CASIA OpenIR

浏览/检索结果: 共5条,第1-5条 帮助

限定条件                        
已选(0)清除 条数/页:   排序方式:
Category-Level 6D Object Pose Estimation With Structure Encoder and Reasoning Attention 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 卷号: 32, 期号: 10, 页码: 6728-6740
作者:  Liu, Jierui;  Cao, Zhiqiang;  Tang, Yingbo;  Liu, Xilong;  Tan, Min
Adobe PDF(22124Kb)  |  收藏  |  浏览/下载:255/4  |  提交时间:2022/11/14
Shape  Three-dimensional displays  Cognition  Pose estimation  Feature extraction  Decoding  Solid modeling  Category-level  6D object pose estimation  structure encoder  reasoning attention  
Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey 期刊论文
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 卷号: 71, 页码: 21
作者:  Tao, Xian;  Gong, Xinyi;  Zhang, Xin;  Yan, Shaohua;  Adak, Chandranath
Adobe PDF(7056Kb)  |  收藏  |  浏览/下载:243/0  |  提交时间:2022/09/19
Anomaly localization (AL)  deep learning  industrial inspection  literature survey  unsupervised learning  
CellNet: A Lightweight Model towards Accurate LOC-Based High-Speed Cell Detection 期刊论文
ELECTRONICS, 2022, 卷号: 11, 期号: 9, 页码: 20
作者:  Long, Xianlei;  Ishii, Idaku;  Gu, Qingyi
Adobe PDF(1681Kb)  |  收藏  |  浏览/下载:381/170  |  提交时间:2022/07/25
cell detection  high-speed vision  convolutional neural network (CNN)  efficient convolutional block  medical image analysis  
Cross-domain few-shot learning approach for lithium-ion battery surface defects classification using an improved siamese network 期刊论文
IEEE SENSORS JOURNAL, 2022, 页码: 1-1
作者:  Wu, Ke;  Tan, Jie;  Liu, Cheng Bao
Adobe PDF(5175Kb)  |  收藏  |  浏览/下载:321/118  |  提交时间:2022/06/14
Few-shot Learning  3D measurement  defect detection  image classification  
Cross-attention-map-based regularization for adversarial domain adaptation 期刊论文
NEURAL NETWORKS, 2022, 卷号: 145, 页码: 128-138
作者:  Jingwei, Li;  Huanjie, Wang;  Ke, Wu;  Chengbao, Liu;  Jie, Tan
Adobe PDF(1969Kb)  |  收藏  |  浏览/下载:238/2  |  提交时间:2021/12/28
Domain adaptation  Few-shot learning  Attention mechanism  Contrastive learning