# Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking

arXiv: https://arxiv.org/abs/2505.18111 · HTML: https://mlsanity.com/paper/2505.18111/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 14 of 14)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [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)
- [Learning Spatio-Temporal Transformer for Visual Tracking](https://mlsanity.com/paper/2103.17154/) (2021)
- [Visual Prompt Multi-Modal Tracking](https://mlsanity.com/paper/2303.10826/) (2023)
- [SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory](https://mlsanity.com/paper/2411.11922/) (2024)
- [Multi-Modal Fusion for End-to-End RGB-T Tracking](https://mlsanity.com/paper/1908.11714/) (2019)
- [SiamMask: A Framework for Fast Online Object Tracking and Segmentation](https://mlsanity.com/paper/2207.02088/) (2022)
- [Enhancing Multi-Camera People Tracking with Anchor-Guided Clustering and Spatio-Temporal Consistency ID Re-Assignment](https://mlsanity.com/paper/2304.09471/) (2023)
- [GTA: Global Tracklet Association for Multi-Object Tracking in Sports](https://mlsanity.com/paper/2411.08216/) (2024)
- [Sea You Later: Metadata-Guided Long-Term Re-Identification for UAV-Based Multi-Object Tracking](https://mlsanity.com/paper/2311.03561/) (2023)
- [Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Check](https://mlsanity.com/paper/2407.13937/) (2024)

## Abstract (arXiv)

We present an effective approach for adapting the Segment Anything Model 2 (SAM2) to the Visual Object Tracking (VOT) task. Our method leverages the powerful pre-trained capabilities of SAM2 and incorporates several key techniques to enhance its performance in VOT applications. By combining SAM2 with our proposed optimizations, we achieved a first place AUC score of 89.4 on the 2024 ICPR Multi-modal Object Tracking challenge, demonstrating the effectiveness of our approach. This paper details our methodology, the specific enhancements made to SAM2, and a comprehensive analysis of our results in the context of VOT solutions along with the multi-modality aspect of the dataset.