中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共14条，第1-10条 帮助

限定条件            
已选(0)清除 条数/页：   排序方式：
Multi-Modality Self-Distillation for Weakly Supervised Temporal Action Localization 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 1504-1519
作者:  Huang, Linjiang;  Wang, Liang;  Li, Hongsheng
收藏  |  浏览/下载：195/0  |  提交时间：2022/03/17
Location awareness  Reliability  Noise measurement  Annotations  Training  Head  Task analysis  Weakly supervised temporal action localization  multi-modality  pseudo label  self-distillation  
VidSfM: Robust and Accurate Structure-From-Motion for Monocular Videos 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 2449-2462
作者:  Cui, Hainan;  Tu, Diantao;  Tang, Fulin;  Xu, Pengfei;  Liu, Hongmin;  Shen, Shuhan
收藏  |  浏览/下载：233/0  |  提交时间：2022/06/06
Cameras  Image reconstruction  Videos  Simultaneous localization and mapping  Video sequences  Robustness  Scalability  Structure from motion  image reconstruction  computational geometry  computer vision  
Cross-Batch Hard Example Mining With Pseudo Large Batch for ID vs. Spot Face Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 3224-3235
作者:  Tan, Zichang;  Liu, Ajian;  Wan, Jun;  Liu, Hao;  Lei, Zhen;  Guo, Guodong;  Li, Stan Z.
收藏  |  浏览/下载：234/0  |  提交时间：2022/07/25
Face recognition  Training  Measurement  Graphics processing units  Deep learning  Logic gates  Feature extraction  Face recognition  ID vs spot  deep learning  cross-batch hard example mining  pseudo large batch  
RVFace: Reliable Vector Guided Softmax Loss for Face Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 2337-2351
作者:  Wang, Xiaobo;  Wang, Shuo;  Liang, Yanyan;  Gu, Liang;  Lei, Zhen
收藏  |  浏览/下载：254/0  |  提交时间：2022/06/06
Deep face recognition  noisy labels detection  margin-based softmax loss  mining-based softmax loss  discriminative feature learning  
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：203/25  |  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  
An Efficient Sampling-Based Attention Network for Semantic Segmentation 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 2850-2863
作者:  He, Xingjian;  Liu, Jing;  Wang, Weining;  Lu, Hanqing
Adobe PDF(3252Kb)  |  收藏  |  浏览/下载：345/75  |  提交时间：2022/06/10
Stochastic processes  Sampling methods  Semantics  Image segmentation  Computational complexity  Pattern recognition  Convolution  Semantic segmentation  stochastic sampling-based attention  deterministic sampling-based attention  
Geometry Sensitive Cross-Modal Reasoning for Composed Query Based Image Retrieval 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 1000-1011
作者:  Zhang, Feifei;  Xu, Mingliang;  Xu, Changsheng
收藏  |  浏览/下载：228/0  |  提交时间：2022/02/16
Visualization  Image retrieval  Semantics  Cognition  Geometry  Task analysis  Electronic mail  Composed query based image retrieval  semantic gap  spatial structure  inter-modal attention  text-guided visual reasoning  
Image Inpainting With Local and Global Refinement 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 2405-2420
作者:  Quan, Weize;  Zhang, Ruisong;  Zhang, Yong;  Li, Zhifeng;  Wang, Jue;  Yan, Dong-Ming
收藏  |  浏览/下载：284/0  |  提交时间：2022/06/06
Image reconstruction  Generators  Convolution  Semantics  Image edge detection  Deep learning  Task analysis  Image inpainting  neural networks  receptive field  
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：297/35  |  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  
Unsupervised Structure-Texture Separation Network for Oracle Character Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 3137-3150
作者:  Wang, Mei;  Deng, Weihong;  Liu, Cheng-Lin
收藏  |  浏览/下载：214/0  |  提交时间：2022/06/10
Character recognition  Bones  Adaptation models  Training  Feature extraction  Writing  Transforms  Oracle character recognition  unsupervised domain adaptation  feature disentanglement  generative adversarial network