CASIA OpenIR

Browse/Search Results:  1-10 of 98 Help

Selected(0)Clear Items/Page:    Sort:
行人分割与识别研究 学位论文
工学博士, 中国科学院自动化研究所: 中国科学院大学, 2019
Authors:  宋纯锋
Adobe PDF(9416Kb)  |  Favorite  |  View/Download:24/0  |  Submit date:2020/01/13
行人图像分割,行人识别,步态识别,弱监督学习  
GaitNet: An end-to-end network for gait based human identification 期刊论文
PATTERN RECOGNITION, 2019, 卷号: 96, 期号: 106988, 页码: 11
Authors:  Song, Chunfeng;  Huang, Yongzhen;  Huang, Yan;  Jia, Ning;  Wang, Liang
View  |  Adobe PDF(3015Kb)  |  Favorite  |  View/Download:15/5  |  Submit date:2019/12/16
Gait recognition  Video-based human identification  End-to-end CNN  Joint learning  
跨摄像头行人重识别问题研究与应用 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:  曹敏
Adobe PDF(13205Kb)  |  Favorite  |  View/Download:47/6  |  Submit date:2019/12/09
行人重识别  度量学习  重排序  奇异问题  区域特定的度量函数  排序损失函数  群体信息  近邻样本  
ESI计算机科学领域热点论文(2019年11月) 其他
2019-11-19
Authors:  张桂英
Adobe PDF(602Kb)  |  Favorite  |  View/Download:70/15  |  Submit date:2019/11/19
Deep imitator: handwriting calligraphy imitation via deep attention networks 期刊论文
Pattern Recogniton, 2019, 期号: 已接收, 页码: 已接收
Authors:  Zhao BC(赵博程);  Tao JH(陶建华);  Yang MH(杨明浩);  Tian ZK(田正坤);  Fan CH(范存航);  Bai Y(白烨)
View  |  Adobe PDF(2498Kb)  |  Favorite  |  View/Download:30/11  |  Submit date:2020/01/05
calligraphy imitation, attention, mata-style matrix, condition Gated Recurrent Unit  
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:75/35  |  Submit date:2019/09/26
A Performance Evaluation of Local Features for Image-Based 3D Reconstruction 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 10, 页码: 4774-4789
Authors:  Fan, Bin;  Kong, Qingqun;  Wang, Xinchao;  Wang, Zhiheng;  Xiang, Shiming;  Pan, Chunhong;  Fua, Pascal
View  |  Adobe PDF(3986Kb)  |  Favorite  |  View/Download:12/0  |  Submit date:2019/12/16
Local feature  image reconstruction  structure from motion (SFM)  3D vision  image matching  
Adversarial Deep Tracking 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2019, 卷号: 29, 期号: 7, 页码: 1998-2011
Authors:  Zhao, Fei;  Wang, Jinqiao;  Wu, Yi;  Tang, Ming
View  |  Adobe PDF(6455Kb)  |  Favorite  |  View/Download:52/20  |  Submit date:2019/04/30
Visual tracking  deep learning  adversarial training  attention  
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:89/30  |  Submit date:2019/04/23
Visual question answering  Coherent dropout  Siamese dropout  Enhanced question encoder  
SOSNet: Second Order Similarity Regularization for Local Descriptor Learning 会议论文
, 美国 长滩, 2019-6
Authors:  Yurun Tian;  Xin Yu;  Bin Fan;  Fuchao Wu;  Huub Heijen;  Vassileios Balntas
View  |  Adobe PDF(681Kb)  |  Favorite  |  View/Download:102/33  |  Submit date:2019/06/10