SMSTracker:A Self-Calibration Multi-Head Self-Attention Transformer for Visual Object Tracking  

作　　者：Zhongyang Wang Hu Zhu Feng Liu 

机构地区：[1]School of Communications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing,210003,China

出　　处：《Computers, Materials & Continua》2024年第7期605-623,共19页计算机、材料和连续体（英文）

基　　金：supported by the National Natural Science Foundation of China under Grant 62177029;the Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX21_0740),China.

摘　　要：Visual object tracking plays a crucial role in computer vision.In recent years,researchers have proposed various methods to achieve high-performance object tracking.Among these,methods based on Transformers have become a research hotspot due to their ability to globally model and contextualize information.However,current Transformer-based object tracking methods still face challenges such as low tracking accuracy and the presence of redundant feature information.In this paper,we introduce self-calibration multi-head self-attention Transformer(SMSTracker)as a solution to these challenges.It employs a hybrid tensor decomposition self-organizing multihead self-attention transformermechanism,which not only compresses and accelerates Transformer operations but also significantly reduces redundant data,thereby enhancing the accuracy and efficiency of tracking.Additionally,we introduce a self-calibration attention fusion block to resolve common issues of attention ambiguities and inconsistencies found in traditional trackingmethods,ensuring the stability and reliability of tracking performance across various scenarios.By integrating a hybrid tensor decomposition approach with a self-organizingmulti-head self-attentive transformer mechanism,SMSTracker enhances the efficiency and accuracy of the tracking process.Experimental results show that SMSTracker achieves competitive performance in visual object tracking,promising more robust and efficient tracking systems,demonstrating its potential to providemore robust and efficient tracking solutions in real-world applications.

关 键 词：Visual object tracking tensor decomposition TRANSFORMER self-attention 

分 类 号：TN624[电子电信—电路与系统]