BERT2DAb: a pre-trained model for antibody representation based on amino acid sequences and 2D-structure by Xiaowei Luo, Fan Tong, Wenbin Zhao, Xiangwen Zheng, Jiangyu Li, Jing Li, Dongsheng Zhao

“…Additionally, existing pre-trained models solely rely on embedding representations using amino acids or k-mers, which do not explicitly take into account the role of secondary structure features. …”
Get full text

Fusing Events and Frames with Coordinate Attention Gated Recurrent Unit for Monocular Depth Estimation by Huimei Duan, Chenggang Guo, Yuan Ou

“…Coordinate attention explicitly models inter-channel dependencies and coordinate information in space. …”
Get full text

Modeling the dynamics of two-factor socio-economic states through mappings close to extension by V. V. Egorov

“…The model is intended to be used for informational, forecasting, management and governance purposes in the presence of a sufficient digitalization’s degree of public structures, without which it is problematic to receive and transmit data for building the model, and perform related calculations.…”
Get full text

GOMFuNet: A Geometric Orthogonal Multimodal Fusion Network for Enhanced Prediction Reliability by Yi Guo, Rui Zhong

“…GOMFuNet synergistically combines two core mathematical principles: (1) It utilizes geometric deep learning, specifically Graph Convolutional Networks (GCNs), within its Cross-Modal Label Fusion Module (CLFM) to perform fusion in a high-level semantic label space, thereby preserving inter-sample topological relationships and enhancing robustness to inconsistencies. (2) It incorporates a novel Label Confidence Learning Module (LCLM) derived from optimization theory, which explicitly enhances prediction reliability by enforcing mathematical orthogonality among the predicted class probability vectors, directly minimizing output uncertainty. …”
Get full text

A Hybrid Query Scheme to Speed Up Queries in Unstructured Peer-to-Peer Networks by Zhan Zhang, Yong Tang, Shigang Chen, Ying Jian

Get full text

A weighted difference loss approach for enhancing multi-label classification by Qiong Hu, Masrah Azrifah Azmi Murad, Azreen Bin Azman, Nurul Amelina Nasharuddin

Get full text

HMS-Net: A Hierarchical Multilabel Fine-Grained Ship Detection Network in Remote Sensing Images by Yunchao Yang, Zhengning Zhang, Pengming Feng, Yiming Yan, Guangjun He, Shaobo Liu, Pengyong Zhang, Haorao Gao

“…Furthermore, we design a hierarchical relationship constraint loss function to explicitly model interclass relationships among ships, optimizing feature distance measurements between different classes. …”
Get full text

A Multi-Objective Gray Consistency Correction Method for Mosaicking Regional SAR Intensity Images with Brightness Anomalies by Jiaying Wang, Xin Shen, Deren Li, Litao Li, Yonghua Jiang, Jun Pan, Zezhong Lu, Wei Yao

“…Applying traditional color harmonization methods increases this issue, causing a loss of brightness information. We propose a multi-objective gray consistency correction method designed explicitly for mosaicking regional SAR intensity images with brightness anomalies to address this. …”
Get full text

Overview of Molecular Diagnostics in Irish Clinical Oncology [version 2; peer review: 2 approved] by Patrick Gillespie, Maeve Lowery, Seán O. Hynes, Tyler Medina, Cathal Seoighe, Walter Kolch

“…Methods Through a combination of web scraping, keyword search, and manual review, we performed a full review of all 856 indications included in the 533 therapy regimens published to date by the NCCP to identify therapy indications with explicit molecular criteria. …”
Get full text

Intent-aware knowledge graph-based model for electrical power material recommendation by Lin Zhao, Ning Luan, Weihua Cheng, Shuming Feng, Hui Wang, Yongcheng Yang, Guixiang Zhu

“…However, a notable drawback of current GNN-based recommendation is their inability to explicitly capture users’ intent in recommendations, which limits the performance. …”
Get full text

Adaptive Fixed-Time Practically Tracking Control for n-Link Flexible-Joint Manipulator With Input Quantization and Input Delay via Command Filter-Based Approach by Rongyang Qiu, Meizhen Xia, Jiu Zhang, Chao Ma

Get full text

Hybrid Models for Emotion Classification and Sentiment Analysis in Indonesian Language by Hendri Ahmadian, Taufik F. Abidin, Hammam Riza, Kahlil Muchtar

“…The study utilizes a specialized version of the Bidirectional Encoder Representations from Transformers (BERT) model known as IndoBERT, tailored explicitly for Bahasa Indonesia. It aims to improve accuracy in the Indonesian natural language understanding benchmark by boosting performance in sentiment analysis and emotion classification tasks. …”
Get full text

Joint variation and ZhuYin dataset for Traditional Chinese document enhancement by Shi-Wei Lo, Hsiu-Mei Chou, Jyh-Horng Wu

Get full text

TROLL 4.0: representing water and carbon fluxes, leaf phenology, and intraspecific trait variation in a mixed-species individual-based forest dynamics model – Part 2: Model evaluat... by S. Schmitt, S. Schmitt, S. Schmitt, F. J. Fischer, J. G. C. Ball, N. Barbier, M. Boisseaux, D. Bonal, B. Burban, X. Chen, G. Derroire, G. Derroire, G. Derroire, J. W. Lichstein, D. Nemetschek, N. Restrepo-Coupe, S. Saleska, G. Sellan, P. Verley, G. Vincent, C. Ziegler, J. Chave, I. Maréchaux

“…Here we evaluate the performance of TROLL 4.0 for two Amazonian sites with contrasting soil and climate properties. …”
Get full text

DuSAFNet: A Multi-Path Feature Fusion and Spectral–Temporal Attention-Based Model for Bird Audio Classification by Zhengyang Lu, Huan Li, Min Liu, Yibin Lin, Yao Qin, Xuanyu Wu, Nanbo Xu, Haibo Pu

“…This work lays the foundation for scalable, automated acoustic monitoring to inform biodiversity assessments and conservation planning.…”
Get full text

SIG-ShapeFormer: A Multi-Scale Spatiotemporal Feature Fusion Network for Satellite Cloud Image Classification by Xuan Liu, Zhenyu Lu, Bingjian Lu, Zhuang Li, Zhongfeng Chen, Yongjie Ma

“…However, most existing models—such as those based on convolutional neural networks (CNNs), Transformer architectures, and their variants like Swin Transformer—primarily focus on spatial modeling of static images and do not explicitly incorporate temporal information, thereby limiting their ability to effectively integrate spatiotemporal features. …”
Get full text

Enhanced Viral Genome Classification Using Large Language Models by Hemalatha Gunasekaran, Nesaian Reginal Wilfred Blessing, Umar Sathic, Mohammad Shahid Husain

Get full text

Hierarchical contrastive learning for multi-label text classification by Wei Zhang, Yun Jiang, Yun Fang, Shuai Pan

Get full text

A bit closer to the past: the three-dimensionalization of an Inca ceremony in the north Calchaquí Valley (Salta, Argentina) by Alejandro Andrés Ferrari, Joaquín Ignacio Izaguirre, Félix Alejandro Acuto

“…Like other expansive polities, the expansion of the Inca empire across the highlands and lowlands of South America is not only a history of trade and warfare, but also of mesmerizing public performances that yielded new and memorable experiences. …”
Get full text

Multibranch Adaptive Fusion Graph Convolutional Network for Traffic Flow Prediction by Xin Zan, Jasmine Siu Lee Lam

“…Experimentally, the newly designed multibranch can efficaciously utilize the prior information of different temporal scales. Our MBAF-GCN achieved better performance in the comparative model, indicating its potential and validity.…”
Get full text