpot: Spend Resolution Where It Matters for Precise Event Spottingcited by 2
  14. 2026Detecting Precise Hand Touch Moments in Egocentric Videocited by 2
  15. 2024Investigating Event-Based Cameras for Video Frame Interpolation in Sportscited by 1
  16. 2025Do We Need Large VLMs for Spotting Soccer Actions?cited by 1
  17. 2025Multi-Focus Temporal Shifting for Precise Event Spotting in Sports Videoscited by 1
  18. 2025MCAD: Multimodal Context-Aware Audio Description Generation For Soccercited by 1
  19. 2026Towards Athlete Fatigue Assessment from Association Football Videoscited by 1
  20. 2026SoccerNet 2026 Challenges Resultscited by 1
  21. 2025Towards Precise Action Spotting: Addressing Temporal Misalignment in Labels with Dynamic Label Assignmentcited by 0
  22. 2025SoccerTrack v2: A Full-Pitch Panoramic Video Dataset for Game State Reconstruction and Ball Action Spottingcited by 0
  23. 2026From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillationcited by 0
  24. 2026Event-based Batting Impact Estimationcited by 0
  25. 2026SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videoscited by 0
  26. 2026Temporal Feature Distillation for Label-Efficient Precise Event Spotting in Sports Videoscited by 0
  27. 2026Entity-Aware Sequence Transduction for Player-Centric Ball Action Spottingcited by 0
  28. 2026ProTracer: Proprioception-Guided Failure Diagnosis in Robot Manipulationcited by 0