CASIA OpenIR

Browse/Search Results:  1-3 of 3 Help

Selected(0)Clear Items/Page:    Sort:
Reading scene text with fully convolutional sequence modeling 期刊论文
NEUROCOMPUTING, 2019, 卷号: 339, 页码: 161-170
Authors:  Gao, Yunze;  Chen, Yingying;  Wang, Jinqiao;  Tang, Ming;  Lu, Hanqing
Favorite  |  View/Download:28/0  |  Submit date:2019/07/12
Fully convolutional sequence modeling  Scene text recognition  
Deep Reinforcement Learning for Query-Conditioned Video Summarization 期刊论文
Applied Sciences - Basel, 2019, 卷号: 9, 期号: 4, 页码: 750-765
Authors:  Yujia Zhang;  Michael Kampffmeyer;  Xiaoguang Zhao;  Min Tan
View  |  Adobe PDF(3674Kb)  |  Favorite  |  View/Download:44/9  |  Submit date:2019/05/05
Query-conditioned Video Summarization  Deep Reinforcement Learning  Visual-text Embedding  Temporal Modeling  Vision Application  
基于多媒体数据的案件智能串并系统的研究与实现 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2014
Authors:  吴迪
Adobe PDF(2804Kb)  |  Favorite  |  View/Download:75/0  |  Submit date:2015/09/02
案件串并  Lda模型  文本建模  图像检索  相似性  Case-merging  Lda Model  Text Modeling  Image Retrieval  Similarity