中文版 | English

在结果中检索

CASIA OpenIR
（本次检索基于用户作品认领结果）

浏览/检索结果: 共20条，第1-10条 帮助

限定条件                        
已选(0)清除 条数/页：   排序方式：
HIDE: Hierarchical iterative decoding enhancement for multi-view 3D human parameter regression 期刊论文
Computer Animation and Virtual Worlds, 2024, 卷号: 35, 期号: 35, 页码: 3
作者:  Lin WT(林伟涛);  Zhang JG(张吉光);  Meng WL(孟维亮);  Liu XL(刘湘龙);  Zhang XP(张晓鹏)
Adobe PDF(11125Kb)  |  收藏  |  浏览/下载：24/5  |  提交时间：2024/06/11
3D human mesh recovery  body modeling  computer vision  deep learning  
Line-Based 3D Building Abstraction and Polygonal Surface Reconstruction From Images 期刊论文
IEEE Transactions on Visualization and Computer Graphics, 2022, 卷号: xx, 期号: xx, 页码: 1-15
作者:  Guo, Jianwei;  Liu, Yanchao;  Song, Xin;  Liu, Haoyu;  Zhang, Xiaopeng;  Cheng, Zhanglin
Adobe PDF(6913Kb)  |  收藏  |  浏览/下载：38/13  |  提交时间：2024/06/03
3D reconstruction  3D Line cloud  Scene abstraction  Polygonal mesh model  
Triple Robustness Augmentation Local Features for multi-source image registration 期刊论文
ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 卷号: 199, 期号: 0, 页码: 1-14
作者:  Changwei Wang;  Lele Xu;  Rongtao Xu;  Shibiao Xu;  Weiliang Meng;  Ruisheng Wang;  Xiaopeng Zhang
Adobe PDF(6581Kb)  |  收藏  |  浏览/下载：50/14  |  提交时间：2024/05/29
DomainFeat: Learning Local Features With Domain Adaptation 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 卷号: 34, 期号: 1, 页码: 46-59
作者:  Xu, Rongtao;  Wang, Changwei;  Xu, Shibiao;  Meng, Weiliang;  Zhang, Yuyang;  Fan, Bin;  Zhang, Xiaopeng
Adobe PDF(6039Kb)  |  收藏  |  浏览/下载：93/13  |  提交时间：2024/03/26
Feature extraction  Location awareness  Visualization  Robustness  Image matching  Detectors  Decoding  Local features  domain adaptation  cross-domain data  consistency loss  
Attention Weighted Local Descriptors 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 9, 页码: 10632-10649
作者:  Wang, Changwei;  Xu, Rongtao;  Lu, Ke;  Xu, Shibiao;  Meng, Weiliang;  Zhang, Yuyang;  Fan, Bin;  Zhang, Xiaopeng
Adobe PDF(8075Kb)  |  收藏  |  浏览/下载：174/8  |  提交时间：2023/11/17
Local features detection and description  consistent attention mechanism  context augmentation  lightweight local descriptors  knowledge distillation  
GeoROS: Georeferenced Real-time Orthophoto Stitching with Unmanned Aerial Vehicle 会议论文
, Kyoto, Japan, Oct 23-27, 2022
作者:  Gao GZ(高广泽);  Yuan MK(袁梦轲);  Ma ZH(马志豪);  Gu JM(谷佳铭);  Meng WL(孟维亮);  Xu SB(徐士彪);  Zhang XP(张晓鹏)
Adobe PDF(2540Kb)  |  收藏  |  浏览/下载：287/98  |  提交时间：2023/05/04
Accurate 3D Locating and Tracking of Basketball Players from Multiple Videos 会议论文
, Tokyo, Japan, 2018.12.3-2018.12.7
作者:  Weiliang Meng;  Shibiao Xu;  Er Li;  Xiangyong Zeng;  Xiaopeng Zhang
Adobe PDF(2936Kb)  |  收藏  |  浏览/下载：154/43  |  提交时间：2023/04/27
tracking  integral space  Gaussian Mixture Model  grouping  
Single-Image Specular Highlight Removal via Real-World Dataset Construction 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 页码: 12
作者:  Wu ZQ(吴仲琦);  Zhuang CQ(庄传青);  Shi J(石剑);  Guo JW(郭建伟);  Xiao J(肖俊);  Zhang XP(张晓鹏);  Yan DM(严冬明)
Adobe PDF(49307Kb)  |  收藏  |  浏览/下载：269/104  |  提交时间：2022/06/15
Specular highlight removal, PSD-Dataset, Deep learning  
Efficient MSPSO Sampling for Object Detection and 6-D Pose Estimation in 3-D Scenes 期刊论文
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2022, 卷号: 69, 期号: 10, 页码: 10281-10291
作者:  Xing, Xuejun;  Guo, Jianwei;  Nan, Liangliang;  Gu, Qingyi;  Zhang, Xiaopeng;  Yan, Dong-Ming
Adobe PDF(4863Kb)  |  收藏  |  浏览/下载：295/9  |  提交时间：2022/06/10
Pose estimation  Three-dimensional displays  Robustness  Robot kinematics  Image segmentation  Deep learning  Clustering algorithms  3-D point cloud  6-D pose estimation  multisubpopulation particle swarm optimization (MSPSO)  point pair features (PPF)  
Key point localization and recurrent neural network based water meter reading recognition 期刊论文
Displays, 2022, 卷号: 74, 期号: 2022, 页码: 0-0
作者:  Jiguang Zhang;  Wenrui Liu;  Shibiao Xu;  Xiaopeng Zhang
Adobe PDF(4271Kb)  |  收藏  |  浏览/下载：237/58  |  提交时间：2022/05/06
Mechanical water meters reading  Reading region detection  Digit wheels recognition  Key point location  Recurrent convolutional network