Results 211 to 220 of about 79,266 (321)

Phase Based Volume Registration Using CUDA

, 2013
Anders Eklund
openalex   +1 more source

YOLO‐EPDS: A Small Object Detection Algorithm for Power Transmission Line Nut Spacing Looseness

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This study proposes YOLO‐EPDS, an enhanced YOLOv9‐based detection framework for identifying nut loosening in transmission lines. By integrating multi‐scale attention, SPD‐Conv, and deformable convolutions with Shape‐IoU loss, the model achieves 79.7% mAP@50 on a self‐constructed dataset, outperforming the baseline in both accuracy and efficiency ...
Guilan Wang, Zenglei Hao, Wangbin Cao, Huawei Mei   +3 more
wiley   +1 more source

Visual motion perception and driving hazard visibility at night-time. [PDF]

Sci Rep
Kennon C, Wood JM, Lacherez PF, Black AA, Cuda D, Henry E, McKendrick AM.   +6 more
europepmc   +1 more source

Debunking the CUDA Myth Towards GPU-based AI Systems [PDF]

Yun-Jae Lee, Juntaek Lim, J. Bang, Eunyeong Cho, Hojin Jeong, Tae‐Su Kim, Hyungjun Kim, Joonhyung Lee, Jinwoo Im, Ranggi Hwang, Se Jung Kwon, Dong‐Soo Lee, Minsoo Rhu   +12 more
openalex   +1 more source

Monocular Unsupervised Depth Estimation of Residual Stratification Based on Ordinal Relation Networks

IET Image Processing, Volume 20, Issue 1, January/December 2026.
ABSTRACT Depth estimation has been widely applied in the field of computer vision, primarily using unsupervised deep neural networks, which often rely on deeper neural networks. However, the addition of layers can result in slower convergence and suboptimal performance.
Ye Kuang, Xiaoyan Jiang, Yongbin Gao
wiley   +1 more source

SPH Based Fluid Animation Using CUDA Enabled GPU

, 2012
Uday A. Nuli
openalex   +1 more source

A Highway Litter Detection Method Based on Multi‐scale Feature Fusion and Dynamic Feature Enhancement

IET Intelligent Transport Systems, Volume 20, Issue 1, January/December 2026.
To address missed detections and false positives in highway litter detection caused by small target sizes and feature degradation, this study proposes a novel framework integrating multi‐scale feature fusion and dynamic feature enhancement mechanisms, which includes a contextual anchor attention module, an improved spatial pyramid pooling module, a ...
Changlu Guo, Yecai Guo, Songbin Li
wiley   +1 more source

A histopathology aware DINO model with attention based representation enhancement. [PDF]

Sci Rep
Ozkan M, Ozcan C, Bumgardner VKC, Gokmen MS.   +3 more
europepmc   +1 more source

Partial Discharge Pattern Recognition Based on Time‐Frequency Multi‐Scale Residual Attention Network

IET Science, Measurement &Technology, Volume 20, Issue 1, January/December 2026.
A time‐frequency multi‐scale residual attention network (TFMRAnet) was designed to analyze partial discharge (PD) signals. The network comprises an adaptive denoising network based on multi‐scale residual attention, a frequency‐domain recognition network, and a decision fusion module based on Dempster‐Shafer (D‐S) evidence theory.
Yunguang Gao, Haohua Jia, Zhipeng Lei, Wenjie Zhang, Junqiang He   +4 more
wiley   +1 more source

AI-generated artwork detection using self-distilled transformers with global-local feature learning and Grad-CAM interpretability. [PDF]

Sci Rep
Yinghua W, Linyan L, Wenjuan M, Yunzhe Z.   +3 more
europepmc   +1 more source