CASIA OpenIR

Browse/Search Results:  1-10 of 468 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
Graph-Based Registration and Blending for Undersea Image Stitching 期刊论文
ROBOTICA, 2020, 卷号: 38, 期号: 3, 页码: 396-409
Authors:  Yang, Xu;  Liu, Zhi-Yong;  Qiao, Hong;  Su, Jian-Hua;  Ji, Da-Xiong;  Zang, Ai-Yun;  Huang, Hai
Favorite  |  View/Download:1/0  |  Submit date:2020/03/30
Undersea image stitching  Feature correspondence  Graph matching  Energy minimization  Nonsubmodular function  
Food det: Detecting foods in refrigerator with supervised transformer network 期刊论文
NEUROCOMPUTING, 2020, 卷号: 379, 页码: 162-171
Authors:  Zhu, Yousong;  Zhao, Xu;  Zhao, Chaoyang;  Wang, Jinqiao;  Lu, Hanqing
Favorite  |  View/Download:0/0  |  Submit date:2020/03/30
Food detection  Spatial transformer  Object detection  
Deep attention based music genre classification 期刊论文
NEUROCOMPUTING, 2020, 卷号: 372, 页码: 84-91
Authors:  Yu, Yang;  Luo, Sen;  Liu, Shenglan;  Qiao, Hong;  Liu, Yang;  Feng, Lin
Favorite  |  View/Download:0/0  |  Submit date:2020/03/30
Music genre classification  Deep neural networks  Serial attention  Parallelized attention  
Multi-view laplacian eigenmaps based on bag-of-neighbors for RGB-D human emotion recognition 期刊论文
INFORMATION SCIENCES, 2020, 卷号: 509, 页码: 243-256
Authors:  Liu, Shenglan;  Guo, Shuai;  Wang, Wei;  Qiao, Hong;  Wang, Yang;  Luo, Wenbo
Favorite  |  View/Download:0/0  |  Submit date:2020/03/30
Human emotion recognition  MvLE  BON  MHON  RGB-D  
Multi-view laplacian least squares for human emotion recognition 期刊论文
NEUROCOMPUTING, 2019, 卷号: 370, 页码: 78-87
Authors:  Guo, Shuai;  Feng, Lin;  Feng, Zhan-Bo;  Li, Yi-Hao;  Wang, Yang;  Liu, Sheng-Lan;  Qiao, Hong
Favorite  |  View/Download:0/0  |  Submit date:2020/03/30
Multi-view learning  Laplacian least squares  Subspace learning  Human emotion recognition  
Adversarial image generation by combining content and style 期刊论文
IET IMAGE PROCESSING, 2019, 卷号: 13, 期号: 14, 页码: 2716-2723
Authors:  Liu, Songyan;  Zhao, Chaoyang;  Gao, Yunze;  Wang, Jinqiao;  Tang, Ming
Favorite  |  View/Download:0/0  |  Submit date:2020/03/30
image recognition  feature extraction  learning (artificial intelligence)  image texture  adversarial image generation  unique style  reference images  style feature extraction module  style specific image generation model  double-cycle training strategy  natural-content pairs  input natural images  style exchange  style-exchanged images  licence-plate image  handbags images  
Nonlinear Asymmetric Multi-Valued Hashing 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2019, 卷号: 41, 期号: 11, 页码: 2660-2676
Authors:  Da, Cheng;  Meng, Gaofeng;  Xiang, Shiming;  Ding, Kun;  Xu, Shibiao;  Yang, Qing;  Pan, Chunhong
View  |  Adobe PDF(2583Kb)  |  Favorite  |  View/Download:162/38  |  Submit date:2018/10/07
Asymmetric hashing  multi-valued embeddings  binary sparse representation  nonlinear transformation  
Integrated thermal assembly using hierarchical kernel regression method 期刊论文
ADVANCED ROBOTICS, 2019, 页码: 15
Authors:  Su, Jianhua;  Chen, Bin;  Liu, Chuankai;  Yang, Xu;  Liu, Zhiyong;  Qiao, Hong
Favorite  |  View/Download:14/0  |  Submit date:2019/12/16
Hierarchical kernel regression  integration thermal assembly model  interference-fit  
Cross-modality interactive attention network for multispectral pedestrian detection 期刊论文
INFORMATION FUSION, 2019, 卷号: 50, 页码: 20-29
Authors:  Zhang, Lu;  Liu, Zhiyong;  Zhang, Shifeng;  Yang, Xu;  Qiao, Hong;  Huang, Kaizhu;  Hussain, Amir
Favorite  |  View/Download:42/0  |  Submit date:2019/07/11
Pedestrian detection  Modality fusion  Cross-modality attention  Deep neural networks  
Adaptive Attention Annotation Model: Optimizing the Prediction Path through Dependency Fusion 期刊论文
KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2019, 卷号: 13, 期号: 9, 页码: 4665-4683
Authors:  Wang, Fangxin;  Liu, Jie;  Zhang, Shuwu;  Zhang, Guixuan;  Zheng, Yang;  Li, Xiaoqian;  Liang, Wei;  Li, Yuejun
View  |  Adobe PDF(1061Kb)  |  Favorite  |  View/Download:45/4  |  Submit date:2019/10/08
image annotation  multiple dependencies  self-attention  prediction path  Triplet Margin loss