Yaxin Xie,Mingyu Zhang,Yonghua Han et al.
Yaxin Xie et al.
In cotton disease detection, the complex farmland environment and the varying scales of disease spots, especially the presence of small-target disease spots, limit the detection accuracy of lightweight models. To address this issue, an impr...
Implementation of Image-Based Artificial Intelligence Is Associated with Increased Case Volume in a High-Acuity, 15-Room Cardiothoracic Operating Suite at a Tertiary Academic Hospital [0.03%]
在一家三级学术医院的高危心脏手术科室中，基于图像的人工智能的实施与病例数量增加有关（该科室设有15间 cardiothoracic 手术室）
Ngoc-Anh A Nguyen,Grace Lee,Sarah Sossong et al.
Ngoc-Anh A Nguyen et al.
Background: Operating rooms generate substantial visual data that is rarely captured systematically. Image-based AI (IBAI) systems using computer vision offer a new approach to real-time perioperative workflow monitoring,...
Optical System Design for Off-Axis Polarization Super-Resolution Imaging with Four Sub-Apertures [0.03%]
四个子孔径离轴偏振超分辨光学系统设计
Xiansong Gu,Chao Wang,Huilin Jiang et al.
Xiansong Gu et al.
We propose a dual-aperture, simultaneous-polarization super-resolution imaging system that combines a total internal reflection optical architecture with a digital micromirror device (DMD) for broadband, high-resolution imaging. The system ...
Hybrid Multi-Objective Neural Architecture Search for Lightweight Patch-Based Mistletoe Classification in UAV Imagery [0.03%]
基于无人机图像的轻量级补丁寄生檞分类的多目标神经体系结构搜索
Miguel-Angel Gil-Rios,Nivia Escalante-Garcia,Juan C Valdiviezo-Navarro et al.
Miguel-Angel Gil-Rios et al.
This paper proposes a novel method for automatically designing lightweight Convolutional Neural Network (CNN) architectures. (1) Background: Automated remote sensing for vegetation monitoring faces challenges from structural complexity and ...
Quantifying and Improving Stereo Camera Calibration Robustness: An Outlier-Aware Algorithm for Digital Twin Data Acquisition [0.03%]
立体相机标定鲁棒性定量分析与改进：一种数字孪生数据采集的抗偏算法
Madalina Carbureanu,Florin-Stefan Zamfir
Madalina Carbureanu
As calibration errors have a direct impact on epipolar consistency, rectification accuracy, and metric 3D reconstruction performance, stereo camera calibration is a fundamental requirement for high-accuracy 3D modeling and reliable digital ...
Prompt-Guided Semantic Latent Direction Learning in Diffusion Models for Abstract Visual Concept Manipulation [0.03%]
提示引导的语义潜在方向学习在扩散模型中的应用以操纵抽象视觉概念
Mahzaib Khalid,Fangli Ying,Al-Garadi Ahmed Mohammed Atef et al.
Mahzaib Khalid et al.
Diffusion-based generative models achieve high-fidelity image synthesis; however, controlling internal representations for abstract visual concepts remains challenging due to the ambiguity of textual descriptions. In this work, we propose a...
MBRSNet: Boundary-Aware Multi-Task Learning with Signed Distance Field Regression for Polyp Segmentation [0.03%]
基于带符号距离场回归的边界感知多任务学习结肠息肉分割(MBRSNet)
Ruishi Lin,Liyong Ma
Ruishi Lin
Accurate polyp segmentation in colonoscopic images remains challenging due to low contrast, irregular morphology, and significant distribution shifts across datasets, which often lead to unreliable boundary delineation and poor generalizati...
ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching [0.03%]
基于Enhanced ShuffleMixer的深度学习视差上采样方法
Mahmoud Tahmasebi,Saif Huq,Kevin Meehan et al.
Mahmoud Tahmasebi et al.
Stereo matching has become an increasingly important component of modern autonomous systems. Developing deep learning-based stereo-matching models that deliver high accuracy while operating in real time continues to be a major challenge in ...
Hyperelastic Regularization for Near-Diffeomorphic Transformer-Based Brain MRI Registration [0.03%]
基于变压器的近微分同胚超弹性正则化脑MRI配准方法
Shiyi Xu,Mohan Xu,Erjin Zhou
Shiyi Xu
Transformer-based deformable brain MRI registration achieves high overlap accuracy, but predicted displacement fields can contain voxels with a non-positive Jacobian determinant-local foldings that violate the diffeomorphism assumption requ...
Benchmarking Barren Plateau Mitigation Strategies in Quantum Neural Networks on Standard and Medical Image Datasets [0.03%]
基于标准数据集和医学图像数据集的量子神经网络中的“荒地基准”缓解策略比较
Maqsudur Rahman,Rui Liu,Anup Majumder et al.
Maqsudur Rahman et al.
Barren plateaus (BPs) pose a major trainability challenge for quantum neural networks (QNNs) by causing gradients to concentrate near zero as circuit size, depth, or expressibility increases. This study presents a comparative benchmark of 1...