Related papers: Benchmarking SAM2-based Trackers on FMOX

Benchmarking SAM2-based Trackers on FMOX

URL: http://arxiv.org/abs/2512.09633v1
Date: Wed, 10 Dec 2025 13:21:09 GMT
Title: Benchmarking SAM2-based Trackers on FMOX
Authors: Senem Aktas, Charles Markham, John McDonald, Rozenn Dahyot,
Abstract summary: We propose to benchmark high performing trackers (SAM2, EfficientTAM, DAM4SAM and SAMURAI) on datasets containing fast moving objects (FMO)<n>Overall the trackers DAM4SAM and SAMURAI perform well on more challenging sequences.
Score: 1.5866079116942815
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Several object tracking pipelines extending Segment Anything Model 2 (SAM2) have been proposed in the past year, where the approach is to follow and segment the object from a single exemplar template provided by the user on a initialization frame. We propose to benchmark these high performing trackers (SAM2, EfficientTAM, DAM4SAM and SAMURAI) on datasets containing fast moving objects (FMO) specifically designed to be challenging for tracking approaches. The goal is to understand better current limitations in state-of-the-art trackers by providing more detailed insights on the behavior of these trackers. We show that overall the trackers DAM4SAM and SAMURAI perform well on more challenging sequences.

Related papers

Accurate Planar Tracking With Robust Re-Detection [17.216623635232928]
We present SAM-H and WOFTSAM, novel planar trackers that combine robust long-term segmentation tracking provided by SAM 2 with 8 degrees-of-freedom homography pose estimation.<n>The proposed methods are evaluated on POT-210 and PlanarTrack tracking benchmarks, setting the new state-of-the-art performance on both.<n>We also present improved ground-truth annotations of initial PlanarTrack poses, enabling more accurate benchmarking in the high-precision p@5 metric.
arXiv Detail & Related papers (2026-02-23T09:13:55Z)
SAM 2++: Tracking Anything at Any Granularity [47.958995827908105]
We present SAM 2++, a unified model towards tracking at any granularity, including masks, boxes, and points.<n>To extend target granularity, we design task-specific prompts to encode various task inputs into general prompt embeddings.<n>To satisfy memory matching, we introduce a task-adaptive memory mechanism that unifies memory across different granularities.
arXiv Detail & Related papers (2025-10-21T17:20:15Z)
Distractor-Aware Memory-Based Visual Object Tracking [17.945503249662675]
We propose a distractor-aware drop-in memory module and introspection-based management method for SAM2.<n>Our design effectively reduces the tracking drift toward distractors and improves redetection capability after object occlusion.<n>We show DAM4SAM outperforms SAM2.1 on thirteen benchmarks and sets new state-of-the-art results on ten.
arXiv Detail & Related papers (2025-09-17T09:54:27Z)
SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Tracking [58.35852822355312]
Visual Object Tracking (VOT) is widely used in applications like autonomous driving to continuously track targets in videos.<n>To address these issues, some methods propose to adapt the video foundation model SAM2 for VOT, where the tracking results of each frame would be encoded as memory for conditioning the rest of frames in an autoregressive manner.<n>We present a SAMITE model, built upon SAM2 with additional modules, to tackle these challenges.
arXiv Detail & Related papers (2025-07-29T12:11:56Z)
SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation [11.1906749425206]
Segment Anything 2 (SAM2) enables robust single-object tracking using segmentation.<n>We propose SAM2MOT, a novel Tracking by paradigm for multi-object tracking.<n> SAM2MOT directly generates tracking boxes from segmentation masks, reducing reliance on detection accuracy.
arXiv Detail & Related papers (2025-04-06T15:32:08Z)
Underwater Camouflaged Object Tracking Meets Vision-Language SAM2 [60.47622353256502]
We propose the first large-scale multi-modal underwater camouflaged object tracking dataset, namely UW-COT220.<n>Based on the proposed dataset, this work first evaluates current advanced visual object tracking methods, including SAM- and SAM2-based trackers, in challenging underwater environments.<n>Our findings highlight the improvements of SAM2 over SAM, demonstrating its enhanced ability to handle the complexities of underwater camouflaged objects.
arXiv Detail & Related papers (2024-09-25T13:10:03Z)
Segment and Track Anything [57.20918630166862]
This report presents a framework called Segment And Track Anything (SAMTrack) SAM-Track allows users to precisely and effectively segment and track any object in a video. It can be used across an array of fields, ranging from drone technology, autonomous driving, medical imaging, augmented reality, to biological analysis.
arXiv Detail & Related papers (2023-05-11T04:33:08Z)
OmniTracker: Unifying Object Tracking by Tracking-with-Detection [119.51012668709502]
OmniTracker is presented to resolve all the tracking tasks with a fully shared network architecture, model weights, and inference pipeline. Experiments on 7 tracking datasets, including LaSOT, TrackingNet, DAVIS16-17, MOT17, MOTS20, and YTVIS19, demonstrate that OmniTracker achieves on-par or even better results than both task-specific and unified tracking models.
arXiv Detail & Related papers (2023-03-21T17:59:57Z)
TAO: A Large-Scale Benchmark for Tracking Any Object [95.87310116010185]
Tracking Any Object dataset consists of 2,907 high resolution videos, captured in diverse environments, which are half a minute long on average. We ask annotators to label objects that move at any point in the video, and give names to them post factum. Our vocabulary is both significantly larger and qualitatively different from existing tracking datasets.
arXiv Detail & Related papers (2020-05-20T21:07:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.