Results 111 to 120 of about 192,101 (191)

R3Net: Recursive Residual Refinement Network Architecture for Decoder‐Free Medical Image Segmentation

Precision Radiation Oncology, Volume 10, Issue 3, Page 319-332, September 2026.
We propose R3Net, a decoder‐free medical image segmentation framework that recursively refines multiscale representations within the encoder using residual pathways. R3Net achieves competitive accuracy with reduced model complexity and improved computational efficiency across multiple medical imaging modalities.
Jing Huang, Yongkang Zhao, Yuhan Li, Zhitao Dai, Cheng Chen, Qiying Lai   +5 more
wiley   +1 more source

Transformer face recognition method based on multi-level feature fusion

四川大学学报. 自然科学版
The convolutional operation in a convolutional neural network only captures local information, whereas the Transformer retains more spatial information and can create long-range connections of images. In the application of vision field, Transformer lacks
XIA Gui-Shu, ZHU Zi-Han, WEI Yong-Chao, ZHU Hong-Chao, XU Wei-Qi   +4 more
doaj  

SE‐Swin: An improved Swin‐Transfomer network of self‐ensemble feature extraction framework for image retrieval

IET Image Processing
The Swin‐Transformer is a variant of the Vision Transformer, which constructs a hierarchical Transformer that computes representations with shifted windows and window multi‐head self‐attention.
Yixuan Xu, Xianbing Wang, Hua Zhang, Hai Lin   +3 more
doaj   +1 more source

Precise delineation of radiation targets for thoracic tumors in the immunotherapy era: From immune mechanisms to clinical practice

Precision Radiation Oncology, Volume 10, Issue 3, Page 371-387, September 2026.
RT‐immunotherapy synergy for thoracic tumors relies on precise target delineation to protect immune components. IFI, reduced volumes, and optimized positioning minimize damage, while multimodal imaging, DL, PBT, and FLASH‐RT enhance control. These innovations shift RT to an immune‐centric model, improving lung and esophageal cancer outcomes.
Xiaoying Chen, Minxiao Yi, Yu Deng, Qian Shen   +3 more
wiley   +1 more source

Transformers meet CNNs for insights into breast mass classification from histopathological images

Frontiers in Artificial Intelligence
IntroductionBreast cancer remains one of the leading causes of cancer-related deaths among women worldwide, highlighting the critical need for accurate histopathological diagnosis and reliable decision-support systems to improve diagnostic sensitivity ...
Vatsala Anand, Ajay Khajuria
doaj   +1 more source

Image Databases for Pollen Grain Classification: Availability, Quality, and Challenges

WIREs Data Mining and Knowledge Discovery, Volume 16, Issue 3, September 2026.
Overview of the study process, from identifying gaps in pollen image databases to a systematic search across six libraries, resulting in 73 final studies, 18 datasets (10 public), and a seven‐point standardization framework proposed under FAIR principles.
Heloise Acco Tives Bedin, Simone de Ramos, André Roberto Ortoncelli, Paula Fernandes Montanher, Patricia A. Jaques   +4 more
wiley   +1 more source

Swin Transformer With Spatial and Local Context Augmentation for Enhanced Semantic Segmentation of Remote Sensing Images

IEEE Open Journal of Signal Processing
Semantic segmentation of remote sensing images is extensively used in crop cover and type analysis, and environmental monitoring. In the semantic segmentation of remote sensing images, owning to the specificity of remote sensing images, not only the ...
Rong-Xing Ding, Yi-Han Xu, Gang Yu, Wen Zhou, Ding Zhou   +4 more
doaj   +1 more source

Time Series Domain Adaptation: A Review

WIREs Data Mining and Knowledge Discovery, Volume 16, Issue 3, September 2026.
This survey provides a comprehensive and systematic review of TSDA methods from the perspectives of access‐privacy constraints, category‐space semantics, and source‐target topology, three orthogonal axes that unify existing approaches within a common taxonomy.
M. T. Furqon, Mahardhika Pratama, Wisnu Jatmiko   +2 more
wiley   +1 more source

Reidentifikasi Orang pada Data Visible-Infrared Menggunakan Klasifier Swin Transformer

Reidentifikasi orang menjadi topik penelitian yang sangat hanget dalam beberapa tahun terakhir dalam visi komputer. Dalam penelitian ini mengusulkan pendekatan reidentifikasi orang yang menggunakan klasifier Swin Transformer pada data citra visual ...
Maulana, Muhammad Azhar
core  

A Unified Deep Learning Framework for Instance Segmentation Across Diverse Cytological Stains

Cytopathology, Volume 37, Issue 5, Page 493-502, September 2026.
Transformer‐based unified cytology segmentation across Papanicolaou, Feulgen and AgNOR achieves stain‐invariant performance. Mask2Former maximises boundary precision (AP75) on the combined dataset, enabling one model to replace multiple stain‐specific deployments without accuracy loss while simplifying clinical integration.
Luís Otávio Santos, Rodrigo de Paula E. Silva Ribeiro, Bibiana Quatrin Tiellet, Laura Maria Effting Silva, Fabiana Botelho de Miranda Onofre, Alexandre Sherlley Casimiro Onofre, Aldo von Wangenheim   +6 more
wiley   +1 more source