Detecting time-series anomalies is extremely intricate due to the rarity of anomalies and imbalanced sample categories, which often result in costly and challenging anomaly labeling. Most of the existing approaches largely depend on assumptions of normality, overlooking labeled abnormal samples. While anomaly assumptions based methods can incorporate prior knowledge of anomalies for data augmentation in training classifiers, the adopted random or coarse-grained augmentation approaches solely focus on pointwise anomalies and lack cutting-edge domain knowledge, making them less likely to achieve better performance. This paper introduces CutAddPaste, a novel anomaly assumption-based approach for detecting time-series anomalies. It primarily employs a data augmentation strategy to generate pseudo anomalies, by exploiting prior knowledge of anomalies as much as possible. At the core of CutAddPaste is cutting patches from random positions in temporal subsequence samples, adding linear trend terms, and pasting them into other samples, so that it can well approximate a variety of anomalies, including point and pattern anomalies. Experiments on standard benchmark datasets demonstrate that our method outperforms the state-of-the-art approaches.

3D point cloud registration is a crucial technology for 3D scene reconstruction and has been successfully applied in various domains, such as smart healthcare and intelligent transportation. With theoretical analysis, we find that geometric structural relationships are essential for 3D point cloud registration. The 3D point cloud registration method achieves excellent performance only when fusing local and global features with geometric structure information. Based on these discoveries, we propose a 3D point cloud registration method based on geometric structure embedding into the attention mechanism (GraM), which can extract the local features of the non-critical point and global features of the corresponding point containing geometric structure information. According to the local and global features, the simple regression operation can obtain the transformation matrix of point cloud pairs, thereby eliminating the semantics that ignores the geometric structure relationship. GraM surpasses the state-of-the-art results by 0.548° and 0.915° regarding the relative rotation error on ModelNet40 and LowModelNet40, respectively.

《地球科学》(ISSN 1000-2383;CN42-1874/P) (原刊名《地球科学——中国地质大学学报》ISSN 1000-2383;CN42-1233/P)，创刊于1957年，是由教育部主管、中国地质大学主办的综合性地学学术理论期刊，月刊，2015年改名为《地球科学》,她以反映中国地质大学教学与科研最新的、高水平的基础地质、应用地质、资源与环境地质及地学工程技术研究成果为主要任务。

Fine-grained image classification constitutes a long-standing challenge, with its performance bottlenecks stemming primarily from high inter-class similarity and insufficient discriminative feature. Feature augmentation alleviates this constraint through cross-image feature fusion, and as an online augmentation approach, integrates seamlessly into network architectures without requiring independent training phases. However, existing methods typically exhibit either random region selection mechanisms or constrained spatial awareness. Such inherent shortcomings critically constrain their ability to generate adequately capacity discriminative feature necessary for fine-grained classification. To this end, we propose CFBoost, a feature augmentation method that incorporates spatial-geometrical coordination to generate diverse features with sufficient capacity. It adaptively modulates spatial-geometric properties within fusion regions while simultaneously constructing feature-capacity-aware semantic labels. CFBoost integrates three core strategies: precisely locating fusion regions and positions to prevent occlusion of essential features, independently smoothing edges in all orientations of the fusion region to mitigate strong edge effects, and generating soft labels from a semantic weight matrix to improve the representational capacity of sample labels. Experiments across four benchmark datasets demonstrate CFBoost's superiority, achieving an average improvement of 2.48% relative to the optimal baseline, with particularly pronounced performance gains on images containing dispersed high-capacity regions.

The accumulation of time-series data and the absence of labels make time-series Anomaly Detection (AD) a self-supervised deep learning task. Single-normality-assumption-based methods, which reveal only a certain aspect of the whole normality, are incapable of tasks involved with a large number of anomalies. Specifically, Contrastive Learning (CL) methods distance negative pairs, many of which consist of both normal samples, thus reducing the AD performance. Existing multi-normality-assumption-based methods are usually two-staged, firstly pre-training through certain tasks whose target may differ from AD, limiting their performance. To overcome the shortcomings, a deep Contrastive One-Class Anomaly detection method of time series (COCA) is proposed by authors, following the normality assumptions of CL and one-class classification. It treats the original and reconstructed representations as the positive pair of negative-sample-free CL, namely "sequence contrast". Next, invariance terms and variance terms compose a contrastive one-class loss function in which the loss of the assumptions is optimized by invariance terms simultaneously and the "hypersphere collapse" is prevented by variance terms. In addition, extensive experiments on two real-world time-series datasets show the superior performance of the proposed method achieves state-of-the-art.