We present a new deep dictionary learning and coding network (DDLCN) for image-
recognition tasks with limited data. The proposed DDLCN has most of the standard deep …

Despite the noteworthy advancements in the field of transfer dictionary learning, a
comprehensive survey remains conspicuously absent. Moreover, since cross-domain …

Most existing methods for visual domain adaptation need to convert high-order tensors into
one-order high-dimensional vectors through naive vectorization operations. However, they …

Cross-domain fault diagnosis methods have been extensively investigated to improve
practical engineering implications for data-driven models. However, the annotated data in …

Abstract Most feature-based Unsupervised Domain Adaptation (UDA) methods aligned
distributions of the source and target domains by minimizing Maximum Mean Discrepancy …

实际应用中脑电信号一直面临采集成本高, 用户间差异大等问题, 制约着基于脑电信号的运动
想象领域的发展. 针对跨受试者运动想象脑电信号识别任务, 本研究提出了一种基于集成式 …

In recent years, with the development of social media, image recognition has been widely
used in the fields of video analysis, object detection and image retrieval. However, due to …

图像识别中数据来源复杂, 不同领域的数据在分布上存在差异等问题. 为提高跨领域图像的识别
能力, 提出了一种基于投影重构的领域适应字典对学**方法. 该方法采用交叉重构技术构建新的 …