Visual object tracking is a fundamental component of transportation systems, especially for intelligent driving. Despite achieving state-of-the-art performance in visual tracking, recent single-branch trackers tend to overlook the weak prior assumptions associated with the Vision Transformer (ViT) encoder and inference pipeline in visual tracking. Moreover, the effectiveness of discriminative trackers remains constrained due to the adoption of the dual-branch pipeline. To tackle the inferior effectiveness of vanilla ViT, we propose an Adaptive ViT Model Prediction tracker (AViTMP) to design a customised tracking method. This method bridges the single-branch network with discriminative models for the first time. Specifically, in the proposed encoder AViT encoder, we introduce a tracking-tailored Adaptor module for vanilla ViT and a joint target state embedding to enrich the target-prior embedding paradigm. Then, we combine the AViT encoder with a discriminative transformer-specific model predictor to predict the accurate location. Furthermore, to mitigate the limitations of conventional inference practice, we present a novel inference pipeline called CycleTrack, which bolsters the tracking robustness in the presence of distractors via bidirectional cycle tracking verification. In the experiments, we evaluated AViTMP on eight tracking benchmarks for a comprehensive assessment, including LaSOT, LaSOTExtSub, AVisT, etc. The experimental results unequivocally establish that, under fair comparison, AViTMP achieves state-of-the-art performance, especially in terms of long-term tracking and robustness.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Tracking


    Beteiligte:
    Tang, Chuanming (Autor:in) / Wang, Kai (Autor:in) / van de Weijer, Joost (Autor:in) / Zhang, Jianlin (Autor:in) / Huang, Yongmei (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.02.2025


    Format / Umfang :

    3449872 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Transformer Sub-Patch Matching for High-Performance Visual Object Tracking

    Tang, Chuanming / Hu, Qintao / Zhou, Gaofan et al. | IEEE | 2023


    SPECIFIC OBJECT TRACKING DEVICE AND SPECIFIC OBJECT TRACKING SYSTEM

    YAMAMOTO KAZUMA / MASUDA MAKOTO | Europäisches Patentamt | 2020

    Freier Zugriff

    Parallel Visual Tracking

    Roberts, J. / Charnley, D. / IFAC | British Library Conference Proceedings | 1993


    Feature Tracking For Visual Odometry

    HUNT SHAWN | Europäisches Patentamt | 2019

    Freier Zugriff

    Special Issue on Visual Tracking

    Mei, Xue / Zhang, Tianzhu / Lu, Huchuan et al. | British Library Online Contents | 2016