CASIA OpenIR

Browse/Search Results:  1-10 of 830 Help

Selected(0)Clear Items/Page:    Sort:
Hierarchical Graph Semantic Pooling Network for Multi-modal Community Question Answer Matching 会议论文
, Nice, France, October 21 - 25, 2019
Authors:  Jun Hu;  Shengsheng Qian;  Quan Fang;  Changsheng Xu
View  |  Adobe PDF(1404Kb)  |  Favorite  |  View/Download:30/13  |  Submit date:2019/09/26
Multi-modal Knowledge-aware Hierarchical Attention Network for Explainable Medical Question Answering 会议论文
, Nice, France, October 21 - 25, 2019
Authors:  Yingying Zhang;  Shengsheng Qian;  Quan Fang;  Changsheng Xu
View  |  Adobe PDF(4568Kb)  |  Favorite  |  View/Download:45/23  |  Submit date:2019/09/26
Adaptive Attention Annotation Model: Optimizing the Prediction Path Through Dependency Fusion 期刊论文
KSII Transactions on Internet and Information Systems, 2019, 期号: 9, 页码: 4665-4683
Authors:  Wang Fangxin(王方心);  Liu Jie;  Zhang Shuwu;  Zhang Guixuan;  Zheng Yang;  Li Xiaoqian;  Liang Wei;  Li Yuejun
View  |  Adobe PDF(1061Kb)  |  Favorite  |  View/Download:13/2  |  Submit date:2019/10/08
Image Annotation  Multiple Dependencies  Self-attention  Prediction Path  Triplet Margin Loss  
Reading selectively via Binary Input Gated Recurrent Unit 会议论文
, 中国澳门, 2019-08
Authors:  Li Z(李哲);  Wang PS(王培松);  Lu HQ(卢汉清);  Cheng J(程健)
View  |  Adobe PDF(1207Kb)  |  Favorite  |  View/Download:82/36  |  Submit date:2019/05/10
A Novel End2End Multiple Tagging Model for Knowledge Extraction 会议论文
, Budapest, Hungary, 2019-7-14
Authors:  Yuanhua Song;  Hongyun Bao;  Zhineng Chen;  Jianquan Ouyang
View  |  Adobe PDF(937Kb)  |  Favorite  |  View/Download:18/6  |  Submit date:2019/10/09
Active Semantic Labeling of Street View Point Clouds 会议论文
, Shanghai, China, 2019-7-8~12
Authors:  Zhou Y(周洋);  Shen SH(申抒含);  Hu ZY(胡占义)
View  |  Adobe PDF(2070Kb)  |  Favorite  |  View/Download:93/32  |  Submit date:2019/04/30
Semantic  Street View  Active Learning  
监控视频开集行人再辨识与重排序研究 学位论文
工程硕士, 中国科学院自动化研究所: 中国科学院自动化研究所, 2019
Authors:  王宏升
Adobe PDF(2722Kb)  |  Favorite  |  View/Download:33/2  |  Submit date:2019/06/19
监控视频  行人再辨识  度量学习  开集行人再辨识  重排序  
基于深度强化学习裁剪物体背景的弱监督物体定位 学位论文
, 北京: 中国科学院大学, 2019
Authors:  郑武
Adobe PDF(3920Kb)  |  Favorite  |  View/Download:45/2  |  Submit date:2019/06/16
弱监督物体定位,深度强化学习,背景裁剪  
面向服务机器人的抓取位置智能检测方法研究 学位论文
工学硕士, 中国科学院自动化研究所: 中国科学院大学, 2019
Authors:  贾群
Adobe PDF(7291Kb)  |  Favorite  |  View/Download:57/4  |  Submit date:2019/06/03
服务机器人,目标检测,目标分割,多任务深度卷积神经网络,抓取位置智能检测  
Scene text detection and recognition with advances in deep learning: a survey 期刊论文
INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2019, 卷号: 22, 期号: 2, 页码: 143-162
Authors:  Liu, Xiyan;  Meng, Gaofeng;  Pan, Chunhong
Favorite  |  View/Download:11/0  |  Submit date:2019/07/11
Natural image  Text detection  Text recognition  Survey