中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共10条，第1-10条 帮助

限定条件                            
已选(0)清除 条数/页：   排序方式：
Narrowing the Gap: Improved Detector Training With Noisy Location Annotations 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 6369-6380
作者:  Wang, Shaoru;  Gao, Jin;  Li, Bing;  Hu, Weiming
Adobe PDF(1489Kb)  |  收藏  |  浏览/下载：280/37  |  提交时间：2022/11/14
Annotations  Noise measurement  Detectors  Task analysis  Training  Object detection  Degradation  Object detection  noisy label  Bayesian estimation  teacher-student learning  
Mixed-Supervised Scene Text Detection With Expectation-Maximization Algorithm 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 5513-5528
作者:  Zhao, Mengbiao;  Feng, Wei;  Yin, Fei;  Zhang, Xu-Yao;  Liu, Cheng-Lin
Adobe PDF(5999Kb)  |  收藏  |  浏览/下载：458/42  |  提交时间：2022/09/19
Costs  Annotations  Training  Labeling  Detectors  Data models  Benchmark testing  Mixed-supervised learning  scene text detection  weak supervision forms  expectation-maximization algorithm  
Urban Scene LOD Vectorized Modeling From Photogrammetry Meshes 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 卷号: 30, 页码: 7458-7471
作者:  Han, Jiali;  Zhu, Lingjie;  Gao, Xiang;  Hu, Zhanyi;  Zhou, Liyang;  Liu, Hongmin;  Shen, Shuhan
Adobe PDF(8168Kb)  |  收藏  |  浏览/下载：323/42  |  提交时间：2021/11/03
Urban reconstruction  building modeling  Markov random field  segment based modeling  
Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 页码: 9703-9718
作者:  Tian, Lei;  Tang, Yongqiang;  Hu, Liangchen;  Ren, Zhida;  Zhang, Wensheng
Adobe PDF(3443Kb)  |  收藏  |  浏览/下载：382/82  |  提交时间：2021/01/06
Domain adaptation  class centroid matching  local manifold self-learning  
Attention-Based Pedestrian Attribute Analysis 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 12, 页码: 6126-6140
作者:  Zichang Tan;  Yang Yang;  Jun Wan;  Hanyuan Hang;  Guodong Guo;  Stan Z. Li
Adobe PDF(3457Kb)  |  收藏  |  浏览/下载：254/50  |  提交时间：2020/10/27
Pedestrian attribute analysis  attention mechanism  pedestrian parsing  
Tangent Fisher Vector on Matrix Manifolds for Action Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 期号: 1, 页码: 3052-3064
作者:  Luo, Guan;  Wei, Jiutong;  Hu, Weiming;  Maybank, Stephen J.
Adobe PDF(2396Kb)  |  收藏  |  浏览/下载：394/84  |  提交时间：2020/04/07
Manifolds  Video sequences  Observability  Videos  Covariance matrices  Kernel  Computational modeling  Action recognition  Fisher vector  Grassmann manifold  Hankel matrix  matrix manifold  
Data-Driven Synthesis of Cartoon Faces Using Different Styles 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 卷号: 26, 期号: 1, 页码: 464-478
作者:  Zhang, Yong;  Dong, Weiming;  Ma, Chongyang;  Mei, Xing;  Li, Ke;  Huang, Feiyue;  Hu, Bao-Gang;  Deussen, Oliver
Adobe PDF(6453Kb)  |  收藏  |  浏览/下载：573/157  |  提交时间：2016/10/25
Cartoon Face  Face Stylization  Data-driven Synthesis  Component-based Modeling  
Fast Localization in Large-Scale Environments Using Supervised Indexing of Binary Features 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 卷号: 25, 期号: 1, 页码: 343-358
作者:  Feng, Youji;  Fan, Lixin;  Wu, Yihong
浏览  |  Adobe PDF(5024Kb)  |  收藏  |  浏览/下载：428/107  |  提交时间：2016/03/19
Image Based Localization  Binary Feature  Approximate Nearest Neighbor Search  
Robust Image Analysis With Sparse Representation on Quantized Visual Features 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 卷号: 22, 期号: 3, 页码: 860-871
作者:  Bao, Bing-Kun;  Zhu, Guangyu;  Shen, Jialie;  Yan, Shuicheng
浏览  |  Adobe PDF(460Kb)  |  收藏  |  浏览/下载：326/86  |  提交时间：2015/09/22
Image Classification  Quantized Visual Feature  Sparse Representation  
PM-PM: PatchMatch With Potts Model for Object Segmentation and Stereo Matching 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 卷号: 24, 期号: 7, 页码: 2182-2196
作者:  Xu, Shibiao;  Zhang, Feihu;  He, Xiaofei;  Shen, Xukun;  Zhang, Xiaopeng
浏览  |  Adobe PDF(5719Kb)  |  收藏  |  浏览/下载：348/104  |  提交时间：2015/09/21
Object Segmentation  Stereo Matching  Potts Model  Patchmatch  Multiple View Reconstruction