中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共12条，第1-10条 帮助

限定条件                            
已选(0)清除 条数/页：   排序方式：
Active Disparity Sampling for Stereo Matching With Adjoint Network 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 卷号: 33, 页码: 354-365
作者:  Zhang, Chenghao;  Meng, Gaofeng;  Tian, Kun;  Ni, Bolin;  Xiang, Shiming
收藏  |  浏览/下载：43/0  |  提交时间：2024/02/21
Stereo matching  domain generalization  active sampling  adjoint network  Bayesian optimization  
Reducing Vision-Answer Biases for Multiple-Choice VQA 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 4621-4634
作者:  Zhang, Xi;  Zhang, Feifei;  Xu, Changsheng
收藏  |  浏览/下载：47/0  |  提交时间：2023/11/17
Multiple-choice VQA  vision-answer bias  causal intervention  counterfactual interaction learning  
Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 3622-3633
作者:  Liu, Chong;  Zhang, Yuqi;  Wang, Hongsong;  Chen, Weihua;  Wang, Fan;  Huang, Yan;  Shen, Yi-Dong;  Wang, Liang
收藏  |  浏览/下载：106/0  |  提交时间：2023/11/17
Index Terms-Image-text retrieval  multimodal transformer  multimodal contrastive training  
Learning Domain Invariant Representations for Generalizable Person Re-Identification 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 509-523
作者:  Zhang, Yi-Fan;  Zhang, Zhang;  Li, Da;  Jia, Zhen;  Wang, Liang;  Tan, Tieniu
收藏  |  浏览/下载：237/0  |  提交时间：2023/03/20
Generalizable person re-Identification  disentanglement  backdoor adjustment  
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：250/0  |  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  
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：305/0  |  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  
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：293/38  |  提交时间：2021/11/03
Urban reconstruction  building modeling  Markov random field  segment based modeling  
Robust Ellipse Fitting Using Hierarchical Gaussian Mixture Models 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 卷号: 30, 页码: 3828-3843
作者:  Zhao, Mingyang;  Jia, Xiaohong;  Fan, Lubin;  Liang, Yuan;  Yan, Dong-Ming
收藏  |  浏览/下载：233/0  |  提交时间：2021/05/06
Kernel  Robustness  Optimization  Gaussian mixture model  Bandwidth  Two dimensional displays  Transforms  Ellipse fitting  GMM  HGMM  RANSAC  outlier  noise  robust statistic  
Nocal-Siam: Refining Visual Features and Response With Advanced Non-Local Blocks for Real-Time Siamese Tracking 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 卷号: 30, 页码: 2656-2668
作者:  Tan, Huibin;  Zhang, Xiang;  Zhang, Zhipeng;  Lan, Long;  Zhang, Wenju;  Luo, Zhigang
Adobe PDF(2898Kb)  |  收藏  |  浏览/下载：176/42  |  提交时间：2021/03/29
Target tracking  Visualization  Feature extraction  Real-time systems  Oceans  Convolution  Task analysis  Siamese trackers  non-local attention  supervisedly attentive  
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：347/72  |  提交时间：2021/01/06
Domain adaptation  class centroid matching  local manifold self-learning