跳到主要导航 跳到搜索 跳到主要内容

HTACPE: A Hybrid Transformer With Adaptive Content and Position Embedding for Sample Learning Efficiency of Hyperspectral Tracker

  • Northwestern Polytechnical University Xian

科研成果: 期刊稿件 › 文章 › 同行评审

23 引用 (Scopus)

摘要

Transformer architecture has demonstrated significant potential in hyperspectral object tracking by leveraging global correlation learning to accurately represent the data distribution. However, existing hyperspectral object trackers based on transformer models typically rely on costly pre-trained models, making them prone to crashing due to overfitting when tuned on small-scale hyperspectral videos, greatly limiting their performance. To address this challenge, in this paper, a Hybrid Transformer with Adaptive Content and Position Embedding (HTACPE) tracker is proposed to improve the learning efficiency of the tracking model, and fully explore the spectral-spatial information. Specifically, an Adaptive Content and Position Embedding Module (ACPEM) is designed to dynamically learn the balance between focusing on positional and content-based information, which allows the model to effectively handle datasets of various sizes. To enhance the spectral-spatial information, a Spectral Grouping Module (SGM) is designed to learn the high-frequency information in complex scenarios, thereby enhancing diversified features. It operates in parallel with the ACPEM feature learning module. Furthermore, a Dynamic Reliability Refinement Module (DRRM) is incorporated to address challenges related to accurate object position perception, iteratively refining prediction parameters to enhance the reliability of the model. Extensive experiments demonstrate that the proposed HTACPE achieves satisfactory tracking performance both qualitatively and quantitatively, especially with insufficient training data.

源语言英语
页(从-至)2384-2398
页数15
期刊IEEE Transactions on Multimedia
卷27
DOI
出版状态已出版 - 2025

学术指纹

探究 'HTACPE: A Hybrid Transformer With Adaptive Content and Position Embedding for Sample Learning Efficiency of Hyperspectral Tracker' 的科研主题。它们共同构成独一无二的学术指纹。

引用此