Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

TrackingNet SUC

TrackingNet SUC is a quantitative performance metric in computer vision that measures how accurately and reliably a visual tracking algorithm tracks target objects across the large-scale TrackingNet benchmark dataset. Calculated as the area under the curve of a success plot, it reflects the percentage of video frames in which the intersection over union overlap between the predicted bounding box and the ground truth bounding box meets or exceeds varying thresholds from zero to one. By averaging these overlap rates across the entire test set, this metric provides a standardized overall score representing a tracking model localization precision, robustness, and ability to handle diverse real-world tracking challenges.

1 item

SwinTrack: A Simple and Strong Baseline for Transformer Tracking

SwinTrack: A Simple and Strong Baseline for Transformer Tracking

Liting Lin, Heng Fan, Zhipeng Zhang, Yong Xu, Haibin Ling

OrganizationsDiDi ChuxingPeng Cheng LaboratorySouth China University of TechnologyStony Brook UniversityUniversity of North Texas

Why you should read this

Presents a fully attentional Siamese tracking baseline that unifies Transformer-based feature extraction, fusion, and historical trajectory encoding to achieve state-of-the-art visual tracking accuracy and speed.

Recently Transformer has been largely explored in tracking and shown state-of-the-art (SOTA) performance. However, existing efforts mainly focus on fusing and enhancing features generated by convolutional neural networks (CNNs). The potential of Transformer in representation learning remains under-explored. In this paper, we aim to further unleash the power of Transformer by proposing a simple yet efficient fully-attentional tracker, dubbed SwinTrack, within classic Siamese framework. In particular, both representation learning and feature fusion in SwinTrack leverage the Transformer architecture, enabling better feature interactions for tracking than pure CNN or hybrid CNN-Transformer frameworks. Besides, to further enhance robustness, we present a novel motion token that embeds historical target trajectory to improve tracking by providing temporal context. Our motion token is lightweight with negligible computation but brings clear gains. In our thorough experiments, SwinTrack exceeds existing approaches on multiple benchmarks. Particularly, on the challenging LaSOT, SwinTrack sets a new record with 0.713 SUC score. It also achieves SOTA results on other benchmarks. We expect SwinTrack to serve as a solid baseline for Transformer tracking and facilitate future research. Our codes and results are released at https://github.com/LitingLin/SwinTrack.

Added

2026-09-26