Results 71 to 80 of about 10,492 (229)

Upsampling DINOv2 Features for Unsupervised Vision Tasks and Weakly Supervised Materials Segmentation

Advanced Intelligent Systems, EarlyView.
Feature from recent image foundation models (DINOv2) are useful for vision tasks (segmentation, object localization) with little or no human input. Once upsampled, they can be used for weakly supervised micrograph segmentation, achieving strong results when compared to classical features (blurs, edge detection) across a range of material systems.
Ronan Docherty, Antonis Vamvakeros, Samuel J. Cooper   +2 more
wiley   +1 more source

Orbital Resizing

Arquivos Brasileiros de Oftalmologia, 2023
Procianoy, Fernando, Cruz, Antonio Augusto Velasco e   +1 more
openaire   +2 more sources

Hiding in Plain Sight: Rethinking the Size and Complexity of Iron Age Hillforts in NW Iberia Thanks to Aerial Archaeology and Geophysics

Archaeological Prospection, EarlyView.
ABSTRACT This paper tackles one key limitation in the analysis of Iron Age communities in the Northwestern Iberian Peninsula: the limited exploration of areas beyond the fortified settlements known as castros (hillforts). The vast majority of archaeological studies have focused exclusively on the areas inside the walls of these settlements, which are ...
César Parcero‐Oubiña, Carlos Otero‐Vilariño, María Gómez‐Faro, Jesús Ignacio Jiménez Chaparro, Pastor Fábrega‐Álvarez, Juan Torrejón‐Valdelomar, Marta Crespo‐Fernández, David González‐Álvarez   +7 more
wiley   +1 more source

Real‐time lithology identification while drilling based on drill cuttings image analysis with ensemble learning

Deep Underground Science and Engineering, EarlyView.
A lithology identification while drilling method was developed, integrating an automated cuttings sampling system, a smart drilling rig, and an ensemble learning model. Underground trials achieved 97.42% accuracy in real‐time identification of cuttings lithology and composition, enhancing hazard management and supporting unmanned drilling technology in
Kun Li, Ting Ren, Ningping Yao, Jon Roberts, Haitao Song, Zhongbei Li, Xueqiu He, Liang Zhao   +7 more
wiley   +1 more source

Sustainable Live Sound Monitoring and Classification System Enabled by a Triboelectric Nanogenerator and Machine Learning Techniques

ENERGY &ENVIRONMENTAL MATERIALS, EarlyView.
A high‐performance Triboelectric Nanogenerator (TENG) acoustic sensor using polyimine/graphite polypropylene (PI/GP) was developed for real‐time, sustainable sound monitoring and classification. The self‐powered device delivers 25.67 μW output power, 92.7% accuracy with MobileNet V1, and powers a wireless transmission circuit, demonstrating dual ...
Majid Haji Bagheri, Araz Rajabi‐Abhari, Owen Gibbs, Pengcheng Xi, Asif Abdullah Khan, Fangzheng Huang, Md Soyaeb Hassan, Ning Yan, Dayan Ban   +8 more
wiley   +1 more source

ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking [PDF]

, 2023
Yutong Kou, Jin Gao, Bing Li, Gang Wang, Weiming Hu, Yizheng Wang, Liang Li   +6 more
openalex   +1 more source

City Slicker or Country Bumpkin?—Distinguishing Urban and Rural Residents From Subtle Facial Cues

European Journal of Social Psychology, EarlyView.
ABSTRACT Stereotypes characterize urban and rural residents as differing in traits, values and social outcomes. Here, we examined how people's stereotypes about urban and rural residents differ, testing their validity using a lens model. Results showed that participants detected whether people resided in urban or rural areas from photos across three ...
McLean G. Morgan, Laura Tian, Nicholas O. Rule   +2 more
wiley   +1 more source

Harnessing deep learning to quantify microstructural complexity in confocal images of plant protein gels

Food Biomacromolecules, EarlyView.
Abstract Understanding plant protein gel microstructure is key to designing functional food systems. This study introduces a deep learning framework using a U‐Net model with a ResNet34 encoder to segment and quantify confocal laser scanning microscopy (CLSM) images of plant protein gels.
Zhi Yang
wiley   +1 more source

Artificial intelligence application in the prediction of spontaneous preterm birth by cervical length in the first trimester of pregnancy: Comparison of three measurement methods

International Journal of Gynecology &Obstetrics, EarlyView.
Abstract Objectives The current study evaluates the efficacy of artificial intelligence (AI)–assisted measurement of cervical length (CL) in predicting spontaneous preterm birth (sPTB), comparing the traditional single‐line and two‐line methods with the innovative AI‐line method in the first trimester of pregnancy. Materials and Methods This study is a
Yi‐yun Tai, Bor‐Yann Tseng, Zhu‐Han Yang, Chi‐Hua Yu, Liona C. Poon   +4 more
wiley   +1 more source

Exploring a Novel Conv‐Transformer Network for Multi‐Modality Heart Segmentation

iRADIOLOGY, EarlyView.
We propose SFAM‐TransUnet for multimodality whole heart segmentation, a novel deep learning framework combining CNNs and transformers. Extensive experiments conducted on the clinical Multi‐Modality Whole Heart Segmentation datasets demonstrate that SFAM‐TransUnet outperforms various alternative methods.
Youyou Ding, Hao Dang, Jiayi Luo, Xiaoyu Zhuo, Ningyu Huang, Junsheng Xiao, Zongwang Lv   +6 more
wiley   +1 more source