Results 41 to 50 of about 13,106 (168)
Survey on Visual Transformer for Image Classification [PDF]
Transformer is a deep learning model based on the self-attention mechanism, showing tremendous potential in computer vision. In image classification tasks, the key challenge lies in efficiently and accurately capturing both local and global features of ...
PENG Bin, BAI Jing, LI Wenjing, ZHENG Hu, MA Xiangyu
core +1 more source
Rare Metals, Volume 45, Issue 5, May 2026.ABSTRACT Laser powder bed fusion (LPBF) can fabricate high‐entropy alloys (HEAs) with refined microstructure and enhanced mechanical properties. However, the deformation and fatigue mechanisms of Al‐containing HEAs produced by LPBF remain unclear. In this work, we systematically investigate the tensile properties, deformation mechanisms, and high‐cycle
Dan Zheng +4 more
wiley +1 more source
Coal-rock interface perception and accurate recognition in heading face under coal dust environment based on machine vision [PDF]
The coal-rock identification technology in the roadway excavation process is the core of the automatic adjustment of roadheader’s cutting head, and it is also one of the key problems restricting the development of intelligent mines.
Baoxu YAN +8 more
core +1 more source
Rare Metals, Volume 45, Issue 4, April 2026.ABSTRACT The development of neuromorphic electronics with visual perception and adaptive capability is highly desirable for advancing artificial vision systems. Herein, we have demonstrated a dual‐plasticity adaptive phototransistor based on IGZO nanofibers that exhibits the perception and dynamic adaptation behavior of rod and cone cells to varying ...
Shanshan Jiang +5 more
wiley +1 more source
融入混合注意力的低缩放因子Seam Carving篡改检测算法
智能科学与技术学报针对现有的Seam Carving篡改检测算法对于低缩放因子情况存在检测精度不高、鲁棒性不强的问题，提出一种融入混合注意力机制的Seam Carving篡改检测算法。首先，利用BayarConv2D约束卷积对图像进行预处理，充分学习图像的噪声特征，并通过矩阵乘法与RGB图像进行特征融合；然后，采用ResNet作为骨干网络进行特征学习，引入残差传播和残差反馈机制，凸显Seam Carving的操作痕迹；最后，利用混合注意力机制同时提取相邻位置和通道之间的特征，更好地捕捉全局特征 ...
赵洁, 常皓婵, 武斌
doaj +1 more source
智能科学与技术学报, 2021 近年来，基于自注意力机制的神经网络在计算机视觉任务中得到广泛的应用。随着智能交通系统的广泛应用，面对复杂多变的交通场景，车牌识别任务的难度不断提高，准确识别的需求更加迫切。因此提出一个基于自注意力的免矫正的车牌识别方法T-LPR。首先对图像进行切片和序列化，并使用3D卷积对切片序列进行特征提取，从而得到图像的嵌入向量序列。然后将嵌入向量序列输入基于Transformer Encoder的编码器中，学习各个嵌入向量之间的关系并输出最终的编码结果。最后使用分类器进行分类。在多个公共数据集上的实验结果表明 ...
曾淦雄, 柯逍
doaj
Conservation Biology, Volume 40, Issue 2, April 2026.Abstract There exists a growing suite of technologies that support significant and exciting progress in biodiversity conservation and research. Citizen scientist participation is common in this research and often focuses on data collection and labeling.
Joycelyn Longdon +5 more
wiley +1 more source
Zhendong Ceshi yu Zhenduan针对长短期记忆神经网络提取特征信息相关性和时间信息依赖性不足的问题，提出基于改进双多头注意力机制的长短期记忆神经网络（improved dual stage attention⁃based long short⁃term memory neural networks， 简称IDSA⁃LSTMNN），以提高滚动轴承剩余使用寿命（remaining useful life， 简称RUL）的预测精度。首先，采用改进的蜘蛛蜂优化器（improved spider wasp optimizer， 简称ISWO ...
doaj +1 more source
Gaoya dianqi, 2023 语音识别是变电站智能运检中关键的人机交互技术。然而，由于生产环境中存在使用专业术语多和噪声大的问题，传统的语音识别方法的效果受限。为此，文中提出了一种基于声音谱特征的语音识别方法。通过融合MFCC与CQT谱，形成一种基于声音谱的特征参数，通过对参数分布的估计，能够有效地降低语音信息中的噪声干扰。为提升语音识别性能，文中设计一个端到端的语音识别模型。该模型基于卷积神经网络（CNN），并融合了CTC和注意力机制。CNN网络能够有效地捕捉语音数据中的局部模式和结构信息 ...
高宝明 +5 more
doaj
Research Review of Deep Learning in Colon Polyp Image Segmentation [PDF]
Colorectal polyp is an abnormal tissue growing in the gastrointestinal tract with the potential to develop into colorectal cancer. Therefore, early detection and removal of colorectal polyps are crucial for preventing colorectal cancer.
LI Guowei, LIU Jing, CAO Hui, JIANG Liang
core +1 more source