CASIA OpenIR

Browse/Search Results:  1-10 of 202 Help

Filters                
Selected(0)Clear Items/Page:    Sort:
基于RGB-D图像的室内场景高精度三维重建研究 学位论文
工学博士, 中国科学院自动化研究所: 中国科学院自动化研究所, 2019
Authors:  李建伟
Adobe PDF(22791Kb)  |  Favorite  |  View/Download:90/3  |  Submit date:2019/06/05
三维重建  同步定位与建图(slam)  计算机视觉  图像处理  深度学习  
图像美学质量评估的方法与应用 学位论文
工学博士, 中国科学院自动化研究所: 中国科学院大学, 2019
Authors:  盛柯恺
Adobe PDF(18854Kb)  |  Favorite  |  View/Download:62/2  |  Submit date:2019/06/18
图像美学质量评估  注意力机制  自监督学习  正则化策略  排序学习  深度学习  
任务型对话系统中口语理解模块方法研究 学位论文
工学硕士, 中国科学院自动化研究所: 中国科学院自动化研究所, 2019
Authors:  白赫
Adobe PDF(2958Kb)  |  Favorite  |  View/Download:36/4  |  Submit date:2019/06/17
对话系统  口语理解  跨语言迁移  强化学习  多任务学习  
移动设备上的室内场景在线三维重建研究 学位论文
, 中国科学院自动化研究所: 中国科学院自动化研究所, 2019
Authors:  刘养东
Adobe PDF(22948Kb)  |  Favorite  |  View/Download:90/4  |  Submit date:2019/07/26
在线三维重建,移动设备,icp 算法,平面先验,动态场景  
3D Scanning of High Dynamic Scenes Using an RGB-D Sensor and an IMU on a Mobile Device 期刊论文
IEEE Access, 2019, 期号: 7, 页码: 24057-24070
Authors:  Liu, Yangdong;  Gao, Wei;  Hu, Zhanyi
View  |  Adobe PDF(4113Kb)  |  Favorite  |  View/Download:47/14  |  Submit date:2019/05/08
Dynamic Scenes  Background Segmentation  Rgb-d  Mobile Device  
Three-Dimensional Attention-Based Deep Ranking Model for Video Highlight Detection 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 卷号: 20, 期号: 10, 页码: 2693-2705
Authors:  Jiao,Yifan;  Li,Zhetao;  Huang,Shucheng;  Yang,Xiaoshan;  Liu,Bin;  Zhang,Tianzhu
View  |  Adobe PDF(4692Kb)  |  Favorite  |  View/Download:128/47  |  Submit date:2018/10/10
Video Highlight Detection  Attention Model  Deep Ranking  
Realistic Procedural Plant Modeling from Multiple View Images 期刊论文
IEEE Transactions on Visualization and Computer Graphics, 2018, 卷号: xx, 期号: xx, 页码: xx
Authors:  Jianwei Guo;  Shibiao Xu;  Dong-Ming Yan;  Zhanglin Cheng;  Marc Jaeger;  Xiaopeng Zhang
View  |  Adobe PDF(24904Kb)  |  Favorite  |  View/Download:97/13  |  Submit date:2018/10/01
Three-dimensional Displays  Solid Modeling  Computational Modeling  Image Reconstruction  Shape  Geometry  Vegetation  
Text2Video: An End-to-end Learning Framework for Expressing Text With Videos 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 卷号: 20, 期号: 9, 页码: 2360-2370
Authors:  Yang, Xiaoshan;  Zhang, Tianzhu;  Xu, Changsheng
View  |  Adobe PDF(2281Kb)  |  Favorite  |  View/Download:124/26  |  Submit date:2018/02/07
Multimedia Storytelling  Video Analysis  Deep Learning  
Document-level Multi-aspect Sentiment Classification by Jointly Modeling Users, Aspects, and Overall Ratings. 会议论文
, Santa Fe, New Mexico, USA, 2018-8
Authors:  Li, Junjie;  Yang, Haitong;  Zong, Chengqing
View  |  Adobe PDF(448Kb)  |  Favorite  |  View/Download:53/19  |  Submit date:2019/01/25
Improving Deep Neural Network Based Speech Synthesis through Contextual Feature Parametrization and Multi-Task Learning 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2018, 卷号: 90, 期号: 7, 页码: 1025-1037
Authors:  Wen, Zhengqi;  Li, Kehuang;  Huang, Zhen;  Lee, Chin-Hui;  Tao, Jianhua;  Zhengqi Wen
View  |  Adobe PDF(995Kb)  |  Favorite  |  View/Download:82/24  |  Submit date:2018/01/05
Dnn-based Speech Synthesis  Vocoder  Speech Parametrization  Blstm  Phoneme Embedded Vector  Multi-task Learning  Pitch-scaled Spectrum