# Clip-level Uncertainty and Temporal-aware Active Learning for End-to-End Multi-Object Tracking

arXiv: https://arxiv.org/abs/2605.09858 · HTML: https://mlsanity.com/paper/2605.09858/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 11 May 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 19 of 19)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [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)
- [MOTR: End-to-End Multiple-Object Tracking with Transformer](https://mlsanity.com/paper/2105.03247/) (2021)
- [DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion](https://mlsanity.com/paper/2111.14690/) (2021)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes](https://mlsanity.com/paper/2304.05170/) (2023)
- [MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking](https://mlsanity.com/paper/2307.15700/) (2023)
- [Plug and Play Active Learning for Object Detection](https://mlsanity.com/paper/2211.11612/) (2022)
- [Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking](https://mlsanity.com/paper/2410.01806/) (2024)
- [SPAMming Labels: Efficient Annotations for the Trackers of Tomorrow](https://mlsanity.com/paper/2404.11426/) (2024)

## Built on by (most cited first, 1 of 1)

- [Probing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Tracking](https://mlsanity.com/paper/2608.17224/) (2026)

## Abstract (arXiv)

Multi-Object Tracking (MOT) in dynamic environments relies on robust temporal reasoning to maintain consistent object identities over time. Transformer-based end-to-end MOT models achieve strong performance by explicitly modeling temporal dependencies, yet training them requires extensive bounding-box and identity annotations. Given the high labeling cost and strong redundancy in videos, Active Learning (AL) is an effective approach to improve annotation efficiency. However, existing AL methods for MOT primarily operate at the frame level, which is structurally misaligned with modern end-to-end trackers whose inference and training rely on multi-frame clips. To bridge this gap, we formulate clip-level active learning and propose Clip-level Uncertainty and Temporal-aware Active Learning (CUTAL). In contrast to frame-based approaches, CUTAL scores each clip using uncertainty metrics derived from multi-frame predictions to capture inter-frame correspondence ambiguities, while enforcing temporal diversity to select an informative and non-redundant subset. Experiments show that CUTAL achieves stronger overall performance than baselines at the same label budgets across MeMOTR and SambaMOTR. Notably, CUTAL achieves performance comparable to full supervision for MeMOTR on both datasets using only 50% of the labeled training data.