CASIA OpenIR

Browse/Search Results:  1-10 of 45 Help

Selected(0)Clear Items/Page:    Sort:
基于多标签分类的属性识别问题研究 学位论文
工学博士, 北京: 中国科学院自动化研究所, 2019
Authors:  李乔哲
Adobe PDF(10540Kb)  |  Favorite  |  View/Download:33/1  |  Submit date:2020/01/14
属性识别  多标签分类  行人属性识别  群体属性识别  
Pedestrian Attribute Recognition by Joint Visual-semantic Reasoning and Knowledge Distillation 会议论文
, 中国澳门, 2019-8
Authors:  Li QZ(李乔哲);  Zhao X(赵鑫);  He R(赫然);  Huang KQ(黄凯奇)
View  |  Adobe PDF(640Kb)  |  Favorite  |  View/Download:38/8  |  Submit date:2020/01/14
Visual-Semantic Graph Reasoning for Pedestrian Attribute Recognition 会议论文
, 夏威夷,美国, 2019-1-27
Authors:  Li QZ(李乔哲);  Zhao X(赵鑫);  He R(赫然);  Huang KQ(黄凯奇)
View  |  Adobe PDF(403Kb)  |  Favorite  |  View/Download:29/5  |  Submit date:2020/01/14
Towards fast and kernelized orthogonal discriminant analysis on person re-identification 期刊论文
Pattern Recognition, 2019, 期号: 94, 页码: 218-229
Authors:  Min Cao;  Chen Chen;  Xiyuan Hu;  Silong Peng
View  |  Adobe PDF(1700Kb)  |  Favorite  |  View/Download:49/10  |  Submit date:2019/09/10
Person Re-identificationmetric Learningsingularity Problemorthogonal Discriminant Analysis  
Unsupervised Object-Level Video Summarization with Online Motion Auto-Encoder 期刊论文
Pattern Recognition Letters, 2018, 期号: 无, 页码: 无
Authors:  Yujia Zhang;  Xiaodan Liang;  Dingwen Zhang;  Min Tan;  Eric P. Xing
View  |  Adobe PDF(3281Kb)  |  Favorite  |  View/Download:30/9  |  Submit date:2019/05/07
Object-level Video Summarization  Online Motion Auto-encoder  Stacked Sparse Lstm Auto-encoder  
基于时空模型的行为识别研究 学位论文
, 北京: 中国科学院大学, 2018
Authors:  曹聪琦
Adobe PDF(13483Kb)  |  Favorite  |  View/Download:204/14  |  Submit date:2018/05/30
行为识别  时空模型  特征提取  序列建模  深度学习  卷积神经网络  循环神经网络  
EgoGesture: A New Dataset and Benchmark for Egocentric Hand Gesture Recognition 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 卷号: 20, 期号: 5, 页码: 1038-1050
Authors:  Zhang, Yifan;  Cao, Congqi;  Cheng, Jian;  Lu, Hanqing
View  |  Adobe PDF(1260Kb)  |  Favorite  |  View/Download:179/69  |  Submit date:2018/05/05
Benchmark  Dataset  Egocentric Vision  Gesture Recognition  First-person View  
Parallel Imaging: A Unified Theoretical Framework for Image Generation 会议论文
, Jinan, China, 20-22 Oct. 2017
Authors:  Kunfeng Wang;  Yue Lu;  Yutong Wang;  Fei-Yue Wang
View  |  Adobe PDF(1049Kb)  |  Favorite  |  View/Download:121/39  |  Submit date:2018/01/08
Multi-modal max-margin supervised topic model for social event analysis 期刊论文
Multimedia Tools and Applications, 2018, 期号: 99, 页码: 1–20
Authors:  Feng Xue;  Jianwei Wang;  Shengsheng Qian;  Tianzhu Zhang;  Xueliang Liu;  Changsheng Xu
View  |  Adobe PDF(2883Kb)  |  Favorite  |  View/Download:109/29  |  Submit date:2018/02/07
Social Event Classification  Multi-modal  Max-margin  Social Media  Topic Model  
RGB-D-based Human Motion Recognition with Deep Learning: A Survey 期刊论文
Computer Vision and Image Understanding, 2018, 卷号: PP, 期号: 1, 页码: 1-22
Authors:  Pichao Wang;  Wanqing Li;  Philip Ogunbona;  Jun Wan;  Sergio Escalera
View  |  Adobe PDF(5390Kb)  |  Favorite  |  View/Download:63/4  |  Submit date:2018/10/04
Human Motion Recognition  Rgb-d Data  Deep Learning  Survey