CASIA OpenIR

Browse/Search Results:  1-10 of 25 Help

Selected(0)Clear Items/Page:    Sort:
Long video question answering: A Matching-guided Attention Model 期刊论文
PATTERN RECOGNITION, 2020, 卷号: 102, 页码: 11
Authors:  Wang, Weining;  Huang, Yan;  Wang, Liang
Favorite  |  View/Download:0/0  |  Submit date:2020/06/02
Long video QA  Matching-guided attention  
Frame-GAN: Increasing the frame rate of gait videos with generative adversarial networks 期刊论文
NEUROCOMPUTING, 2020, 卷号: 380, 页码: 95-104
Authors:  Xue, Wei;  Ai, Hong;  Sun, Tianyu;  Song, Chunfeng;  Huang, Yan;  Wang, Liang
Favorite  |  View/Download:18/0  |  Submit date:2020/03/30
Gait recognition  Generative adversarial networks  Metric learning  Deep learning  
Discriminative structure learning of sum-product networks for data stream classification 期刊论文
NEURAL NETWORKS, 2020, 卷号: 123, 页码: 163-175
Authors:  Sun, Zhengya;  Liu, Cheng-Lin;  Niu, Jinghao;  Zhang, Wensheng
Favorite  |  View/Download:11/0  |  Submit date:2020/03/30
Sum-product network  Discriminative structure learning  Data stream classification  
Realtime multi-scale scene text detection with scale-based region proposal network 期刊论文
PATTERN RECOGNITION, 2020, 卷号: 98, 页码: 14
Authors:  He, Wenhao;  Zhang, Xu-Yao;  Yin, Fei;  Luo, Zhenbo;  Ogier, Jean-Marc;  Liu, Cheng-Lin
Favorite  |  View/Download:11/0  |  Submit date:2020/03/30
Scene text detection  Multi-scale  Speedup  Scale-based region proposal network  
Deep Unbiased Embedding Transfer for Zero-Shot Learning 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 页码: 1958-1971
Authors:  Jia, Zhen;  Zhang, Zhang;  Wang, Liang;  Shan, Caifeng;  Tan, Tieniu
Favorite  |  View/Download:12/0  |  Submit date:2020/03/30
Visualization  Feature extraction  Semantics  Training  Seals  Prototypes  Indexes  Zero-shot learning  image classification  projection domain shift  convolutional neural network  generative adversarial network  
Tangent Fisher Vector on Matrix Manifolds for Action Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 页码: 3052-3064
Authors:  Luo, Guan;  Wei, Jiutong;  Hu, Weiming;  Maybank, Stephen J.
Favorite  |  View/Download:16/0  |  Submit date:2020/04/07
Manifolds  Video sequences  Observability  Videos  Covariance matrices  Kernel  Computational modeling  Action recognition  Fisher vector  Grassmann manifold  Hankel matrix  matrix manifold  
Geometry Guided Pose-Invariant Facial Expression Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 页码: 4445-4460
Authors:  Zhang, Feifei;  Zhang, Tianzhu;  Mao, Qirong;  Xu, Changsheng
Favorite  |  View/Download:0/0  |  Submit date:2020/06/02
Facial expression recognition  facial image synthesis  generative adversarial network  facial landmarks  
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:75/27  |  Submit date:2019/12/16
Gait recognition  Video-based human identification  End-to-end CNN  Joint learning  
Dual L-1-Normalized Context Aware Tensor Power Iteration and Its Applications to Multi-object Tracking and Multi-graph Matching 期刊论文
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2019, 页码: 33
Authors:  Hu, Weiming;  Shi, Xinchu;  Zhou, Zongwei;  Xing, Junliang;  Ling, Haibin;  Maybank, Stephen
Favorite  |  View/Download:107/0  |  Submit date:2019/12/16
Multi-dimensional assignment  Context  hyper-context aware tensor power iteration  Multi-object tracking  Multi-graph matching  
Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 10, 页码: 5105-5120
Authors:  Li, Debang;  Wu, Huikai;  Zhang, Junge;  Huang, Kaiqi
Favorite  |  View/Download:23/0  |  Submit date:2019/12/16
Reinforcement learning  adversarial learning  image cropping