中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共19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：214/26  |  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  
Learning Aligned Image-Text Representations Using Graph Attentive Relational Network 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 期号: 30, 页码: 1840-1852
作者:  Jing, Ya;  Wang, Wei;  Wang, Liang;  Tan, Tieniu
Adobe PDF(4532Kb)  |  收藏  |  浏览/下载：319/51  |  提交时间：2021/03/08
Graph neural networks  Visualization  Semantics  Task analysis  Feature extraction  Annotations  Recurrent neural networks  Image-text matching  cross-modal retrieval  person search  graph neural network  
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.
浏览  |  Adobe PDF(2396Kb)  |  收藏  |  浏览/下载：352/76  |  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  
Conditional High-Order Boltzmann Machines for Supervised Relation Learning 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 卷号: 26, 期号: 9, 页码: 4297-4310
作者:  Huang, Yan;  Wang, Wei;  Wang, Liang;  Tan, Tieniu
浏览  |  Adobe PDF(4175Kb)  |  收藏  |  浏览/下载：439/158  |  提交时间：2017/06/19
Deep Learning  High-order Boltzmann Machine  Relation Learning  Face Verification  Action Similarity Labeling  
Dynamic Graph Cuts in Parallel 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 卷号: 26, 期号: 8, 页码: 3775-3788
作者:  Yu, Miao;  Shen, Shuhan;  Hu, Zhanyi
浏览  |  Adobe PDF(3907Kb)  |  收藏  |  浏览/下载：348/108  |  提交时间：2017/09/12
Dynamic Graph Cuts  Parallel Computation  Video Segmentation  Grabcut  
Removing Turbulence Effect via Hybrid Total Variation and Deformation-Guided Kernel Regression 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 卷号: 25, 期号: 10, 页码: 4943-4958
作者:  Xie, Yuan;  Zhang, Wensheng;  Tao, Dacheng;  Hu, Wenrui;  Qu, Yanyun;  Wang, Hanzi;  Yuan Xie
浏览  |  Adobe PDF(9193Kb)  |  收藏  |  浏览/下载：499/151  |  提交时间：2016/10/22
Image Restoration  Atmospheric Turbulence  Total Variation  Deformation-guided Kernel  
Speeding Up the Bilateral Filter: A Joint Acceleration Way 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 卷号: 25, 期号: 6, 页码: 2657-2672
作者:  Dai, Longquan;  Yuan, Mengke;  Zhang, Xiaopeng
浏览  |  Adobe PDF(7883Kb)  |  收藏  |  浏览/下载：301/80  |  提交时间：2016/10/20
Fast Bilateral Filter  Best N-term Approximation  Haar Functions  Truncated Trigonometric Functions  
A Nonlocal TV-Based Variational Method for PolSAR Data Speckle Reduction 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 卷号: 25, 期号: 6, 页码: 2620-2634
作者:  Nie, Xiangli;  Qiao, Hong;  Zhang, Bo;  Huang, Xiayuan
浏览  |  Adobe PDF(5355Kb)  |  收藏  |  浏览/下载：483/175  |  提交时间：2016/10/20
Polarimetric Synthetic Aperture Radar (Polsar)  Speckle Reduction  Nonlocal Total Variation (Nltv)  Complex Wishart Distribution  Conjugate Function  Variational Model  
Cross-Modal Subspace Learning via Pairwise Constraints 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 卷号: 24, 期号: 12, 页码: 5543-5556
作者:  Ran He(赫然);  Man Zhang;  Liang Wang;  Ye Ji;  Qiyue Yin;  Ji, Ye
浏览  |  Adobe PDF(2205Kb)  |  收藏  |  浏览/下载：422/115  |  提交时间：2016/01/18
Multi Modal  Pairwise Constraint  Subspace Clustering  
Horror Image Recognition Based on Context-Aware Multi-Instance Learning 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 卷号: 24, 期号: 12, 页码: 5193-5205
作者:  Li, Bing;  Xiong, Weihua;  Wu, Ou;  Hu, Weiming;  Maybank, Stephen;  Yan, Shuicheng;  Bing Li
浏览  |  Adobe PDF(906Kb)  |  收藏  |  浏览/下载：756/304  |  提交时间：2015/11/12
Horror Image Recognition  Context-aware Multi-instance Learning  Visual Saliency