Accurate 2D multi-person pose estimation remains challenging due to issues such as occlusion, missing body parts, and low resolution, particularly in complex backgrounds. This paper proposes an refinement network for multi-person pose estimation through the complementary fusion of extended local receptive fields and contextual information. The proposed cascaded dilated convolution module (DCM) expands the local receptive field through geometric perception, addressing the issue of feature ambiguity in low-resolution and small-scale human bodies. Simultaneously, a hybrid self-attention module (HSM) is introduced to integrate the semantic relevance of joints and precise spatial location information by parallelly combining convolutional self-attention (CSA) and coordinate attention (CA). This optimizes localization through semantic association, not only reducing background interference but also resolving the problem of overlapping joints in multi-person scenarios. Consequently, the network framework achieves an effective balance between the accuracy of human feature extraction at different scales and computational speed. Extensive experiments conducted on the MS COCO and CrowdPose datasets demonstrate that the proposed network architecture outperforms comparable methods, exhibiting superior robustness and computational performance in high-density crowd scenes, uneven lighting conditions, and complex texture scenarios. The related code and models are available at https://github.com/Twl-GZ/Human-pose .

Convolutional neural network (CNN) and Transformer-based hybrid models have been successfully applied to hyperspectral image (HSI) classification, enhancing the local feature extraction capability of single Transformer-based models. However, these Transformers in the hybrid models suffer from structural redundancy in components such as positional encoding (PE) and multi-layer perceptron (MLP). To address the issue, we propose a novel attention architecture termed twice attention convolution module and simplified Transformer (TAST) for HSI classification. The proposed TAST primarily consists of a twice attention convolution module (TACM) and a simplified Transformer. TACM is designed to improve the ability to extract local features. In addition, we introduce the simplified Transformer by removing the PE and MLP components from the original Transformer, which captures long-range dependencies while simplifying the structure of the original Transformer. Experimental results on four public datasets demonstrate that the proposed TAST model outperforms both state-of-the-art CNN and Transformer models in terms of classification performance, with improvements in terms of overall accuracy (OA) around 3.87%-34.95% (Indian Pines), 0.35%-23.43% (Salinas), 0.37%-6.05% (WHU-Hi-LongKou), and 0.65%-10.79% (WHU-Hi-HongHu).

The authenticity of audio-visual content is being challenged by advanced multimedia editing technologies inspired by Artificial Intelligence-Generated Content (AIGC). Temporal forgery localization aims to detect suspicious contents by locating forged segments. So far, most of the existing methods are based on Convolutional Neural Networks (CNNs) or Transformers, yet neither of them has fully considered the complex relationships within forged audio-visual content. To address this issue, in this paper, we propose a novel method, named TransHFC, which innovatively introduces hypergraphs to model group relationships among segments while considering point-to-point relationships through Transformers. Through its dual hypergraph filtering convolution branch, TransHFC captures both temporal and spatial level group relationships, enhancing the representation of forged segment features. Furthermore, we propose a new hypergraph filtering convolution Auto-Encoder that uses a multi-frequency filter bank for adaptive signal capture. This design compensates for the limitation of a single hypergraph filter. Our extensive experiments on Lav-DF, TVIL, Psynd, and HAD datasets demonstrate that TransHFC achieves state-of-the-art performance.

Deep learning-based hyperspectral image (HSI) classification models typically utilize multiple feature extraction layers to learn the features of land covers. Nevertheless, they encounter challenges, e.g., 1) Transformers require substantial computational resources, and 2) these layers are carefully assembled and designed. Recently, large kernel convolutional neural networks (LKCNNs) show excellent performance in natural visual tasks. To tackle these limitations and explore the capability of LKCNNs for HSI classification, we present a novel simple and powerful multi-scale large kernel convolutional neural network architecture (MSLKCNN) with the largest kernel size as large as 15 × 15, in contrast to commonly used 3 × 3, for HSI classification. MSLKCNN avoids these specialized designs, comprising a noise suppression module (NSM) and a multi-scale large kernel convolution (MSLKC). Specifically, NSM is first used to suppress the noise and reduce the number of the bands before extracting the features. Then, MSLKC, as the only feature extraction layer of MSLKCNN, joints three parallel convolutions to capture the features of various types (i.e. spectral, spectral-spatial) and ranges (i.e., small local, larger local, and global) from the dimension of scale: (C1) convolution with a kernel size of 1 × 1 is used to extract spectral features; (C2) multi-scale large kernel depthwise separable convolution (MLKDC) is proposed to learn the spectral-spatial features of different ranges including short-range, middle-range, and long-range; and (C3) multi-scale dilated depthwise separable convolution (MDDC) is designed to aggregate the spectral-spatial features between land covers at various distances. Extensive experimental results on three public HSI datasets demonstrate the competitiveness of the proposed MSLKCNN compared with several state-of-the-art methods.

Abstract Recently, with graph neural networks (GNNs) becoming a powerful technique for graph representation, many excellent GNN-based models have been proposed for processing heterogeneous graphs, which are termed Heterogeneous graph neural networks (HGNNs). However, existing HGNNs tend to aggregate information from either direct neighbors or those connected by short metapaths, thereby neglecting the higher-order information and global feature similarity information in heterogeneous graphs. In this paper, we propose a Multi-View Heterogeneous graph neural network (MV-HGNN) to aggregate these information. Firstly, two auxiliary views, specifically a global feature similarity view and a graph diffusion view, are generated from the original heterogeneous graph. Secondly, MV-HGNN performs two message-passing strategies to get the representation of different views. Subsequently, a transformer-based aggregator is used to get the semantic information. Subsequently, the representations of the three views are fused into a final composite representation. We evaluate our method on the node classification task over three commonly used heterogeneous graph datasets, and the results demonstrate that our proposed MV-HGNN significantly outperforms state-of-the-art baselines.

Graph convolutional network (GCN) has attracted increasing attention in hyperspectral image (HSI) classification due to its capability to capture the long-range correlations between adjacent land covers. Most GCN-based HSI classification methods have been proposed to address the four limitations (shape-fixed kernel, massive calculations and parameters, limited classification ability with limited labeled samples, and difficulty to capture the long-term relationships of land covers) of convolutional neural networks (CNNs) by operating on superpixel-based nodes. However, the pixels in each superpixel share the spectral-spatial features, overlooking the unique characteristics of individual pixels. To address these limitations of GCN and CNN and fully exploit their advantages, we propose a novel multibranch attention framework (MFAF), in which the specially designed GCN and CNN branches learn the complementary spectral-spatial features. Specifically, we develop a multiscale attentional GCN to enhance the ability to understand the long-range correlations between land covers, accomplished by constructing the multiscale attentional adjacency matrix. Then, based on the two designs of the dual-branch depthwise separable convolution (DSC) and the attention-based residual block, we present a new complementary dual convolutional attention network that extracts more discriminative spectral-spatial features of pixels. Finally, we introduce an attention-based fusion pooling (AFP) mechanism to combine the features generated by different network branches. Extensive experimental evaluations on four public HSI datasets demonstrate that the proposed MFAF achieves better performance than several state-of-the-art methods, delivering superior and consistent results in terms of overall accuracy (OA), average accuracy (AA), and kappa coefficient (KAPPA).

Abstract Incomplete Multi-View Clustering (IMVC) attempts to give an optimal clustering solution for incomplete multi-view data that suffer from missing instances in certain views. However, most existing IMVC methods still have various drawbacks in practical applications, such as arbitrary incomplete scenarios cannot be handled; the computational cost is relatively high; most valuable nonlinear relations among samples are often ignored; complementary information among views is not sufficiently exploited. To address the above issues, in this paper, we present a novel and flexible unified graph learning framework, called Multiple Kernel-based Anchor Graph coupled low-rank Tensor learning for Incomplete Multi-View Clustering (MKAGT_IMVC), whose goal is to adaptively learn the optimal unified similarity matrix from all incomplete views. Specifically, according to the characteristics of incomplete multi-view data, MKAGT_IMVC innovatively improves an anchor selection strategy. Then, a novel cross-view anchor graph fusion mechanism is introduced to construct multiple fused complete anchor graphs, which captures more the intra-view and inter-view nonlinear relations. Moreover, a graph learning model combining low-rank tensor constraint and consensus graph constraint is developed, where all fused complete anchor graphs are regarded as prior knowledge to initialize this model. Extensive experiments conducted on eight incomplete multi-view datasets clearly show that our method delivers superior performance relative to some state-of-the-art methods in terms of clustering ability and time-consuming.

Summary The information propagation mechanism in graph‐structured networks such as social networks is the foundation of network security. The graph convolutional network (GCN) is a powerful approach for semisupervised node classification on graph‐structure data. The vertex features which pass through the graph network are affected by the k‐hop neighborhood vertices. However, current high‐order GCN approaches merged the k‐hop neighborhood using coarse pooling and complicated weight parameters. To reduce the computational complexity and preserve topological of the graph data, with weight sharing mechanism we propose a novel GCN based on a novel higher‐order pooling layer for semisupervised classification. The proposed model and its variants are experimental studied on several large‐scale citation network datasets using semisupervised learning. The experimental results show that the proposed model and its variants have lower computational complexity and achieve the state‐of‐the‐art in the node classification accuracy.

Real photograph denoising is extremely challenging in low-level computer vision since the noise is sophisticated and cannot be fully modeled by explicit distributions. Although deep-learning techniques have been actively explored for this issue and achieved convincing results, most of the networks may cause vanishing or exploding gradients, and usually entail more time and memory to obtain a remarkable performance. This article overcomes these challenges and presents a novel network, namely, PID controller guide attention neural network (PAN-Net), taking advantage of both the proportional-integral-derivative (PID) controller and attention neural network for real photograph denoising. First, a PID-attention network (PID-AN) is built to learn and exploit discriminative image features. Meanwhile, we devise a dynamic learning scheme by linking the neural network and control action, which significantly improves the robustness and adaptability of PID-AN. Second, we explore both the residual structure and share-source skip connections to stack the PID-ANs. Such a framework provides a flexible way to feature residual learning, enabling us to facilitate the network training and boost the denoising performance. Extensive experiments show that our PAN-Net achieves superior denoising results against the state-of-the-art in terms of image quality and efficiency.

Summary Recent studies have demonstrated that network community structure can significantly reduce the network transport efficiency. In this paper, the weakening community structure (WCS) strategy based on adding of edges that can effectively weaken the network community characteristics and improve the network transport efficiency is proposed. The WCS performance was validated by experiments, which were performed on pseudo‐random network, scale‐free artificial network with community structures, and real internet, using the shortest path routing and the local routing. The experimental results have demonstrated that the WCS strategy can greatly improve the network load capacity and reduce the average length of the shortest path by adding a small amount of edges between communities. The proposed mechanism not only provides the improvement of network transport efficiency but also can be adapted for restraining of malicious information propagation through the network.