# UnsMOT: Unified Framework for Unsupervised Multi-Object Tracking with Geometric Topology Guidance

arXiv: https://arxiv.org/abs/2309.01078 · HTML: https://mlsanity.com/paper/2309.01078/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 53 references that are in the map.
- First posted on arXiv 3 Sep 2023.

## Builds on (most cited first, 30 of 32)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [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)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [Towards Real-Time Multi-Object Tracking](https://mlsanity.com/paper/1909.12605/) (2019)
- [Quasi-Dense Similarity Learning for Multiple Object Tracking](https://mlsanity.com/paper/2006.06664/) (2020)
- [Learning a Neural Solver for Multiple Object Tracking](https://mlsanity.com/paper/1912.07515/) (2019)
- [Track to Detect and Segment: An Online Multi-Object Tracker](https://mlsanity.com/paper/2103.08808/) (2021)
- [Deep Affinity Network for Multiple Object Tracking](https://mlsanity.com/paper/1810.11780/) (2018)
- [Learning by tracking: Siamese CNN for robust target association](https://mlsanity.com/paper/1604.07866/) (2016)
- [POI: Multiple Object Tracking with High Performance Detection and Appearance Feature](https://mlsanity.com/paper/1610.06136/) (2016)
- [How To Train Your Deep Multi-Object Tracker](https://mlsanity.com/paper/1906.06618/) (2019)
- [SiamMOT: Siamese Multi-Object Tracking](https://mlsanity.com/paper/2105.11595/) (2021)
- [Learning Context Graph for Person Search](https://mlsanity.com/paper/1904.01830/) (2019)
- [Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking](https://mlsanity.com/paper/2103.16178/) (2021)
- [Re-ID Driven Localization Refinement for Person Search](https://mlsanity.com/paper/1909.08580/) (2019)
- [Query-guided End-to-End Person Search](https://mlsanity.com/paper/1905.01203/) (2019)
- [Simple Unsupervised Multi-Object Tracking](https://mlsanity.com/paper/2006.02609/) (2020)
- [GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization](https://mlsanity.com/paper/2010.00067/) (2020)
- [Self-Supervised Multi-Object Tracking with Cross-Input Consistency](https://mlsanity.com/paper/2111.05943/) (2021)
- [PathTrack: Fast Trajectory Annotation with Path Supervision](https://mlsanity.com/paper/1703.02437/) (2017)
- [Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification](https://mlsanity.com/paper/1901.06129/) (2019)

## Abstract (arXiv)

Object detection has long been a topic of high interest in computer vision literature. Motivated by the fact that annotating data for the multi-object tracking (MOT) problem is immensely expensive, recent studies have turned their attention to the unsupervised learning setting. In this paper, we push forward the state-of-the-art performance of unsupervised MOT methods by proposing UnsMOT, a novel framework that explicitly combines the appearance and motion features of objects with geometric information to provide more accurate tracking. Specifically, we first extract the appearance and motion features using CNN and RNN models, respectively. Then, we construct a graph of objects based on their relative distances in a frame, which is fed into a GNN model together with CNN features to output geometric embedding of objects optimized using an unsupervised loss function. Finally, associations between objects are found by matching not only similar extracted features but also geometric embedding of detections and tracklets. Experimental results show remarkable performance in terms of HOTA, IDF1, and MOTA metrics in comparison with state-of-the-art methods.