Turkish scene text recognition: Introducing extensive real and synthetic datasets and a novel recognition model by Serdar Yıldız

“…Existing datasets, regardless of the language, tend to grapple with issues such as limited sample quantity and high noise levels, which considerably restrict the progression and overall efficacy of STR research and applications. …”
Get full text

A U-Shaped Architecture Based on Hybrid CNN and Mamba for Medical Image Segmentation by Xiaoxuan Ma, Yingao Du, Dong Sui

“…In addition, HCMUNet features a redesigned skip connection and a novel attention module that integrates multi-scale features to recover spatial details lost during down-sampling and to promote richer cross-dimensional interactions. …”
Get full text

A Reordering Buffer Management Method at Edge Gateway in Hybrid IP-ICN Multipath Transmission System by Yuqi Liu, Rui Han, Xu Wang

“…This paper proposes a gateway framework for hybrid IP-ICN multipath transmission systems, enabling protocol conversion and quality of service management. A packet reordering module is integrated at the egress gateway to address complex packet disorder issues caused by ICN multipath transmission, thereby enhancing the service quality provided to IP terminals. …”
Get full text

INRNet: Neighborhood Re-Ranking-Based Method for Pedestrian Text-Image Retrieval by Kehao Wang, Yuhui Wang, Lian Xue, Qifeng Li

“…Finally, we input the restructured data into our Implicit Neighborhood Inference (INI) module, utilizing nearest neighbor intersection to optimize retrieval performance. …”
Get full text

Harnessing Spatial-Frequency Information for Enhanced Image Restoration by Cheol-Hoon Park, Hyun-Duck Choi, Myo-Taeg Lim

“…(b) Variants of attention mechanisms have been proposed for high-resolution images in low-level vision tasks, but these methods still require inherently high computational costs. To address these issues, we propose a Frequency-Aware Network (FreANet) for image restoration, which consists of two simple yet effective modules. …”
Get full text

Enhancing Binary Convolutional Neural Networks for Hyperspectral Image Classification by Xuebin Tang, Ke Zhang, Xiaolei Zhou, Lingbin Zeng, Shan Huang

“…EBCNN incorporates an adaptive gradient scaling module that utilizes a multi-scale pyramid squeeze attention (PSA) mechanism during the training phase, which can adjust training gradients flexibly and efficiently. …”
Get full text

DFAST: A Differential-Frequency Attention-Based Band Selection Transformer for Hyperspectral Image Classification by Deren Fu, Yiliang Zeng, Jiahong Zhao

“…Specifically, a Differential-Frequency Attention-based Band Selection Embedding Module (DFASEmbeddings) is designed to extract original spectral, first-order derivative, and frequency domain features via a multi-branch structure. …”
Get full text

DHQ-DETR: Distributed and High-Quality Object Query for Enhanced Dense Detection in Remote Sensing by Chenglong Li, Jianwei Zhang, Bihan Huo, Yingjian Xue

“…In this paper, we propose the DHQ-DETR framework, which addresses these issues by modeling bounding box offsets as distributions. …”
Get full text

YOLOv11-ND: A Method for Identifying Traffic Targets in Nighttime Urban Environments by Danyang Zhu, Hao Zhou, Yunlong Gao, Yongjuan Wang

“…By using nighttime traffic targets as the research object, this paper suggests YOLOv11-ND, an enhanced target recognition method, to address the aforementioned issues. First, based on WTConv, the WTC3k2 module is intended to take the position of C3k2 in the backbone part. …”
Get full text

A critical approach to SDGs through Collaborative Online International Learning: experiences from Canada and Spain by Mari Carmen Campoy-Cubillo, Vivian Jimenez-Estrada

“…The authors provide an account and reflection of their collaboration centered on the institutional challenges and opportunities that currently exist for courses that aim to engage Indigenous and critical/ecological thinking.Results and discussionThe background of the collaboration leads to a detailed analysis of the context of COIL implementation and the reflections on the modules’ development and improvement. Our recommendations are based on lessons learned from the substantive and technical challenges and opportunities on the complexity of teaching about contemporary ecological/social issues, as well as the tools required to inspire future activists.…”
Get full text

CFANet: The Cross-Modal Fusion Attention Network for Indoor RGB-D Semantic Segmentation by Long-Fei Wu, Dan Wei, Chang-An Xu

“…A lightweight skip connection module is designed to fuse low-level and high-level features. …”
Get full text

EPPTA: Efficient partially observable reinforcement learning agent for penetration testing applications by Zegang Li, Qian Zhang, Guangwen Yang

“…We incorporate an implicit belief module in EPPTA, grounded on the belief update formula of the traditional POMDP model, which represents the agent's probabilistic estimation of the current environment state. …”
Get full text

A segmented differential evolution with enhanced diversity and semi-adaptive parameter control by Huarong Xu, Zhiyu Zhang, Qianwei Deng, Shengke Lin

“…Thirdly, new diversity maintenance mechanisms are proposed, including population initialization, shrinkage, and updating, which better ameliorated the conflicting issues of search range and search rate that existed at all stages of the DE variant. …”
Get full text

Complex Indoor Human Detection with You Only Look Once: An Improved Network Designed for Human Detection in Complex Indoor Scenes by Yufeng Xu, Yan Fu

“…The YOLOv8 algorithm is a cutting-edge technology in the field of object detection, but it is still affected by indoor low-light environments and large changes in human scale. To address these issues, this article proposes a novel method based on YOLOv8 called CIHD-YOLO, which is specifically designed for indoor human detection. …”
Get full text

Reinforcement Learning with Multi-Policy Movement Strategy for Weakly Supervised Temporal Sentence Grounding by Shan Jiang, Yuqiu Kong, Lihe Zhang, Baocai Yin

“…To better learn the alignment, we propose a Gaussian-based Dual-Alignment Module (GDAM) which combines the strengths of both scoring-based and reconstruction-based alignment methods, addressing the issues of negative sample bias and language bias. …”
Get full text

Anxiety in Children: The Contribution of Parental Characteristics by Beáta Bécsi, Jenifer Pataki, Gergő József Szőllősi

“…<b>Background/Objectives</b>: The prevalence of behavioral problems and mental health issues, including anxiety, among children is rising, potentially affecting their long-term well-being and social functioning. …”
Get full text

Individual Contribution-Based Spatial-Temporal Attention on Skeleton Sequences for Human Interaction Recognition by Xing Liu, Bo Gao

“…To address the above issues, we propose an innovative method by designing the individual contribution based spatial-temporal attention graph convolutional network. …”
Get full text

Real time weed identification with enhanced mobilevit model for mobile devices by Xiaoyan Liu, Qingru Sui, Zhihui Chen

“…Also, existing methods generally use large, slow multi-layer convolutional networks (CNNs), which are impractical for use on mobile embedded devices. To address those issues, we propose a lightweight weed identification model based on an enhanced MobileViT architecture, effectively balancing high accuracy with real-time performance. …”
Get full text

TEGKT: tendency-enhanced evolution graph KAN transformer for information popularity prediction by Yanchao Liu, Junpeng Gong, Wenchao Song, Chi Zhang, Pengzhou Zhang

“…To overcome the those issues, we introduce a novel Tendency-Enhanced Evolution Graph KAN Transformer framework ( TEGKT ), which is specifically tailored for information popularity prediction. …”
Get full text