# ROAM: Recurrently Optimizing Tracking Model

arXiv: https://arxiv.org/abs/1907.12006 · HTML: https://mlsanity.com/paper/1907.12006/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jul 2019.

## Built on by (most cited first, 28 of 28)

- [Learning Spatio-Temporal Transformer for Visual Tracking](https://mlsanity.com/paper/2103.17154/) (2021)
- [Learning Target Candidate Association to Keep Track of What Not to Track](https://mlsanity.com/paper/2103.16556/) (2021)
- [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)
- [Transforming Model Prediction for Tracking](https://mlsanity.com/paper/2203.11192/) (2022)
- [STMTrack: Template-free Visual Tracking with Space-time Memory Networks](https://mlsanity.com/paper/2104.00324/) (2021)
- [LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search](https://mlsanity.com/paper/2104.14545/) (2021)
- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [Active Learning for Deep Visual Tracking](https://mlsanity.com/paper/2110.13259/) (2021)
- [Siamese Transformer Pyramid Networks for Real-Time UAV Tracking](https://mlsanity.com/paper/2110.08822/) (2021)
- [SiamMask: A Framework for Fast Online Object Tracking and Segmentation](https://mlsanity.com/paper/2207.02088/) (2022)
- [Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens](https://mlsanity.com/paper/2401.01674/) (2024)
- [Ranking-Based Siamese Visual Tracking](https://mlsanity.com/paper/2205.11761/) (2022)
- [SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking](https://mlsanity.com/paper/2105.11237/) (2021)
- [Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking](https://mlsanity.com/paper/2507.07483/) (2025)
- [Tracking by Joint Local and Global Search: A Target-aware Attention based Approach](https://mlsanity.com/paper/2106.04840/) (2021)
- [Learning Localization-aware Target Confidence for Siamese Visual Tracking](https://mlsanity.com/paper/2204.14093/) (2022)
- [VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification](https://mlsanity.com/paper/2512.09646/) (2025)
- [CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search](https://mlsanity.com/paper/2107.03463/) (2021)
- [DeepMix: Online Auto Data Augmentation for Robust Visual Object Tracking](https://mlsanity.com/paper/2104.11585/) (2021)
- [Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking](https://mlsanity.com/paper/2111.11625/) (2021)
- [Leveraging the Power of Data Augmentation for Transformer-based Tracking](https://mlsanity.com/paper/2309.08264/) (2023)
- [Real-Time Visual Object Tracking via Few-Shot Learning](https://mlsanity.com/paper/2103.10130/) (2021)
- [Context-aware Visual Tracking with Joint Meta-updating](https://mlsanity.com/paper/2204.01513/) (2022)
- [Spatio-Temporal Matching for Siamese Visual Tracking](https://mlsanity.com/paper/2105.02408/) (2021)
- [Explicitly Modeling the Discriminability for Instance-Aware Visual Object Tracking](https://mlsanity.com/paper/2110.15030/) (2021)
- [Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking](https://mlsanity.com/paper/2112.14016/) (2021)
- [Learning Tracking Representations from Single Point Annotations](https://mlsanity.com/paper/2404.09504/) (2024)

## Abstract (arXiv)

In this paper, we design a tracking model consisting of response generation and bounding box regression, where the first component produces a heat map to indicate the presence of the object at different positions and the second part regresses the relative bounding box shifts to anchors mounted on sliding-window locations. Thanks to the resizable convolutional filters used in both components to adapt to the shape changes of objects, our tracking model does not need to enumerate different sized anchors, thus saving model parameters. To effectively adapt the model to appearance variations, we propose to offline train a recurrent neural optimizer to update tracking model in a meta-learning setting, which can converge the model in a few gradient steps. This improves the convergence speed of updating the tracking model while achieving better performance. We extensively evaluate our trackers, ROAM and ROAM++, on the OTB, VOT, LaSOT, GOT-10K and TrackingNet benchmark and our methods perform favorably against state-of-the-art algorithms.