Pedestrian detection method based on improved YOLOv5 by Shangtao You, Zhenchao Gu, Kai Zhu

“…However, pedestrian detection suffers from occlusion and small target. First, the HorNet to improve the higher-order spatial interaction capability of the model, expand the effective sensory field, and enhance the feature extraction of pedestrians. …”
Get full text

Automatic Stylized Action Generation in Animation Using Deep Learning by Xiaoyu Su, Hyung-Gi Kim

“…Specifically, our method combines labeled and unlabeled animation data to train stylization models, employing spatiotemporal graph convolutional networks (ST-GCN) and StyleNet modules. The ST-GCN leverages the topological information of the character skeleton to enhance network representation capabilities, while StyleNet modules enable the transfer of both global and local styles. …”
Get full text

Traditional guidance mechanism based deep robust watermarking by Xuejing GUO, Yixiang FANG, Yi ZHAO, Tianzhu ZHANG, Wenchao ZENG, Junxiang WANG

“…With the development of network and multimedia technology, multimedia data has gradually become a key source of information for people, making digital media the primary battlefield for copyright protection and anti-counterfeit traceability.Digital watermarking techniques have been widely studied and recognized as important tools for copyright protection.However, the robustness of conventional digital watermarking methods is limited as sensitive digital media can easily be affected by noise and external interference during transmission.Then the existing powerful digital watermarking technology’s comprehensive resistance to all forms of attacks must be enhanced.Moreover, the conventional robust digital watermarking algorithm’s generalizability across a variety of image types is limited due to its embedding method.Deep learning has been widely used in the development of robust digital watermarking systems due to its self-learning abilities.However, current initialization techniques based on deep neural networks rely on random parameters and features, resulting in low-quality model generation, lengthy training times, and potential convergence issues.To address these challenges, a deep robust digital watermarking algorithm based on a traditional bootstrapping mechanism was proposed.It combined the benefits of both traditional digital watermarking techniques and deep neural networks, taking into account their learning abilities and robust characteristics.The algorithm used the classic robust digital watermarking algorithm to make watermarked photos, and the constructed feature guaranteed the resilience of traditional watermarked images.The final dense image was produced by fusing the conventionally watermarked image with the deep network using the U-Net structure.The testing results demonstrate that the technique can increase the stego image’s resistance to various attacks and provide superior visual quality compared to the conventional algorithm.…”
Get full text

An Explainable Deep Learning Network for Environmental Microorganism Classification Using Attention-Enhanced Semi-Local Features by R. Karthik, Armaano Ajay, Akshaj Singh Bisht, Jaehyuk Cho, V. E. Sathishkumar

Get full text

Co-occurrence feature learning for visual recognition of immature leukocytes by Yi-Ting Hsiao, Si-Wa Chan, Yen-Chieh Ouyang, Ju-Huei Chien

“…Finally, DCONN extracts spatial texture information using a co-occurrence matrix to improve classification accuracy. …”
Get full text

DeepU-Net: A Parallel Dual-Branch Model for Deeply Fusing Multiscale Features for Road Extraction From High-Resolution Remote Sensing Images by Guoqing Zhou, Haiyang Zhi, Ertao Gao, Yanling Lu, Jianjun Chen, Yuhang Bai, Xiao Zhou

“…Therefore, this article introduces a dual-branch deep fusion network, named “DeepU-Net,” for obtaining global and local information in parallel. …”
Get full text

Lightweight Deep Learning Model, ConvNeXt-U: An Improved U-Net Network for Extracting Cropland in Complex Landscapes from Gaofen-2 Images by Shukuan Liu, Shi Cao, Xia Lu, Jiqing Peng, Lina Ping, Xiang Fan, Feiyu Teng, Xiangnan Liu

“…ConvNeXt-U retains the U-shaped structure of U-Net but replaces the encoder with a simplified ConvNeXt architecture. …”
Get full text

Enhanced diabetic retinopathy detection using U-shaped network and capsule network-driven deep learning by Govindharaj I, Poongodai A, Gnanajeyaraman Rajaram, Santhakumar D, Ravichandran S, Vijaya Prabhu R, Udayakumar K, Yazhinian S

Get full text

Enhancing semantic segmentation of Ecuadorian shrimp ponds through fine-tuned vision transformers and U-Net architectures utilizing open-source remote sensing data by Daniel Jacome, Jianghao Wang, Yong Ge

Get full text

CausalCervixNet: convolutional neural networks with causal insight (CICNN) in cervical cancer cell classification—leveraging deep learning models for enhanced diagnostic accuracy by Zahra Taghados, Zohreh Azimifar, Malihezaman Monsefi, Mojgan Akbarzadeh Jahromi

“…This study introduces CausalCervixNet, a Convolutional Neural Network with Causal Insight (CICNN) tailored for cervical cancer cell classification. …”
Get full text

MHAGuideNet: a 3D pre-trained guidance model for Alzheimer’s Disease diagnosis using 2D multi-planar sMRI images by Yuanbi Nie, Qiushi Cui, Wenyuan Li, Yang Lü, Tianqing Deng

“…Results The proposed MHAGuideNet is tested using two datasets: the ADNI and OASIS datasets. …”
Get full text

FloodNet-Lite: A Lightweight Deep Learning for Flood Mapping Using Remote Sensing Data With Optimized UNet and Edge Deployment Approach in 6G by Puviyarasi Thirugnanasammandamoorthi, Debabrata Ghosh, Ram Kishan Dewangan, Mohammad Kamrul Hasan, Khairul Akram Zainol Ariffin, Huda Saleh Abbas, Hashim Elshafie, Rashid A. Saeed, Ala Eldin Awouda

Get full text

How do GPs and patients share the responsibility for cancer safety netting follow-up actions? A qualitative interview study of GPs and patients in Oxfordshire, UK by Clare Bankhead, Sue Ziebland, Daniel Jones, Brian D Nicholson, Charlotte Albury, Julie Evans, John I Macartney

“…Objective To explore patients’ and General Practitioners' (GPs) accounts of how responsibility for follow-up was perceived and shared in their experiences of cancer safety netting occurring within the past 6 months.Design In-depth interviews were recorded and transcribed verbatim. …”
Get full text

Rising Net Shortwave Radiation and Land Surface Temperature Drive Snow Cover Phenology Shifts Across the Mongolian Plateau During the 2000–2022 Hydrological Years by Xiaona Chen, Shiqiu Lin

“…Attribution analysis demonstrates that 47.72% of <i>D</i>_e variability stems from increased net shortwave radiation (+0.38 Wm⁻² yr⁻¹) and rising temperatures (+0.06 °C yr⁻¹) during the melting season, with net shortwave radiation exerting stronger control (<i>R</i>² = 0.73) than temperature (<i>R</i>² = 0.63). …”
Get full text

Study of genetic parameters and relationships between agronomic and physiological traits in Kabuli type chickpea genotypes under drought stress by Hadi Afzali, Mehdi Mohayeji, Hassan Farhbakhsh

“…However, highest CVg belonged to stomatal conductance and net photosynthesis in drought stress condition. …”
Get full text

AED-Net: A High-Resolution Remote Sensing Image Road Extraction Method Integrating Atrous Spatial Pyramid Pooling and Efficient Channel Attention Mechanism by Jintong Ren, Lizhi Liu, Zixuan Xia, Yang Liu

“…Furthermore, ablation studies validate the effectiveness and necessity of the proposed improvements. In summary, AED-Net has made significant progress in multi-scale feature extraction, boundary information restoration, and critical feature learning, offering new insights and solutions for the development of road network extraction technologies. …”
Get full text

BioAug-Net: a bioimage sensor-driven attention-augmented segmentation framework with physiological coupling for early prostate cancer detection in T2-weighted MRI by Muhammad Arshad, Chengliang Wang, Muhammad Wajeeh Us Sima, Jamshed Ali Shaikh, Hanen Karamti, Raed Alharthi, Julius Selecky

Get full text

SPCB-Net: A Multi-Scale Skin Cancer Image Identification Network Using Self-Interactive Attention Pyramid and Cross-Layer Bilinear-Trilinear Pooling by Xin Qian, Tengfei Weng, Qi Han, Chen Wu, Hongxiang Xu, Mingyang Hou, Zicheng Qiu, Baoping Zhou, Xianqiang Gao

Get full text

Quantitative evaluation of flood extent detection using attention U-Net case studies from Eastern South Wales Australia in March 2021 and July 2022 by Falah Fakhri, Ioannis Gkanatsios

“…This research proposes an innovative approach to applying an attention U-Net on SAR datasets to detect and extract flood extent maps. …”
Get full text

The mosquito vectors that sustained malaria transmission during the Magude project despite the combined deployment of indoor residual spraying, insecticide-treated nets and mass-dr... by Lucía Fernández Montoya, Helena Martí-Soler, Mara Máquina, Kiba Comiche, Inocencia Cuamba, Celso Alafo, Lizette L Koekemoer, Ellie Sherrard-Smith, Quique Bassat, Beatriz Galatas, Pedro Aide, Nelson Cuamba, Dulcisaria Jotamo, Francisco Saúte, Krijn P Paaijmans

“…The "Magude project" aimed but failed to interrupt local malaria transmission in Magude district, southern Mozambique, by using a comprehensive package of interventions, including indoor residual spraying (IRS), pyrethroid-only long-lasting insecticide treated nets (LLINs) and mass-drug administration (MDA). …”
Get full text