中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共8条，第1-8条 帮助

限定条件    
已选(0)清除 条数/页：   排序方式：
Temporal-adaptive sparse feature aggregation for video object detection 期刊论文
PATTERN RECOGNITION, 2022, 卷号: 127, 页码: 108587
作者:  He, Fei;  Li, Qiaozhe;  Zhao, Xin;  Huang, Kaiqi
Adobe PDF(1549Kb)  |  收藏  |  浏览/下载：334/44  |  提交时间：2022/06/10
Video object detection  Temporal-adaptive sparse sampling  Pixel-adaptive aggregation  Object-relational aggregation  
Partial NIR-VIS Heterogeneous Face Recognition With Automatic Saliency Search 期刊论文
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2021, 卷号: 16, 页码: 5003-5017
作者:  Luo, Mandi;  Ma, Xin;  Li, Zhihang;  Cao, Jie;  He, Ran
Adobe PDF(4346Kb)  |  收藏  |  浏览/下载：308/61  |  提交时间：2021/12/28
Face recognition  Task analysis  Visualization  Image recognition  Lighting  Feature extraction  Training  Heterogeneous face recognition  near infrared-visible matching  information bottleneck  neural architecture search  
Unsupervised Video Summarization via Relation-Aware Assignment Learning 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 3203-3214
作者:  Gao, Junyu;  Yang, Xiaoshan;  Zhang, Yingying;  Xu, Changsheng
Adobe PDF(3649Kb)  |  收藏  |  浏览/下载：339/66  |  提交时间：2021/11/03
Feature extraction  Training  Optimization  Semantics  Recurrent neural networks  Task analysis  Graph neural network  unsupervised learning  video summarization  
Richly Activated Graph Convolutional Network for Robust Skeleton-Based Action Recognition 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2021, 卷号: 31, 期号: 5, 页码: 1915-1925
作者:  Song, Yi-Fan;  Zhang, Zhang;  Shan, Caifeng;  Wang, Liang
Adobe PDF(3381Kb)  |  收藏  |  浏览/下载：410/65  |  提交时间：2021/06/15
Skeleton  Robustness  Noise measurement  Three-dimensional displays  Degradation  Standards  Feature extraction  Action recognition  skeleton  activation map  graph convolutional network  occlusion  jittering  
Dynamical Channel Pruning by Conditional Accuracy Change for Deep Neural Networks 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 卷号: 无, 期号: 无, 页码: 无
作者:  Chen, Zhiqiang;  Xu, Ting-Bing;  Du, Changde;  Liu, Cheng-Lin;  He, Huiguang
浏览  |  Adobe PDF(4352Kb)  |  收藏  |  浏览/下载：308/68  |  提交时间：2021/01/27
Conditional accuracy change (CAC), direct criterion, dynamical channel pruning, neural network compression, structure shaping.  
ScleraSegNet: An Attention Assisted U-Net Model for Accurate Sclera Segmentation 期刊论文
IEEE Transactions on Biometrics, Behavior, and Identity Science, 2020, 卷号: 2, 期号: 1, 页码: 40-54
作者:  Wang, Caiyong;  Wang, Yunlong;  Liu, Yunfan;  He, Zhaofeng;  He, Ran;  Sun, Zhenan
浏览  |  Adobe PDF(5290Kb)  |  收藏  |  浏览/下载：424/128  |  提交时间：2020/06/10
Sclera segmentation  sclera recognition  U-net  attention mechanism  SSBC  
Recurrent Prediction with Spatio-temporal Attention for Crowd Attribute Recognition 期刊论文
IEEE Transactions on Circuits and Systems for Video Technology, 2019, 卷号: 30, 期号: Early Access, 页码: 1 - 1
作者:  Li, Qiaozhe;  Zhao, Xin;  He, Ran;  Huang, Kaiqi
浏览  |  Adobe PDF(2648Kb)  |  收藏  |  浏览/下载：416/106  |  提交时间：2020/01/14
Crowd video understanding , Attribute recognition , Attention mechanism , Multi-label classification  
3D Aided Duet GANs for Multi-View Face Image Synthesis 期刊论文
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2019, 卷号: 14, 期号: 8, 页码: 2028-2042
作者:  Cao, Jie;  Hu, Yibo;  Yu, Bing;  He, Ran;  Sun, Zhenan
浏览  |  Adobe PDF(4053Kb)  |  收藏  |  浏览/下载：437/85  |  提交时间：2019/07/12
Face rotation and frontalization  Multi-view face synthesis  Pose-invariant face recognition  Face reconstruction