# Action tube generation by person query matching for spatio-temporal action detection

arXiv: https://arxiv.org/abs/2503.12969 · HTML: https://mlsanity.com/paper/2503.12969/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 47 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Builds on (most cited first, 30 of 41)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [MOTR: End-to-End Multiple-Object Tracking with Transformer](https://mlsanity.com/paper/2105.03247/) (2021)
- [A Short Note on the Kinetics-700 Human Action Dataset](https://mlsanity.com/paper/1907.06987/) (2019)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [Long-Term Feature Banks for Detailed Video Understanding](https://mlsanity.com/paper/1812.05038/) (2018)
- [MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition](https://mlsanity.com/paper/2201.08383/) (2022)
- [TubeDETR: Spatio-Temporal Video Grounding with Transformers](https://mlsanity.com/paper/2203.16434/) (2022)
- [Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization](https://mlsanity.com/paper/2006.07976/) (2020)
- [Actor-Centric Relation Network](https://mlsanity.com/paper/1807.10982/) (2018)
- [Action Tubelet Detector for Spatio-Temporal Action Localization](https://mlsanity.com/paper/1705.01861/) (2017)
- [You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization](https://mlsanity.com/paper/1911.06644/) (2019)

## Abstract (arXiv)

This paper proposes a method for spatio-temporal action detection (STAD) that directly generates action tubes from the original video without relying on post-processing steps such as IoU-based linking and clip splitting. Our approach applies query-based detection (DETR) to each frame and matches DETR queries to link the same person across frames. We introduce the Query Matching Module (QMM), which uses metric learning to bring queries for the same person closer together across frames compared to queries for different people. Action classes are predicted using the sequence of queries obtained from QMM matching, allowing for variable-length inputs from videos longer than a single clip. Experimental results on JHMDB, UCF101-24, and AVA datasets demonstrate that our method performs well for large position changes of people while offering superior computational efficiency and lower resource requirements.