# Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking

arXiv: https://arxiv.org/abs/2012.02337 · HTML: https://mlsanity.com/paper/2012.02337/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 30 of 36)

- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [StrongSORT: Make DeepSORT Great Again](https://mlsanity.com/paper/2202.13514/) (2022)
- [MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking](https://mlsanity.com/paper/2303.10404/) (2023)
- [FLAG: Flow-based 3D Avatar Generation from Sparse Observations](https://mlsanity.com/paper/2203.05789/) (2022)
- [A Survey of Sound Source Localization with Deep Learning Methods](https://mlsanity.com/paper/2109.03465/) (2021)
- [Simple Cues Lead to a Strong Multi-Object Tracker](https://mlsanity.com/paper/2206.04656/) (2022)
- [TransCenter: Transformers with Dense Representations for Multiple-Object Tracking](https://mlsanity.com/paper/2103.15145/) (2021)
- [JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking](https://mlsanity.com/paper/2210.11940/) (2022)
- [Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.14829/) (2021)
- [MotionTrack: Learning Motion Predictor for Multiple Object Tracking](https://mlsanity.com/paper/2306.02585/) (2023)
- [EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving](https://mlsanity.com/paper/2402.18302/) (2024)
- [HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations](https://mlsanity.com/paper/2308.11261/) (2023)
- [MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model](https://mlsanity.com/paper/2408.09178/) (2024)
- [Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation](https://mlsanity.com/paper/2201.01297/) (2022)
- [TrackFlow: Multi-Object Tracking with Normalizing Flows](https://mlsanity.com/paper/2308.11513/) (2023)
- [DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions](https://mlsanity.com/paper/2309.04682/) (2023)
- [Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equation](https://mlsanity.com/paper/2312.15906/) (2023)
- [Learning of Global Objective for Network Flow in Multi-Object Tracking](https://mlsanity.com/paper/2203.16210/) (2022)
- [Multi-view Tracking Using Weakly Supervised Human Motion Prediction](https://mlsanity.com/paper/2210.10771/) (2022)
- [DeconfuseTrack:Dealing with Confusion for Multi-Object Tracking](https://mlsanity.com/paper/2403.02767/) (2024)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [Learning Data Association for Multi-Object Tracking using Only Coordinates](https://mlsanity.com/paper/2403.08018/) (2024)
- [SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking](https://mlsanity.com/paper/2203.03985/) (2022)
- [Towards Frame Rate Agnostic Multi-Object Tracking](https://mlsanity.com/paper/2209.11404/) (2022)
- [3D Multiple Object Tracking on Autonomous Driving: A Literature Review](https://mlsanity.com/paper/2309.15411/) (2023)
- [Tracking Different Ant Species: An Unsupervised Domain Adaptation Framework and a Dataset for Multi-object Tracking](https://mlsanity.com/paper/2301.10559/) (2023)
- [Learnable Graph Matching: A Practical Paradigm for Data Association](https://mlsanity.com/paper/2303.15414/) (2023)
- [Tracking Objects with 3D Representation from Videos](https://mlsanity.com/paper/2306.05416/) (2023)
- [Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation](https://mlsanity.com/paper/2312.04167/) (2023)
- [OCTrack: Benchmarking the Open-Corpus Multi-Object Tracking](https://mlsanity.com/paper/2407.14047/) (2024)

## Abstract (arXiv)

Despite the recent advances in multiple object tracking (MOT), achieved by joint detection and tracking, dealing with long occlusions remains a challenge. This is due to the fact that such techniques tend to ignore the long-term motion information. In this paper, we introduce a probabilistic autoregressive motion model to score tracklet proposals by directly measuring their likelihood. This is achieved by training our model to learn the underlying distribution of natural tracklets. As such, our model allows us not only to assign new detections to existing tracklets, but also to inpaint a tracklet when an object has been lost for a long time, e.g., due to occlusion, by sampling tracklets so as to fill the gap caused by misdetections. Our experiments demonstrate the superiority of our approach at tracking objects in challenging sequences; it outperforms the state of the art in most standard MOT metrics on multiple MOT benchmark datasets, including MOT16, MOT17, and MOT20.