Non-target information also matters: InverseFormer tracker for single object tracking

IF 4.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Image and Vision Computing Pub Date : 2026-04-01 Epub Date: 2026-02-08 DOI:10.1016/j.imavis.2026.105922

Qiuhang Gu , Baopeng Zhang , Zhu Teng , Hongwei Xu

{"title":"Non-target information also matters: InverseFormer tracker for single object tracking","authors":"Qiuhang Gu , Baopeng Zhang , Zhu Teng , Hongwei Xu","doi":"10.1016/j.imavis.2026.105922","DOIUrl":null,"url":null,"abstract":"<div><div>Visual object tracking has been significantly improved by Transformer-based methods. However, most existing trackers perform target-oriented inference, which enhances target-relevant features while ignoring non-target features. We argue that non-target information also contains abundant clues that can provide significant guidance for tracking inference. In this work, we propose a novel InverseFormer tracker constructed by stacking multiple InverseFormer blocks. The proposed InverseFormer block consists of a context aggregation unit and an inverse enhancement unit. The former aggregates local context correlation information while boosting tracking efficiency. The latter enhances the template-search image pair by using non-target information in the search region, which significantly suppresses background-relevant features while preserving target details, leading to more accurate tracking. Extensive experiments conducted on seven benchmarks demonstrate that our tracker outperforms state-of-the-art methods at a real-time speed of 45 FPS.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"168 ","pages":"Article 105922"},"PeriodicalIF":4.2000,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Image and Vision Computing","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0262885626000284","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2026/2/8 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

Visual object tracking has been significantly improved by Transformer-based methods. However, most existing trackers perform target-oriented inference, which enhances target-relevant features while ignoring non-target features. We argue that non-target information also contains abundant clues that can provide significant guidance for tracking inference. In this work, we propose a novel InverseFormer tracker constructed by stacking multiple InverseFormer blocks. The proposed InverseFormer block consists of a context aggregation unit and an inverse enhancement unit. The former aggregates local context correlation information while boosting tracking efficiency. The latter enhances the template-search image pair by using non-target information in the search region, which significantly suppresses background-relevant features while preserving target details, leading to more accurate tracking. Extensive experiments conducted on seven benchmarks demonstrate that our tracker outperforms state-of-the-art methods at a real-time speed of 45 FPS.

查看原文本刊更多论文

非目标信息也很重要：用于单目标跟踪的InverseFormer跟踪器

基于transformer的视觉目标跟踪方法得到了显著改进。然而，大多数现有的跟踪器执行面向目标的推理，增强了与目标相关的特征，而忽略了非目标特征。我们认为，非目标信息也包含了丰富的线索，可以为跟踪推理提供重要的指导。在这项工作中，我们提出了一种新的InverseFormer跟踪器，该跟踪器由多个InverseFormer块堆叠而成。所提出的InverseFormer块由上下文聚合单元和逆增强单元组成。前者聚合了本地上下文相关信息，提高了跟踪效率。后者通过在搜索区域使用非目标信息来增强模板搜索图像对，在保留目标细节的同时显著抑制背景相关特征，从而提高跟踪精度。在七个基准测试上进行的大量实验表明，我们的跟踪器在45 FPS的实时速度下优于最先进的方法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Image and Vision Computing 工程技术-工程：电子与电气

CiteScore

8.50

自引率

8.50%

发文量

143

审稿时长

7.8 months

期刊介绍： Image and Vision Computing has as a primary aim the provision of an effective medium of interchange for the results of high quality theoretical and applied research fundamental to all aspects of image interpretation and computer vision. The journal publishes work that proposes new image interpretation and computer vision methodology or addresses the application of such methods to real world scenes. It seeks to strengthen a deeper understanding in the discipline by encouraging the quantitative comparison and performance evaluation of the proposed methodology. The coverage includes: image interpretation, scene modelling, object recognition and tracking, shape analysis, monitoring and surveillance, active vision and robotic systems, SLAM, biologically-inspired computer vision, motion analysis, stereo vision, document image understanding, character and handwritten text recognition, face and gesture recognition, biometrics, vision-based human-computer interaction, human activity and behavior understanding, data fusion from multiple sensor inputs, image databases.