# Multi-Object Tracking as Attention Mechanism

arXiv: https://arxiv.org/abs/2307.05874 · HTML: https://mlsanity.com/paper/2307.05874/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 23 references that are in the map.
- First posted on arXiv 12 Jul 2023.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [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)
- [MOTR: End-to-End Multiple-Object Tracking with Transformer](https://mlsanity.com/paper/2105.03247/) (2021)
- [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)
- [CityPersons: A Diverse Dataset for Pedestrian Detection](https://mlsanity.com/paper/1702.05693/) (2017)
- [Person Re-identification in the Wild](https://mlsanity.com/paper/1604.02531/) (2016)
- [Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking](https://mlsanity.com/paper/2007.14557/) (2020)
- [Deep Affinity Network for Multiple Object Tracking](https://mlsanity.com/paper/1810.11780/) (2018)
- [TransCenter: Transformers with Dense Representations for Multiple-Object Tracking](https://mlsanity.com/paper/2103.15145/) (2021)
- [Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving](https://mlsanity.com/paper/2205.14882/) (2022)

## Built on by (most cited first, 3 of 3)

- [MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost](https://mlsanity.com/paper/2509.01157/) (2025)
- [SFSORT: Scene Features-based Simple Online Real-Time Tracker](https://mlsanity.com/paper/2404.07553/) (2024)
- [Attention-Aware Multi-View Pedestrian Tracking](https://mlsanity.com/paper/2504.03047/) (2025)

## Abstract (arXiv)

We propose a conceptually simple and thus fast multi-object tracking (MOT) model that does not require any attached modules, such as the Kalman filter, Hungarian algorithm, transformer blocks, or graph networks. Conventional MOT models are built upon the multi-step modules listed above, and thus the computational cost is high. Our proposed end-to-end MOT model, textitTicrossNet, is composed of a base detector and a cross-attention module only. As a result, the overhead of tracking does not increase significantly even when the number of instances (Nt) increases. We show that TicrossNet runs textitin real-time; specifically, it achieves 32.6 FPS on MOT17 and 31.0 FPS on MOT20 (Tesla V100), which includes as many as >100 instances per frame. We also demonstrate that TicrossNet is robust to Nt; thus, it does not have to change the size of the base detector, depending on Nt, as is often done by other models for real-time processing.