CASIA OpenIR

浏览/检索结果: 共45条,第1-10条 帮助

已选(0)清除 条数/页:   排序方式:
Global Patch Cross-Attention for Point Cloud Analysis 会议论文
5th Chinese Conference, PRCV 2022, Shenzhen, China, November 4–7, 2022, Proceedings, Part III, 深圳, 2022.11.4-2022.11.7
作者:  Tao ML(陶满礼);  Zhao CY(赵朝阳);  Wang JQ(王金桥);  Tang M(唐明)
Adobe PDF(6422Kb)  |  收藏  |  浏览/下载:12/3  |  提交时间:2024/05/30
Global patch · Cross-attention · Contextual description · Point cloud analysis  
Interaction-Aware Trajectory Prediction with Point Transformer 会议论文
, Bilbao, Bizkaia, Spain, 24-28 September 2023
作者:  Yahui, Liu;  Xingyuan, Dai;  Jianwu, Fang;  Bin, Tian;  Yisheng, Lv
Adobe PDF(519Kb)  |  收藏  |  浏览/下载:2/1  |  提交时间:2024/05/28
trajectory prediction  
面向自动驾驶的感知预测一体化方法研究 学位论文
, 2024
作者:  刘雅慧
Adobe PDF(10624Kb)  |  收藏  |  浏览/下载:22/1  |  提交时间:2024/05/27
Autonomous Driving  Integrated Perception and Prediction  Point Cloud Classification  Trajectory Prediction  Scene Motion Prediction  
单幅图像超分辨率重建技术研究进展 期刊论文
自动化学报, 2022, 卷号: 48, 期号: 11, 页码: 2634-2654
作者:  张芳;  赵东旭;  肖志涛;  耿磊;  吴骏;  刘彦北
Adobe PDF(2376Kb)  |  收藏  |  浏览/下载:9/4  |  提交时间:2024/05/20
超分辨率重建  单幅图像  空域方法  深度学习  
Adaptively Enhancing Facial Expression Crucial Regions via a Local Non-local Joint Network 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 2, 页码: 331-348
作者:  Guanghui Shi;  Shasha Mao;  Shuiping Gou;  Dandan Yan;  Licheng Jiao;  Lin Xiong
Adobe PDF(3926Kb)  |  收藏  |  浏览/下载:19/6  |  提交时间:2024/04/23
Facial expression recognition, deep neural network, multiple network ensemble, attention network, facial crucial regions  
Deep Video Harmonization by Improving Spatial-temporal Consistency 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 1, 页码: 46-54
作者:  Xiuwen Chen;  Li Fang;  Long Ye;  Qin Zhang
Adobe PDF(3779Kb)  |  收藏  |  浏览/下载:7/4  |  提交时间:2024/04/23
Harmonization, temporal consistency, video editing, video composition, nonlocal similarity  
MAUN: Memory-Augmented Deep Unfolding Network for Hyperspectral Image Reconstruction 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 5, 页码: 1139-1150
作者:  Qian Hu;  Jiayi Ma;  Yuan Gao;  Junjun Jiang;  Yixuan Yuan
Adobe PDF(10937Kb)  |  收藏  |  浏览/下载:24/4  |  提交时间:2024/04/10
Compressive imaging  deep unfolding network hyperspectral image  
基于特征的三维点云配准研究 学位论文
, 2023
作者:  Shiyi Guo
Adobe PDF(25276Kb)  |  收藏  |  浏览/下载:147/11  |  提交时间:2024/01/07
点云配准  三维特征提取  外点剔除  低重叠率场景  激光点云序列配准  
Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 1, 页码: 231-239
作者:  Yahui Liu;  Bin Tian;  Yisheng Lv;  Lingxi Li;  Fei-Yue Wang
Adobe PDF(8541Kb)  |  收藏  |  浏览/下载:247/160  |  提交时间:2024/01/02
Content-based Transformer  deep learning  feature aggregator  local attention  point cloud classification  
Toward Accurate and Efficient Road Extraction by Leveraging the Characteristics of Road Shapes 期刊论文
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 卷号: 61, 页码: 16
作者:  Wang, Changwei;  Xu, Rongtao;  Xu, Shibiao;  Meng, Weiliang;  Wang, Ruisheng;  Zhang, Jiguang;  Zhang, Xiaopeng
Adobe PDF(13777Kb)  |  收藏  |  浏览/下载:106/1  |  提交时间:2023/11/17
Efficient and accurate road extraction  efficient strip transformer module (ESTM)  geometric deformation estimation module (GDEM)  road edge focal loss (REF loss)  road shape-aware network (RSANet)