CASIA OpenIR

浏览/检索结果: 共15条,第1-10条 帮助

限定条件    
已选(0)清除 条数/页:   排序方式:
Holographic Feature Learning of Egocentric-Exocentric Videos for Multi-Domain Action Recognition 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 24, 页码: 2273-2286
作者:  Huang, Yi;  Yang, Xiaoshan;  Gao, Junyun;  Xu, Changsheng
Adobe PDF(2409Kb)  |  收藏  |  浏览/下载:313/62  |  提交时间:2022/07/25
Videos  Feature extraction  Visualization  Task analysis  Computational modeling  Target recognition  Prototypes  Egocentric videos  exocentric videos  holographic feature  multi-domain  action recognition  
Single-Image Specular Highlight Removal via Real-World Dataset Construction 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 页码: 12
作者:  Wu ZQ(吴仲琦);  Zhuang CQ(庄传青);  Shi J(石剑);  Guo JW(郭建伟);  Xiao J(肖俊);  Zhang XP(张晓鹏);  Yan DM(严冬明)
Adobe PDF(49307Kb)  |  收藏  |  浏览/下载:242/94  |  提交时间:2022/06/15
Specular highlight removal, PSD-Dataset, Deep learning  
Visual Question Answering With Dense Inter- and Intra-Modality Interactions 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 3518-3529
作者:  Liu, Fei;  Liu, Jing;  Fang, Zhiwei;  Hong, Richang;  Lu, Hanqing
Adobe PDF(2891Kb)  |  收藏  |  浏览/下载:265/58  |  提交时间:2021/12/28
Visualization  Knowledge discovery  Connectors  Encoding  Task analysis  Image coding  Stacking  Visual question answering  attention  dense interactions  
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:298/60  |  提交时间:2021/11/03
Feature extraction  Training  Optimization  Semantics  Recurrent neural networks  Task analysis  Graph neural network  unsupervised learning  video summarization  
Joint Learning in the Spatio-Temporal and Frequency Domains for Skeleton-Based Action Recognition 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 卷号: 22, 期号: 9, 页码: 2207-2220
作者:  Guyue, Hu;  Bo, Cui;  Shan, Yu
Adobe PDF(4803Kb)  |  收藏  |  浏览/下载:279/54  |  提交时间:2020/09/28
Skeleton-based Action Recognition  Frequency Attention  Synchronous Local and Non-local Learning  Soft-margin Focal Loss  Pesudo Multi-task Learning  
Show, Tell, and Polish: Ruminant Decoding for Image Captioning 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 卷号: 22, 期号: 8, 页码: 2149-2162
作者:  Guo, Longteng;  Liu, Jing;  Lu, Shichen;  Lu, Hanqing
Adobe PDF(4378Kb)  |  收藏  |  浏览/下载:201/30  |  提交时间:2020/08/31
Image captioning  Multi-pass decoding  Rumination  
WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 卷号: 22, 期号: 2, 页码: 380-393
作者:  Zhang, Shifeng;  Xie, Yiliang;  Wan, Jun;  Xia, Hansheng;  Li, Stan Z.;  Guo, Guodong
浏览  |  Adobe PDF(6651Kb)  |  收藏  |  浏览/下载:303/52  |  提交时间:2020/04/07
Benchmark testing  Detectors  Training  Urban areas  Cameras  Task analysis  Deep learning  Pedestrian detection  dataset  rich diversity  high density  
Effective Image Retrieval via Multilinear Multi-Index Fusion 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 卷号: 21, 期号: 11, 页码: 2878-2890
作者:  Zhang, Zhizhong;  Xie, Yuan;  Zhang, Wensheng;  Tian, Qi
浏览  |  Adobe PDF(1024Kb)  |  收藏  |  浏览/下载:390/99  |  提交时间:2020/03/30
Visualization  Image representation  Optimization  Buildings  Indexing  Image retrieval  multi-index fusion  tensor multi-rank  person re-identification  
Deep Multi-Modality Adversarial Networks for Unsupervised Domain Adaptation 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 卷号: 21, 期号: 9, 页码: 2419-2431
作者:  Ma, Xinhong;  Zhang, Tianzhu;  Xu, Changsheng
Adobe PDF(2142Kb)  |  收藏  |  浏览/下载:331/41  |  提交时间:2019/12/16
Unsupervised domain adaptation  triplet loss  stacked attention  multi-modality  social event recognition  
Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-Scale Image Retrieval 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 卷号: 21, 期号: 6, 页码: 1551-1562
作者:  Xu, Jian;  Wang, Chunheng;  Qi, Chengzuo;  Shi, Cunzhao;  Xiao, Baihua
浏览  |  Adobe PDF(4727Kb)  |  收藏  |  浏览/下载:339/75  |  提交时间:2019/07/11
Iterative manifold embedding layer  image retrieval  incomplete data