CASIA OpenIR

Browse/Search Results:  1-10 of 626 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:40/17  |  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:78/45  |  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:16/2  |  Submit date:2019/10/08
Image Annotation  Multiple Dependencies  Self-attention  Prediction Path  Triplet Margin Loss  
FERLrTc: 2D+3D facial expression recognition via low-rank tensor completion 期刊论文
SIGNAL PROCESSING, 2019, 卷号: 161, 页码: 74-88
Authors:  Fu, Yunfang;  Ruan, Qiuqi;  Luo, Ziyan;  Jin, Yi;  An, Gaoyun;  Wan, Jun
Favorite  |  View/Download:11/0  |  Submit date:2019/07/12
Tensor Tucker decomposition  2D+3D Facial expression recognition  Tensor low-rank representation  Tensor completion  Multi-modality  
Activation-based association profiles differentiate network roles across cognitive loads 期刊论文
HUMAN BRAIN MAPPING, 2019, 卷号: 40, 期号: 9, 页码: 2800-2812
Authors:  Zuo, Nianming;  Salami, Alireza;  Yang, Yihong;  Yang, Zhengyi;  Sui, Jing;  Jian, Tianzi
View  |  Adobe PDF(2320Kb)  |  Favorite  |  View/Download:19/1  |  Submit date:2019/07/12
association  cognitive performance  functional activation  functional magnetic resonance imaging (fMRI)  working memory  
Improving visual question answering using dropout and enhanced question encoder 期刊论文
PATTERN RECOGNITION, 2019, 卷号: 90, 期号: 1, 页码: 404-414
Authors:  Fang, Zhiwei;  Liu, Jing;  Li, Yong;  Qiao, Yanyuan;  Lu, Hanqing
View  |  Adobe PDF(1624Kb)  |  Favorite  |  View/Download:63/16  |  Submit date:2019/04/23
Visual question answering  Coherent dropout  Siamese dropout  Enhanced question encoder  
Dense semantic embedding network for image captioning 期刊论文
PATTERN RECOGNITION, 2019, 卷号: 90, 页码: 285-296
Authors:  Xiao, Xinyu;  Wang, Lingfeng;  Ding, Kun;  Xiang, Shiming;  Pan, Chunhong
Favorite  |  View/Download:30/0  |  Submit date:2019/04/23
Image captioning  Retrieval  High-level semantic information  Visual concept  Densely embedding  Long short-term memory  
多种模态下的人脸活体检测技术研究 学位论文
, 北京: 中国科学院大学, 2019
Authors:  肖金川
Adobe PDF(11213Kb)  |  Favorite  |  View/Download:64/1  |  Submit date:2019/06/19
人脸活体检测  人脸防伪  多模态  卷积神经网络  虚拟生成  
引入物理环境信息的问答技术研究 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2019
Authors:  姚轶群
Adobe PDF(2023Kb)  |  Favorite  |  View/Download:64/5  |  Submit date:2019/06/17
自然语言理解  物理环境  视觉  问答  推理  
MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification 期刊论文
PATTERN RECOGNITION, 2019, 卷号: 90, 页码: 436-449
Authors:  Li, Yabei;  Zhang, Zhang;  Cheng, Yanhua;  Wang, Liang;  Tan, Tieniu
Favorite  |  View/Download:25/0  |  Submit date:2019/04/23
Indoor scene classification  Multi-modal fusion  RGB-D  Attentive pooling