Chunjuan Bo^1,*, Xin Chen², Junxing Zhang¹

CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 1105-1122, 2024, DOI:10.32604/cmc.2024.052329 - 18 July 2024

Abstract Significant advancements have been witnessed in visual tracking applications leveraging ViT in recent years, mainly due to the formidable modeling capabilities of Vision Transformer (ViT). However, the strong performance of such trackers heavily relies on ViT models pretrained for long periods, limiting more flexible model designs for tracking tasks. To address this issue, we propose an efficient unsupervised ViT pretraining method for the tracking task based on masked autoencoders, called TrackMAE. During pretraining, we employ two shared-parameter ViTs, serving as the appearance encoder and motion encoder, respectively. The appearance encoder encodes randomly masked image data,… More >

Yannan Cai, Ke Tan, Zhenzhong Wei^*

CMC-Computers, Materials & Continua, Vol.75, No.1, pp. 1621-1640, 2023, DOI:10.32604/cmc.2023.036177 - 06 February 2023

Abstract Label assignment refers to determining positive/negative labels for each sample to supervise the training process. Existing Siamese-based trackers primarily use fixed label assignment strategies according to human prior knowledge; thus, they can be sensitive to predefined hyperparameters and fail to fit the spatial and scale variations of samples. In this study, we first develop a novel dynamic label assignment (DLA) module to handle the diverse data distributions and adaptively distinguish the foreground from the background based on the statistical characteristics of the target in visual object tracking. The core of DLA module is a two-step… More >