Fusion of syntactic enhancement and semantic enhancement for aspect-based sentiment analysis by LIU Yao, WU Yunfei, ZHOU Hongjing, HUANG Shaonian, ZHANG Zhen

“…The graph neural networks mainly focus on the syntactic structure when they are used to model the syntactic dependency tree of a sentence for aspect-based sentiment analysis (ABSA). …”
Get full text

Fusion of syntactic enhancement and semantic enhancement for aspect-based sentiment analysis by LIU Yao, WU Yunfei, ZHOU Hongjing, HUANG Shaonian, ZHANG Zhen

“…The graph neural networks mainly focus on the syntactic structure when they are used to model the syntactic dependency tree of a sentence for aspect-based sentiment analysis (ABSA). …”
Get full text

A Synergistic CNN-DF Method for Landslide Susceptibility Assessment by Jiangang Lu, Yi He, Lifeng Zhang, Qing Zhang, Jiapeng Tang, Tianbao Huo, Yunhao Zhang

“…The complex structures and intricate hyperparameters of existing deep learning (DL) models make achieving higher accuracy in landslide susceptibility assessment (LSA) time-consuming and labor-intensive. …”
Get full text

Aircraft Multi-stage Altitude Prediction Under Satellite Signal Loss by Mengchan HUANG, Qiang MIAO

“…LTCA efficiently exploited attention mechanisms to extract key features from multi-dimensional flight parameter data samples through adaptive global average pooling (GAP) and one-dimensional convolution, considering global and local information. …”
Get full text

Vision Transformers (ViTs) for Feature Extraction and Classification of AI-Generated Visual Designs by Qing Yun

Get full text

Coseismic Landslide Mapping Based on Trans-UNet and Transfer Learning by Tianhe Ren, Wenping Gong, Jun Chen, Liang Gao, Jiahao Wu, Xuyang Xiang

“…The Trans-UNet model integrates a UNet-like encoder–decoder structure with a Transformer module to enhance global context extraction, a U-shaped full-scale feature extraction module to preserve multiscale spatial details, and a convolutional decoder for effective feature fusion and resolution restoration. …”
Get full text

Action recognition using part and attention enhanced feature fusion by Danfeng Zhuang, Min Jiang, Lei Wang, Mohamed Sanim Akremi, Hedi Tabia

Get full text

Swin-GAT Fusion Dual-Stream Hybrid Network for High-Resolution Remote Sensing Road Extraction by Hongkai Zhang, Hongxuan Yuan, Minghao Shao, Junxin Wang, Suhong Liu

“…By decoupling detailed feature extraction from global context modeling, the proposed framework more faithfully represents complex road structures. …”
Get full text

Enhancing leaf disease classification using GAT-GCN hybrid model by Shyam Sundhar, Riya Sharma, Priyansh Maheshwari, Suvidha Rupesh Kumar, T. Sunil Kumar

“…Agriculture plays a critical role in the global economy, providing livelihoods and ensuring food security for billions. …”
Get full text

Single-Image Superresolution for RGB Remote Sensing Imagery via Multiscale CNN-Transformer Feature Fusion by Xudong Yao, Haopeng Zhang, Sizhe Wen, Zhenwei Shi, Zhiguo Jiang

“…MSTB generates multiscale tokens with multiple convolutional layers to obtain multiscale global information. …”
Get full text

Quantifying Interdisciplinarity in Scientific Articles Using Deep Learning Toward a TRIZ-Based Framework for Cross-Disciplinary Innovation by Nicolas Douard, Ahmed Samet, George Giakos, Denis Cavallucci

“…Interdisciplinary research (IDR) is essential for addressing complex global challenges that surpass the capabilities of any single discipline. …”
Get full text

YOLO-AFR: An Improved YOLOv12-Based Model for Accurate and Real-Time Dangerous Driving Behavior Detection by Tianchen Ge, Bo Ning, Yiwu Xie

“…YOLO-AFR builds upon the YOLOv12 architecture and introduces three key innovations: (1) the redesign of the original A2C2f module by introducing a Feature-Refinement Feedback Network (FRFN), resulting in a new A2C2f-FRFN structure that adaptively refines multiscale features, (2) the integration of self-calibrated convolution (SC-Conv) modules in the backbone to enhance multiscale contextual modeling, and (3) the employment of a SEAM-based detection head to improve global contextual awareness and prediction accuracy. …”
Get full text

An explainable hybrid feature aggregation network with residual inception positional encoding attention and EfficientNet for cassava leaf disease classification by M. Sundara Srivathsan, S. Alden Jenish, K. Arvindhan, R. Karthik

Get full text

Urban Land Use Classification Model Fusing Multimodal Deep Features by Yougui Ren, Zhiwei Xie, Shuaizhi Zhai

“…The spectral features and subgraph features are then constructed, and a graph convolutional network (GCN) is utilized to extract the node relational features from both the global and local graphs, forming the topological structure deep features while aggregating local features into global ones. …”
Get full text

Self-Supervised Social Recommendation Algorithm Fusing Residual Networks by WANG Yujie, YANG Zhe

Get full text

Residual Vision Transformer and Adaptive Fusion Autoencoders for Monocular Depth Estimation by Wei-Jong Yang, Chih-Chen Wu, Jar-Ferr Yang

“…In this paper, by using a single camera, we propose an end-to-end supervised monocular depth estimation autoencoder, which contains an encoder with a structure with a mixed convolution neural network and vision transformers and an effective adaptive fusion decoder to obtain high-precision depth maps. …”
Get full text

Advanced AI techniques for classifying Alzheimer’s disease and mild cognitive impairment by Sophie Tascedda, Sophie Tascedda, Sophie Tascedda, Pierfrancesco Sarti, Pierfrancesco Sarti, Veronica Rivi, Claudia Savia Guerrera, Giuseppe Alessio Platania, Mario Santagati, Filippo Caraci, Filippo Caraci, Johanna M. C. Blom, Johanna M. C. Blom

Get full text

Directed Knowledge Graph Embedding Using a Hybrid Architecture of Spatial and Spectral GNNs by Guoqiang Hou, Qiwen Yu, Fan Chen, Guang Chen

“…To address this limitation, a directed spectral graph transformer (DSGT), a hybrid architecture model, is constructed by integrating the graph transformer and directed spectral graph convolution networks. The graph transformer leverages multi-head attention mechanisms to capture the global connectivity of the feature graph from different perspectives in the spatial domain, which bridges the gap between frequency responses and, further, naturally couples the graph transformer and directed graph convolutional neural networks (GCNs). …”
Get full text

Speckle Noise Reduction for Medical Ultrasound Images Using Hybrid CNN-Transformer Network by Anparasy Sivaanpu, Kumaradevan Punithakumar, Rui Zheng, Michelle Noga, Dean Ta, Edmond H. M. Lou, Lawrence H. Le

“…It is integrated into the encoder-decoder structure, allowing the model to focus on both local and global texture structural information. …”
Get full text

Graph-Based Feature Crossing to Enhance Recommender Systems by Congyu Cai, Hong Chen, Yunxuan Liu, Daoquan Chen, Xiuze Zhou, Yuanguo Lin

“…Additionally, ensuring that the crossed features capture both global graph structures and local context is non-trivial, requiring innovative techniques for multi-scale representation learning. …”
Get full text