# Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers

arXiv: https://arxiv.org/abs/1801.03049 · HTML: https://mlsanity.com/paper/1801.03049/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jan 2018.

## Built on by (most cited first, 30 of 34)

- [VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows](https://mlsanity.com/paper/2108.05015/) (2021)
- [Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark](https://mlsanity.com/paper/2103.16746/) (2021)
- [Learning Normal Dynamics in Videos with Meta Prototype Network](https://mlsanity.com/paper/2104.06689/) (2021)
- [OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning](https://mlsanity.com/paper/2403.09634/) (2024)
- [Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning](https://mlsanity.com/paper/2110.03909/) (2021)
- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction](https://mlsanity.com/paper/2103.16449/) (2021)
- [MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking](https://mlsanity.com/paper/2107.10433/) (2021)
- [WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking](https://mlsanity.com/paper/2201.07425/) (2022)
- [Visual Object Tracking in First Person Vision](https://mlsanity.com/paper/2209.13502/) (2022)
- [Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation](https://mlsanity.com/paper/2111.04017/) (2021)
- [Is First Person Vision Challenging for Object Tracking?](https://mlsanity.com/paper/2108.13665/) (2021)
- [Tiny Object Tracking: A Large-scale Dataset and A Baseline](https://mlsanity.com/paper/2202.05659/) (2022)
- [360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Tracking](https://mlsanity.com/paper/2307.14630/) (2023)
- [360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videos](https://mlsanity.com/paper/2404.13953/) (2024)
- [CST Anti-UAV: A Thermal Infrared Benchmark for Tiny UAV Tracking in Complex Scenes](https://mlsanity.com/paper/2507.23473/) (2025)
- [Tracking by Joint Local and Global Search: A Target-aware Attention based Approach](https://mlsanity.com/paper/2106.04840/) (2021)
- [Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search](https://mlsanity.com/paper/2205.09676/) (2022)
- [An Informative Tracking Benchmark](https://mlsanity.com/paper/2112.06467/) (2021)
- [Adaptive Siamese Tracking with a Compact Latent Network](https://mlsanity.com/paper/2302.00930/) (2023)
- [MobilePhys: Personalized Mobile Camera-Based Contactless Physiological Sensing](https://mlsanity.com/paper/2201.04039/) (2022)
- [EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization in Egocentric Vision](https://mlsanity.com/paper/2511.08007/) (2025)
- [Benchmarking Deep Trackers on Aerial Videos](https://mlsanity.com/paper/2103.12924/) (2021)
- [Updatable Siamese Tracker with Two-stage One-shot Learning](https://mlsanity.com/paper/2104.15049/) (2021)
- [Learning to Adapt to Unseen Abnormal Activities under Weak Supervision](https://mlsanity.com/paper/2203.13610/) (2022)
- [Real-Time Visual Object Tracking via Few-Shot Learning](https://mlsanity.com/paper/2103.10130/) (2021)
- [Deep Convolutional Correlation Iterative Particle Filter for Visual Tracking](https://mlsanity.com/paper/2107.02984/) (2021)
- [Learning Online for Unified Segmentation and Tracking Models](https://mlsanity.com/paper/2111.06994/) (2021)
- [Context-aware Visual Tracking with Joint Meta-updating](https://mlsanity.com/paper/2204.01513/) (2022)
- [MAML MOT: Multiple Object Tracking based on Meta-Learning](https://mlsanity.com/paper/2405.07272/) (2024)

## Abstract (arXiv)

This paper improves state-of-the-art visual object trackers that use online adaptation. Our core contribution is an offline meta-learning-based method to adjust the initial deep networks used in online adaptation-based tracking. The meta learning is driven by the goal of deep networks that can quickly be adapted to robustly model a particular target in future frames. Ideally the resulting models focus on features that are useful for future frames, and avoid overfitting to background clutter, small parts of the target, or noise. By enforcing a small number of update iterations during meta-learning, the resulting networks train significantly faster. We demonstrate this approach on top of the high performance tracking approaches: tracking-by-detection based MDNet and the correlation based CREST. Experimental results on standard benchmarks, OTB2015 and VOT2016, show that our meta-learned versions of both trackers improve speed, accuracy, and robustness.