# TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking

arXiv: https://arxiv.org/abs/2104.00194 · HTML: https://mlsanity.com/paper/2104.00194/

## Key facts

- Cited by 93 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 70 references that are in the map.
- First posted on arXiv 1 Apr 2021.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [TrackFormer: Multi-Object Tracking with Transformers](https://mlsanity.com/paper/2101.02702/) (2021)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [TransTrack: Multiple Object Tracking with Transformer](https://mlsanity.com/paper/2012.15460/) (2020)
- [MOT20: A benchmark for multi object tracking in crowded scenes](https://mlsanity.com/paper/2003.09003/) (2020)
- [CrowdHuman: A Benchmark for Detecting Human in a Crowd](https://mlsanity.com/paper/1805.00123/) (2018)
- [Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2005.08514/) (2020)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Learning a Neural Solver for Multiple Object Tracking](https://mlsanity.com/paper/1912.07515/) (2019)
- [Multiple Object Tracking: A Literature Review](https://mlsanity.com/paper/1409.7618/) (2014)
- [MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking](https://mlsanity.com/paper/1504.01942/) (2015)
- [Learning to Track with Object Permanence](https://mlsanity.com/paper/2103.14258/) (2021)
- [Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking](https://mlsanity.com/paper/2007.14557/) (2020)
- [Rethinking the competition between detection and ReID in Multi-Object Tracking](https://mlsanity.com/paper/2010.12138/) (2020)
- [PolyTransform: Deep Polygon Transformer for Instance Segmentation](https://mlsanity.com/paper/1912.02801/) (2019)
- [Deep Affinity Network for Multiple Object Tracking](https://mlsanity.com/paper/1810.11780/) (2018)
- [Online Multi-Object Tracking with Dual Matching Attention Networks](https://mlsanity.com/paper/1902.00749/) (2019)
- [Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies](https://mlsanity.com/paper/1701.01909/) (2017)
- [How To Train Your Deep Multi-Object Tracker](https://mlsanity.com/paper/1906.06618/) (2019)
- [TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model](https://mlsanity.com/paper/2006.05683/) (2020)
- [RetinaTrack: Online Single Stage Joint Detection and Tracking](https://mlsanity.com/paper/2003.13870/) (2020)

## Built on by (most cited first, 30 of 93)

- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [MOTR: End-to-End Multiple-Object Tracking with Transformer](https://mlsanity.com/paper/2105.03247/) (2021)
- [Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking](https://mlsanity.com/paper/2203.14360/) (2022)
- [BoT-SORT: Robust Associations Multi-Pedestrian Tracking](https://mlsanity.com/paper/2206.14651/) (2022)
- [StrongSORT: Make DeepSORT Great Again](https://mlsanity.com/paper/2202.13514/) (2022)
- [MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors](https://mlsanity.com/paper/2211.09791/) (2022)
- [Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification](https://mlsanity.com/paper/2302.11813/) (2023)
- [MeMOT: Multi-Object Tracking with Memory](https://mlsanity.com/paper/2203.16761/) (2022)
- [Global Tracking Transformers](https://mlsanity.com/paper/2203.13250/) (2022)
- [Towards Grand Unification of Object Tracking](https://mlsanity.com/paper/2207.07078/) (2022)
- [Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking](https://mlsanity.com/paper/2308.00783/) (2023)
- [Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking](https://mlsanity.com/paper/2302.03802/) (2023)
- [SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth](https://mlsanity.com/paper/2306.05238/) (2023)
- [Tracking Objects as Pixel-wise Distributions](https://mlsanity.com/paper/2207.05518/) (2022)
- [SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking](https://mlsanity.com/paper/2211.08824/) (2022)
- [Real-time 3D Single Object Tracking with Transformer](https://mlsanity.com/paper/2209.00860/) (2022)
- [JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking](https://mlsanity.com/paper/2210.11940/) (2022)
- [Focus On Details: Online Multi-object Tracking with Diverse Fine-grained Representation](https://mlsanity.com/paper/2302.14589/) (2023)
- [ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking](https://mlsanity.com/paper/2308.13229/) (2023)
- [Spatio-Temporal Graph Neural Networks: A Survey](https://mlsanity.com/paper/2301.10569/) (2023)
- [3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking](https://mlsanity.com/paper/2308.06635/) (2023)
- [TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes](https://mlsanity.com/paper/2308.11157/) (2023)
- [ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2303.15334/) (2023)
- [OmniTracker: Unifying Object Tracking by Tracking-with-Detection](https://mlsanity.com/paper/2303.12079/) (2023)
- [Scalable Video Object Segmentation with Identification Mechanism](https://mlsanity.com/paper/2203.11442/) (2022)
- [MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving](https://mlsanity.com/paper/2409.16149/) (2024)
- [LLM-AD: Large Language Model based Audio Description System](https://mlsanity.com/paper/2405.00983/) (2024)
- [Trackastra: Transformer-based cell tracking for live-cell microscopy](https://mlsanity.com/paper/2405.15700/) (2024)
- [DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions](https://mlsanity.com/paper/2309.04682/) (2023)
- [Beyond MOT: Semantic Multi-Object Tracking](https://mlsanity.com/paper/2403.05021/) (2024)

## Abstract (arXiv)

Tracking multiple objects in videos relies on modeling the spatial-temporal interactions of the objects. In this paper, we propose a solution named TransMOT, which leverages powerful graph transformers to efficiently model the spatial and temporal interactions among the objects. TransMOT effectively models the interactions of a large number of objects by arranging the trajectories of the tracked objects as a set of sparse weighted graphs, and constructing a spatial graph transformer encoder layer, a temporal transformer encoder layer, and a spatial graph transformer decoder layer based on the graphs. TransMOT is not only more computationally efficient than the traditional Transformer, but it also achieves better tracking accuracy. To further improve the tracking speed and accuracy, we propose a cascade association framework to handle low-score detections and long-term occlusions that require large computational resources to model in TransMOT. The proposed method is evaluated on multiple benchmark datasets including MOT15, MOT16, MOT17, and MOT20, and it achieves state-of-the-art performance on all the datasets.