CASIA OpenIR

Browse/Search Results:  1-10 of 20 Help

Selected(0)Clear Items/Page:    Sort:
Learning Proposal-Aware Re-Ranking for Weakly-Supervised Temporal Action Localization 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 卷号: 34, 期号: 1, 页码: 207-220
Authors:  Hu, Yufan;  Fu, Jie;  Chen, Mengyuan;  Gao, Junyu;  Dong, Jianfeng;  Fan, Bin;  Liu, Hongmin
Favorite  |  View/Download:10/0  |  Submit date:2024/03/26
Proposals  Feature extraction  Location awareness  Videos  Measurement  Task analysis  Optimization  weakly-supervised temporal action localization  Proposal-aware reranking  
增强型灰度图像空间实现虹膜活体检测 期刊论文
中国图象图形学报, 2020, 页码: 1421-1435
Authors:  刘明康;  王宏民;  李琦;  孙哲南
Adobe PDF(9535Kb)  |  Favorite  |  View/Download:35/14  |  Submit date:2024/02/23
Unsupervised Multi-Expert Learning Model for Underwater Image Enhancement 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2024, 卷号: 11, 期号: 3, 页码: 708-722
Authors:  Hongmin Liu;  Qi Zhang;  Yufan Hu;  Hui Zeng;  Bin Fan
Adobe PDF(59664Kb)  |  Favorite  |  View/Download:32/11  |  Submit date:2024/02/19
Multi-expert learning  underwater image enhancement  unsupervised learning  
Seeing Through Darkness: Visual Localization at Night via Weakly Supervised Learning of Domain Invariant Features 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 1713-1726
Authors:  Fan, Bin;  Yang, Yuzhu;  Feng, Wensen;  Wu, Fuchao;  Lu, Jiwen;  Liu, Hongmin
Favorite  |  View/Download:66/0  |  Submit date:2023/11/17
Domain invariant local features  image matching  long-term visual localization  weakly supervised learning  
Active learning based 3d semantic labeling from images and videos 期刊论文
IEEE Transactions on Circuits and Systems for Video Technology, 2021, 卷号: 32, 期号: 12, 页码: 8101-8115
Authors:  Mengqi Rong;  Hainan Cui;  Zhanyi Hu;  Hanqing Jiang;  Hongmin Liu;  Shuhan Shen
Adobe PDF(6704Kb)  |  Favorite  |  View/Download:109/38  |  Submit date:2023/09/25
Incremental Translation Averaging 期刊论文
IEEE Transactions on Circuits and Systems for Video Technology, 2022, 卷号: 32, 期号: 11, 页码: 7783-7795
Authors:  Gao, Xiang;  Zhu, Lingjie;  Fan, Bin;  Liu, Hongmin;  Shen, Shuhan
Favorite  |  View/Download:176/0  |  Submit date:2022/12/27
Translation averaging  Incremental estimation  Accuracy and robustness  Simplicity and efficiency  
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
Authors:  Cui, Hainan;  Tu, Diantao;  Tang, Fulin;  Xu, Pengfei;  Liu, Hongmin;  Shen, Shuhan
Favorite  |  View/Download:213/0  |  Submit date:2022/06/06
Cameras  Image reconstruction  Videos  Simultaneous localization and mapping  Video sequences  Robustness  Scalability  Structure from motion  image reconstruction  computational geometry  computer vision  
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
Authors:  Han, Jiali;  Zhu, Lingjie;  Gao, Xiang;  Hu, Zhanyi;  Zhou, Liyang;  Liu, Hongmin;  Shen, Shuhan
Adobe PDF(8168Kb)  |  Favorite  |  View/Download:240/32  |  Submit date:2021/11/03
Urban reconstruction  building modeling  Markov random field  segment based modeling  
Vectorized indoor surface reconstruction from 3D point cloud with multistep 2D optimization 期刊论文
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2021, 卷号: 177, 页码: 57-74
Authors:  Han, Jiali;  Rong, Mengqi;  Jiang, Hanqing;  Liu, Hongmin;  Shen, Shuhan
Adobe PDF(13876Kb)  |  Favorite  |  View/Download:361/60  |  Submit date:2021/08/15
Indoor reconstruction  Vectorized model  Multistep 2D optimization  LoD  Semantic segmentation  
Complete and Accurate Indoor Scene Capturing and Reconstruction Using a Drone and a Robot 期刊论文
IEEE Sensors Journal, 2021, 卷号: 21, 期号: 10, 页码: 11858-11869
Authors:  Gao, Xiang;  Zhu, Lingjie;  Cui, Hainan;  Hu, Zhanyi;  Liu, Hongmin;  Shen, Shuhan
Favorite  |  View/Download:184/0  |  Submit date:2021/06/07
Indoor scene capturing and reconstruction  Drone-robot cooperation  Aerial map construction  Ground robot localization  Ground-to-aerial image merging