# Real-time Online Multi-Object Tracking in Compressed Domain

arXiv: https://arxiv.org/abs/2204.02081 · HTML: https://mlsanity.com/paper/2204.02081/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 40 references that are in the map.
- First posted on arXiv 5 Apr 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [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)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [CityPersons: A Diverse Dataset for Pedestrian Detection](https://mlsanity.com/paper/1702.05693/) (2017)
- [MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking](https://mlsanity.com/paper/1504.01942/) (2015)
- [Compressed Video Action Recognition](https://mlsanity.com/paper/1712.00636/) (2017)
- [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)
- [POI: Multiple Object Tracking with High Performance Detection and Appearance Feature](https://mlsanity.com/paper/1610.06136/) (2016)
- [Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism](https://mlsanity.com/paper/1708.02843/) (2017)
- [Fast Object Detection in Compressed Video](https://mlsanity.com/paper/1811.11057/) (2018)
- [MV-YOLO: Motion Vector-aided Tracking by Semantic Object Detection](https://mlsanity.com/paper/1805.00107/) (2018)
- [Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering](https://mlsanity.com/paper/1805.10916/) (2018)

## Built on by (most cited first, 6 of 6)

- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [CoVA: Exploiting Compressed-Domain Analysis to Accelerate Video Analytics](https://mlsanity.com/paper/2207.00588/) (2022)
- [Task-Aware Encoder Control for Deep Video Compression](https://mlsanity.com/paper/2404.04848/) (2024)
- [Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain](https://mlsanity.com/paper/2209.14757/) (2022)
- [MVTrack: Ultrafast Appearance-Free Moving Object Tracking from Compressed Bitstreams](https://mlsanity.com/paper/2608.10790/) (2026)
- [Albireo: Adaptive, Energy-Efficient Inference Framework for Video Object Detection on the Edge](https://mlsanity.com/paper/2609.29648/) (2026)

## Abstract (arXiv)

Recent online Multi-Object Tracking (MOT) methods have achieved desirable tracking performance. However, the tracking speed of most existing methods is rather slow. Inspired from the fact that the adjacent frames are highly relevant and redundant, we divide the frames into key and non-key frames respectively and track objects in the compressed domain. For the key frames, the RGB images are restored for detection and data association. To make data association more reliable, an appearance Convolutional Neural Network (CNN) which can be jointly trained with the detector is proposed. For the non-key frames, the objects are directly propagated by a tracking CNN based on the motion information provided in the compressed domain. Compared with the state-of-the-art online MOT methods,our tracker is about 6x faster while maintaining a comparable tracking performance.