CASIA OpenIR

Browse/Search Results:  1-10 of 41 Help

Selected(0)Clear Items/Page:    Sort:
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:9/3  |  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:160/13  |  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:110/37  |  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:83/23  |  Submit date:2018/01/08
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:44/2  |  Submit date:2018/10/04
Human Motion Recognition  Rgb-d Data  Deep Learning  Survey  
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:  Xue, Feng;  Wang, Jianwei;  Qian, Shengsheng;  Zhang, Tianzhu;  Liu, Xueliang;  Xu, Changsheng
View  |  Adobe PDF(2883Kb)  |  Favorite  |  View/Download:66/17  |  Submit date:2018/02/07
Social Event Classification  Multi-modal  Max-margin  Social Media  Topic Model  
An Equalized Global Graph Model-Based Approach for Multicamera Object Tracking 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2017, 卷号: 27, 期号: 11, 页码: 2367-2381
Authors:  Chen, Weihua;  Cao, Lijun;  Chen, Xiaotang;  Huang, Kaiqi
View  |  Adobe PDF(16585Kb)  |  Favorite  |  View/Download:47/5  |  Submit date:2018/03/03
Global Graph Model  Multicamera Multiobject Tracking  Nonoverlapping Visual Object Tracking  
An Equalised Global Graphical Model-Based Approach for Multi-Camera Object Tracking 期刊论文
IEEE Transactions on Circuits and Systems for Video Technology, 2017, 卷号: 27, 期号: 11, 页码: 2367-2381
Authors:  Weihua Chen;  Lijun Cao;  Xiaotang Chen;  Kaiqi Huang
View  |  Adobe PDF(23628Kb)  |  Favorite  |  View/Download:62/13  |  Submit date:2018/01/03
Multi-camera Multi-object Tracking  Global Graph Model  Non-overlapping Visual Object Tracking  
多摄像机视觉目标跟踪关键问题研究 学位论文
, 北京: 中国科学院研究生院, 2017
Authors:  陈威华
Adobe PDF(29116Kb)  |  Favorite  |  View/Download:84/8  |  Submit date:2018/01/25
单目标跟踪  单摄像机多目标跟踪  跨摄像机多目标跟踪  多摄像机目标跟踪  行人再识别  
Parallel vision for perception and understanding of complex scenes: methods, framework, and perspectives 期刊论文
ARTIFICIAL INTELLIGENCE REVIEW, 2017, 卷号: 48, 期号: 3, 页码: 299-329
Authors:  Wang, Kunfeng;  Gou, Chao;  Zheng, Nanning;  Rehg, James M.;  Wang, Fei-Yue
View  |  Adobe PDF(2235Kb)  |  Favorite  |  View/Download:134/66  |  Submit date:2018/01/05
Visual Perception  Complex Scenes  Parallel Vision  Acp Methodology  Computer Graphics  Image Synthesis