# Spatio-Temporal Action Detection Under Large Motion

arXiv: https://arxiv.org/abs/2209.02250 · HTML: https://mlsanity.com/paper/2209.02250/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 55 references that are in the map.
- First posted on arXiv 6 Sep 2022.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization](https://mlsanity.com/paper/2006.07976/) (2020)
- [MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions](https://mlsanity.com/paper/2105.07404/) (2021)
- [Action Tubelet Detector for Spatio-Temporal Action Localization](https://mlsanity.com/paper/1705.01861/) (2017)
- [Learning Generalisable Omni-Scale Representations for Person Re-Identification](https://mlsanity.com/paper/1910.06827/) (2019)
- [Asynchronous Interaction Aggregation for Action Detection](https://mlsanity.com/paper/2004.07485/) (2020)
- [You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization](https://mlsanity.com/paper/1911.06644/) (2019)
- [Online Real-time Multiple Spatiotemporal Action Localisation and Prediction](https://mlsanity.com/paper/1611.08563/) (2016)
- [Actions as Moving Points](https://mlsanity.com/paper/2001.04608/) (2020)
- [TubeR: Tubelet Transformer for Video Action Detection](https://mlsanity.com/paper/2104.00969/) (2021)
- [ROAD: The ROad event Awareness Dataset for Autonomous Driving](https://mlsanity.com/paper/2102.11585/) (2021)
- [STEP: Spatio-Temporal Progressive Learning for Video Action Detection](https://mlsanity.com/paper/1904.09288/) (2019)
- [Finding Action Tubes](https://mlsanity.com/paper/1411.6031/) (2014)

## Built on by (most cited first, 14 of 14)

- [IDD-X: A Multi-View Dataset for Ego-relative Important Object Localization and Explanation in Dense and Unstructured Traffic](https://mlsanity.com/paper/2404.08561/) (2024)
- [Computer Vision for Primate Behavior Analysis in the Wild](https://mlsanity.com/paper/2401.16424/) (2024)
- [Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives](https://mlsanity.com/paper/2309.12067/) (2023)
- [Game State and Spatio-temporal Action Detection in Soccer using Graph Neural Networks and 3D Convolutional Networks](https://mlsanity.com/paper/2502.15462/) (2025)
- [A Survey on Deep Learning-based Spatio-temporal Action Detection](https://mlsanity.com/paper/2308.01618/) (2023)
- [Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos](https://mlsanity.com/paper/2505.09455/) (2025)
- [FOOTPASS: A Multi-Modal Multi-Agent Tactical Context Dataset for Play-by-Play Action Spotting in Soccer Broadcast Videos](https://mlsanity.com/paper/2511.16183/) (2025)
- [A Semantic and Motion-Aware Spatiotemporal Transformer Network for Action Detection](https://mlsanity.com/paper/2405.08204/) (2024)
- [SoccerNet 2026 Challenges Results](https://mlsanity.com/paper/2607.07320/) (2026)
- [STMixer: A One-Stage Sparse Action Detector](https://mlsanity.com/paper/2404.09842/) (2024)
- [Action tube generation by person query matching for spatio-temporal action detection](https://mlsanity.com/paper/2503.12969/) (2025)
- [SoccerNet 2026 Player-Centric Ball-Action Spotting:Retraining and Post-Processing Extensions to the FOOTPASS Baselines](https://mlsanity.com/paper/2606.09679/) (2026)
- [SoccerNet 2026 Player-Centric Ball Action Spotting: Per-Player Attention with Agreement-Based Ensembling](https://mlsanity.com/paper/2606.28389/) (2026)
- [Entity-Aware Sequence Transduction for Player-Centric Ball Action Spotting](https://mlsanity.com/paper/2608.01696/) (2026)

## Abstract (arXiv)

Current methods for spatiotemporal action tube detection often extend a bounding box proposal at a given keyframe into a 3D temporal cuboid and pool features from nearby frames. However, such pooling fails to accumulate meaningful spatiotemporal features if the position or shape of the actor shows large 2D motion and variability through the frames, due to large camera motion, large actor shape deformation, fast actor action and so on. In this work, we aim to study the performance of cuboid-aware feature aggregation in action detection under large action. Further, we propose to enhance actor feature representation under large motion by tracking actors and performing temporal feature aggregation along the respective tracks. We define the actor motion with intersection-over-union (IoU) between the boxes of action tubes/tracks at various fixed time scales. The action having a large motion would result in lower IoU over time, and slower actions would maintain higher IoU. We find that track-aware feature aggregation consistently achieves a large improvement in action detection performance, especially for actions under large motion compared to the cuboid-aware baseline. As a result, we also report state-of-the-art on the large-scale MultiSports dataset. The Code is available at https://github.com/gurkirt/ActionTrackDetectron.