当前位置: X-MOL 学术J. Electron. Imaging › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
SiamPAT: Siamese point attention networks for robust visual tracking
Journal of Electronic Imaging ( IF 1.0 ) Pub Date : 2021-09-01 , DOI: 10.1117/1.jei.30.5.053001
Hang Chen 1 , Weiguo Zhang 1 , Danghui Yan 1
Affiliation  

Attention mechanism originates from the study of human visual behavior, which has been widely used in various fields of artificial intelligence in recent years and has become an important part of neural network structure. Many attention mechanism-based trackers have gained improved performance in both accuracy and robustness. However, these trackers cannot suppress the influence of background information and distractors accurately and do not enhance the target object information, which limits the performance of these trackers. We propose new Siamese point attention (SPA) networks for robust visual tracking. SPA networks learn position attention and channel attention jointly on two branch information. To construct point attention, each point on the template feature is used to calculate the similarity on the search feature. The similarity calculation is based on the local information of the target object, which can reduce the influence of background, deformation, and rotation factors. We can obtain the region of interest by calculating the position attention from point attention. Position attention is integrated into the calculation of channel attention to reduce the influence of irrelevant areas. In addition, we also propose the object attention, and integrate it into the classification and regression module to further enhance the semantic information of the target object and improve the tracking accuracy. Extensive experiments are also conducted on five benchmark datasets. The experiment results show that our method achieves state-of-the-art performance.

中文翻译:

SiamPAT:用于稳健视觉跟踪的连体点注意网络

注意机制起源于对人类视觉行为的研究,近年来广泛应用于人工智能的各个领域,成为神经网络结构的重要组成部分。许多基于注意力机制的跟踪器在准确性和鲁棒性方面都获得了改进。然而,这些跟踪器不能准确地抑制背景信息和干扰物的影响,也没有增强目标对象信息,这限制了这些跟踪器的性能。我们提出了新的连体点注意 (SPA) 网络以进行稳健的视觉跟踪。SPA 网络在两个分支信息上联合学习位置注意力和通道注意力。为了构建点注意力,模板特征上的每个点都用于计算搜索特征上的相似度。相似度计算基于目标物体的局部信息,可以减少背景、变形、旋转等因素的影响。我们可以通过从点注意力计算位置注意力来获得感兴趣的区域。将位置注意力整合到渠道注意力的计算中,以减少无关区域的影响。此外,我们还提出了对象注意力,并将其集成到分类和回归模块中,以进一步增强目标对象的语义信息,提高跟踪精度。还对五个基准数据集进行了广泛的实验。实验结果表明,我们的方法达到了最先进的性能。变形和旋转因素。我们可以通过从点注意力计算位置注意力来获得感兴趣的区域。将位置注意力整合到渠道注意力的计算中,以减少无关区域的影响。此外,我们还提出了对象注意力,并将其集成到分类和回归模块中,以进一步增强目标对象的语义信息,提高跟踪精度。还对五个基准数据集进行了广泛的实验。实验结果表明,我们的方法达到了最先进的性能。变形和旋转因素。我们可以通过从点注意力计算位置注意力来获得感兴趣的区域。将位置注意力整合到渠道注意力的计算中,以减少无关区域的影响。此外,我们还提出了对象注意力,并将其集成到分类和回归模块中,以进一步增强目标对象的语义信息,提高跟踪精度。还对五个基准数据集进行了广泛的实验。实验结果表明,我们的方法达到了最先进的性能。此外,我们还提出了对象注意力,并将其集成到分类和回归模块中,以进一步增强目标对象的语义信息,提高跟踪精度。还对五个基准数据集进行了广泛的实验。实验结果表明,我们的方法达到了最先进的性能。此外,我们还提出了对象注意力,并将其集成到分类和回归模块中,以进一步增强目标对象的语义信息,提高跟踪精度。还对五个基准数据集进行了广泛的实验。实验结果表明,我们的方法达到了最先进的性能。
更新日期:2021-09-01
down
wechat
bug