# SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory

arXiv: https://arxiv.org/abs/2411.11922 · HTML: https://mlsanity.com/paper/2411.11922/

## Key facts

- Cited by 94 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 53 references that are in the map.
- First posted on arXiv 18 Nov 2024.

## Builds on (most cited first, 30 of 47)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (2018)
- [LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking](https://mlsanity.com/paper/1809.07845/) (2018)
- [Transformer Tracking](https://mlsanity.com/paper/2103.15436/) (2021)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [Learning Spatio-Temporal Transformer for Visual Tracking](https://mlsanity.com/paper/2103.17154/) (2021)
- [Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking](https://mlsanity.com/paper/2203.14360/) (2022)
- [TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild](https://mlsanity.com/paper/1803.10794/) (2018)
- [Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework](https://mlsanity.com/paper/2203.11991/) (2022)
- [BoT-SORT: Robust Associations Multi-Pedestrian Tracking](https://mlsanity.com/paper/2206.14651/) (2022)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [Probabilistic Regression for Visual Tracking](https://mlsanity.com/paper/2003.12565/) (2020)
- [Tracking Anything with Decoupled Video Segmentation](https://mlsanity.com/paper/2309.03903/) (2023)
- [Siamese Box Adaptive Network for Visual Tracking](https://mlsanity.com/paper/2003.06761/) (2020)
- [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://mlsanity.com/paper/2312.00863/) (2023)
- [StableVideo: Text-driven Consistency-aware Diffusion Video Editing](https://mlsanity.com/paper/2308.09592/) (2023)
- [Deeper and Wider Siamese Networks for Real-Time Visual Tracking](https://mlsanity.com/paper/1901.01660/) (2019)
- [AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark](https://mlsanity.com/paper/2410.03051/) (2024)
- [Need for Speed: A Benchmark for Higher Frame Rate Object Tracking](https://mlsanity.com/paper/1703.05884/) (2017)
- [AiATrack: Attention in Attention for Transformer Visual Tracking](https://mlsanity.com/paper/2207.09603/) (2022)
- [LaSOT: A High-quality Large-scale Single Object Tracking Benchmark](https://mlsanity.com/paper/2009.03465/) (2020)
- [Learning Target Candidate Association to Keep Track of What Not to Track](https://mlsanity.com/paper/2103.16556/) (2021)

## Built on by (most cited first, 30 of 94)

- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [A Survey on Vision-Language-Action Models: An Action Tokenization Perspective](https://mlsanity.com/paper/2507.01925/) (2025)
- [A Distractor-Aware Memory for Visual Object Tracking with SAM2](https://mlsanity.com/paper/2411.17576/) (2024)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds](https://mlsanity.com/paper/2503.10625/) (2025)
- [Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos](https://mlsanity.com/paper/2506.05302/) (2025)
- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation](https://mlsanity.com/paper/2504.07962/) (2025)
- [3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks](https://mlsanity.com/paper/2505.05800/) (2025)
- [OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation](https://mlsanity.com/paper/2503.07098/) (2025)
- [Advancing Complex Video Object Segmentation via Progressive Concept Construction](https://mlsanity.com/paper/2507.15852/) (2025)
- [DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving](https://mlsanity.com/paper/2601.01528/) (2026)
- [SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation](https://mlsanity.com/paper/2504.04519/) (2025)
- [Precise Action-to-Video Generation Through Visual Action Prompts](https://mlsanity.com/paper/2508.13104/) (2025)
- [SAM2 for Image and Video Segmentation: A Comprehensive Survey](https://mlsanity.com/paper/2503.12781/) (2025)
- [DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation](https://mlsanity.com/paper/2505.18078/) (2025)
- [SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations](https://mlsanity.com/paper/2512.05905/) (2025)
- [Open-World Object Counting in Videos](https://mlsanity.com/paper/2506.15368/) (2025)
- [iMOVE: Instance-Motion-Aware Video Understanding](https://mlsanity.com/paper/2502.11594/) (2025)
- [MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation](https://mlsanity.com/paper/2503.06700/) (2025)
- [Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting](https://mlsanity.com/paper/2504.05541/) (2025)
- [Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation](https://mlsanity.com/paper/2602.03595/) (2026)
- [Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting](https://mlsanity.com/paper/2503.22204/) (2025)
- [HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis](https://mlsanity.com/paper/2604.03305/) (2026)
- [HiM2SAM: Enhancing SAM2 with Hierarchical Motion Estimation and Memory Optimization towards Long-term Tracking](https://mlsanity.com/paper/2507.07603/) (2025)
- [MoSAM: Motion-Guided Segment Anything Model with Spatial-Temporal Memory Selection](https://mlsanity.com/paper/2505.00739/) (2025)
- [SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Tracking](https://mlsanity.com/paper/2507.21732/) (2025)
- [VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding](https://mlsanity.com/paper/2601.07290/) (2026)
- [A Computer Vision Pipeline for Individual-Level Behavior Analysis: Benchmarking on the Edinburgh Pig Dataset](https://mlsanity.com/paper/2509.12047/) (2025)
- [3AM: 3egment Anything with Geometric Consistency in Videos](https://mlsanity.com/paper/2601.08831/) (2026)

## Abstract (arXiv)

The Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks but faces challenges in visual object tracking, particularly when managing crowded scenes with fast-moving or self-occluding objects. Furthermore, the fixed-window memory approach in the original model does not consider the quality of memories selected to condition the image features for the next frame, leading to error propagation in videos. This paper introduces SAMURAI, an enhanced adaptation of SAM 2 specifically designed for visual object tracking. By incorporating temporal motion cues with the proposed motion-aware memory selection mechanism, SAMURAI effectively predicts object motion and refines mask selection, achieving robust, accurate tracking without the need for retraining or fine-tuning. SAMURAI operates in real-time and demonstrates strong zero-shot performance across diverse benchmark datasets, showcasing its ability to generalize without fine-tuning. In evaluations, SAMURAI achieves significant improvements in success rate and precision over existing trackers, with a 7.1% AUC gain on LaSOText and a 3.5% AO gain on GOT-10k. Moreover, it achieves competitive results compared to fully supervised methods on LaSOT, underscoring its robustness in complex tracking scenarios and its potential for real-world applications in dynamic environments.