In recent years, a surge of criminal activities with cross-cryptocurrency trades have emerged in Ethereum, the second-largest public blockchain platform. Most of the existing anomaly detection methods utilize the traditional machine learning with feature engineering or graph representation learning technique to capture the information in transaction network. However, these methods either ignore the timestamp information and the transaction flow direction information in transaction network or only consider single transaction network, the cross-cryptocurrency trading patterns in Ethereum are usually ignored. In this paper, we introduce a Multi-layer Temporal Transaction Anomaly Detection (MT $$^2$$2 AD) model in Ethereum network with graph neural network. Specifically, for a given Ethereum token transaction network, we first extract its initial features including the structure subgraph and edge’s feature. Then, we model the temporal information in subgraph as a series of network snapshots according to the timestamp on each edge and time window. To capture the cross-cryptocurrency trading patterns, we combine the snapshots from multiple token transactions at a given timestamp, and we consider it as a new combined graph. We further use the graph convolution encoder with attention mechanism and pooling operation on this new graph to obtain the graph-level embedding, and we transform the anomaly detection on dynamic multi-layer Ethereum transaction networks as a graph classification task with these graph-level embeddings. MT $$^2$$2 AD can integrate the transaction structure feature, edge’s feature and cross-cryptocurrency trading patterns into a framework to perform the anomaly detection with graph neural networks. Experiments on three real-world multi-layer transaction networks show that the proposed MT $$^2$$2 AD (0.8789 Precision, 0.9375 Recall, 0.4987 FbMacro and 0.9351 FbWeighted) can achieve the best performance on most evaluation metrics in comparison with some competing approaches, and the effectiveness in consideration of multiple tokens is also demonstrated.

Cylindrical panorama stitching is able to generate high resolution images of a scene with a wide field-of-view (FOV), making it a useful scene representation for applications like environmental sensing and robot localization. Traditional image stitching methods based on hand-crafted features are effective for constructing a cylindrical panorama from a sequence of images in the case when there are sufficient reliable features in the scene. However, these methods are unable to handle low-texture environments where no reliable feature correspondence can be established. This paper proposes a novel two-step image alignment method based on deep learning and iterative optimization to address the above issue. In particular, a light-weight end-to-end trainable convolutional neural network (CNN) architecture called ShiftNet is proposed to estimate the initial shifts between images, which is further optimized in a sub-pixel refinement procedure based on a specified camera motion model. Extensive experiments on a synthetic dataset, rendered photo-realistic images, and real images were carried out to evaluate the performance of our proposed method. Both qualitative and quantitative experimental results demonstrate that cylindrical panorama stitching based on our proposed image alignment method leads to significant improvements over traditional feature based methods and recent deep learning based methods for challenging low-texture environments.

Nowadays, Artificial Intelligence Generated Content (AIGC) has shown promising prospects in both computer vision and natural language processing communities. Meanwhile, as an essential aspect of AIGC, image to captions has received much more attention. Recent vision-language research is developing from the bulky region visual representations based on object detectors toward more convenient and flexible grid ones. However, this kind of research typically concentrates on image understanding tasks like image classification, with less attention paid to content generation tasks. In this paper, we explore how to capitalize on the expressive features embedded in the grid visual representations for better image captioning. To this end, we present a Transformer-based image captioning model, dubbed FeiM, with two straightforward yet effective designs. We first design the feature queries that consist of a limited set of learnable vectors, which act as the local signals to capture specific visual information from global grid features. Then, taking augmented global grid features and the local feature queries as inputs, we develop a feature interaction module to query relevant visual concepts from grid features, and to enable interaction between the local signal and overall context. Finally, the refined grid visual representations and the linguistic features pass through a Transformer architecture for multi-modal fusion. With the two novel and simple designs, FeiM can fully leverage meaningful visual knowledge to improve image captioning performance. Extensive experiments are performed on the competitive MSCOCO benchmark to confirm the effectiveness of the proposed approach, and the results show that FeiM yields more eminent results than existing advanced captioning models.

Point cloud completion aims to reconstruct the complete 3D shape from incomplete point clouds, and it is crucial for tasks such as 3D object detection and segmentation. Despite the continuous advances in point cloud analysis techniques, feature extraction methods are still confronted with apparent limitations. The sparse sampling of point clouds, used as inputs in most methods, often results in a certain loss of global structure information. Meanwhile, traditional local feature extraction methods usually struggle to capture the intricate geometric details. To overcome these drawbacks, we introduce PointCFormer, a transformer framework optimized for robust global retention and precise local detail capture in point cloud completion. This framework embraces several key advantages. First, we propose a relation-based local feature extraction method to perceive local delicate geometry characteristics. This approach establishes a fine-grained relationship metric between the target point and its k-nearest neighbors, quantifying each neighboring point's contribution to the target point's local features. Secondly, we introduce a progressive feature extractor that integrates our local feature perception method with self-attention. Starting with a denser sampling of points as input, it iteratively queries long-distance global dependencies and local neighborhood relationships. This extractor maintains enhanced global structure and refined local details, without generating substantial computational overhead. Additionally, we develop a correction module after generating point proxies in the latent space to reintroduce denser information from the input points, enhancing the representation capability of the point proxies. PointCFormer demonstrates state-of-the-art performance on several widely used benchmarks.

Accurate traffic prediction is pivotal when constructing intelligent cities to enhance urban mobility and to efficiently manage traffic flows. Traditional deep learning-based traffic prediction models primarily focus on capturing spatial and temporal dependencies, thus overlooking the existence of spatial and temporal heterogeneities. Heterogeneity is a crucial inherent characteristic of traffic data for the practical applications of traffic prediction. Spatial heterogeneities refer to the differences in traffic patterns across different regions, e.g., variations in traffic flow between office and commercial areas. Temporal heterogeneities refer to the changes in traffic patterns across different time steps, e.g., from morning to evening. Although existing models attempt to capture heterogeneities through predefined handcrafted features, multiple sets of parameters, and the fusion of spatial–temporal graphs, there are still some limitations. We propose a self-supervised learning-based traffic prediction framework called Traffic Prediction with Self-Supervised Learning (TPSSL) to address this issue. This framework leverages a spatial–temporal encoder for the prediction task and introduces adaptive data masking to enhance the robustness of the model against noise disturbances. Moreover, we introduce two auxiliary self-supervised learning paradigms to capture spatial heterogeneities and temporal heterogeneities, which also enrich the embeddings of the primary prediction task. We conduct experiments on four widely used traffic flow datasets, and the results demonstrate that TPSSL achieves state-of-the-art performance in traffic prediction tasks.