CASIA OpenIR

Browse/Search Results:  1-10 of 33 Help

Selected(0)Clear Items/Page:    Sort:
基于注意与记忆机制的视觉描述 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:  王君波
Adobe PDF(6335Kb)  |  Favorite  |  View/Download:43/1  |  Submit date:2020/01/07
视觉描述  注意与记忆机制  长序列建模  模态相关性  关系学习  
面向用户行为序列的深度上下文建模 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2019
Authors:  崔强
Adobe PDF(12117Kb)  |  Favorite  |  View/Download:66/4  |  Submit date:2019/06/18
上下文信息  深度学习  用户行为序列  循环神经网络  注意力机制  
面向非结构化文本的关系抽取关键技术研究 学位论文
, 中科院自动化所: 中科院自动化所, 2019
Authors:  曾祥荣
Adobe PDF(8436Kb)  |  Favorite  |  View/Download:152/11  |  Submit date:2019/06/04
信息抽取  关系分类  关系抽取  多关系抽取  深度学习  强化学习  
Read, Watch, Listen, and Summarize: Multi-Modal Summarization for Asynchronous Text, Image, Audio and Video 期刊论文
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2019, 卷号: 31, 期号: 5, 页码: 996-1009
Authors:  Li, Haoran;  Zhu, Junnan;  Ma, Cong;  Zhang, Jiajun;  Zong, Chengqing
View  |  Adobe PDF(2826Kb)  |  Favorite  |  View/Download:31/5  |  Submit date:2019/07/12
Summarization  multimedia  multi-modal  cross-modal  natural language processing  computer vision  
Inductive Zero-Shot Image Annotation via Embedding Graph 期刊论文
IEEE ACCESS, 2019, 卷号: 7, 页码: 107816-107830
Authors:  Wang, Fangxin;  Liu, Jie;  Zhang, Shuwu;  Zhang, Guixuan;  Li, Yuejun;  Yuan, Fei
View  |  Adobe PDF(1472Kb)  |  Favorite  |  View/Download:48/12  |  Submit date:2019/10/08
Contextualized word embeddings  graph convolutional network  image annotation  Node2Vec  zero-shot  
基于类脑皮层模型的动作序列获取与分析 学位论文
, 北京: 中国科学院大学, 2018
Authors:  潘瑞晗
Adobe PDF(3000Kb)  |  Favorite  |  View/Download:69/0  |  Submit date:2018/06/05
层次时序记忆模型  离散hopfield网络  动作场景分析  脑皮层  
Multi-view pedestrian captioning with an attention topic CNN model 期刊论文
COMPUTERS IN INDUSTRY, 2018, 卷号: 97, 页码: 47-53
Authors:  Liu, Quan;  Chen, Yingying;  Wang, Jinqiao;  Zhang, Sijiong
Favorite  |  View/Download:5/0  |  Submit date:2019/12/16
Image captioning  Pedestrian description  Multi-view captions  
Image Class Prediction by Joint Object, Context, and Background Modeling 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2018, 卷号: 28, 期号: 2, 页码: 428-438
Authors:  Zhang, Chunjie;  Zhu, Guibo;  Liang, Chao;  Zhang, Yifan;  Huang, Qingming;  Tian, Qi
View  |  Adobe PDF(2826Kb)  |  Favorite  |  View/Download:132/50  |  Submit date:2017/09/14
Background Modeling  Context Modeling  Image Class Prediction  Object Modeling  
MSMO: Multimodal Summarization with Multimodal Output 会议论文
, Brussels, Belgium, October 31th–November 4th, 2018
Authors:  Zhu, Junnan;  Li, Haoran;  Liu, Tianshang;  Zhou, Yu;  Zhang, Jiajun;  Zong, Chengqing
View  |  Adobe PDF(3533Kb)  |  Favorite  |  View/Download:97/17  |  Submit date:2018/10/09
Coupled Deep Learning for Heterogeneous Face Recognition 会议论文
, New Orleans, Louisiana, USA, February 2–7, 2018
Authors:  Xiang Wu;  Lingxiao Song;  Ran He;  Tieniu Tan
View  |  Adobe PDF(391Kb)  |  Favorite  |  View/Download:108/17  |  Submit date:2018/01/04