OPT OpenIR

浏览/检索结果: 共9条,第1-9条 帮助

限定条件    
已选(0)清除 条数/页:   排序方式:
CAM-RNN: Co-Attention Model Based RNN for Video Captioning 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 11
作者:  Zhao, Bin;  Li, Xuelong;  Lu, Xiaoqiang
Adobe PDF(6676Kb)  |  收藏  |  浏览/下载:265/2  |  提交时间:2019/09/24
Attention model  video captioning  recurrent neural network  
From Deterministic to Generative: Multimodal Stochastic RNNs for Video Captioning 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2019, 卷号: 30, 期号: 10, 页码: 3047-3058
作者:  Song, Jingkuan;  Guo, Yuyu;  Gao, Lianli;  Li, Xuelong;  Hanjalic, Alan;  Shen, Heng Tao
Adobe PDF(3046Kb)  |  收藏  |  浏览/下载:198/0  |  提交时间:2019/10/11
Recurrent neural network (RNN)  uncertainty  video captioning  
Exploiting spatial relation for fine-grained image classification 期刊论文
Pattern Recognition, 2019, 卷号: 91, 页码: 47-55
作者:  Qi, Lei;  Lu, Xiaoqiang;  Li, Xuelong
Adobe PDF(1595Kb)  |  收藏  |  浏览/下载:204/1  |  提交时间:2019/03/29
用于空间在轨组装模块化光学主反射镜的对接技术研究 学位论文
, 北京: 中国科学院大学, 2019
作者:  李旭鹏
Adobe PDF(4792Kb)  |  收藏  |  浏览/下载:165/0  |  提交时间:2019/06/14
空间在轨组装  模块化对接技术  双点接触模型  双弹性缓冲模型  被动式轴向锁紧机构  
Spatiotemporal interest point detector exploiting appearance and motion-variation information 期刊论文
JOURNAL OF ELECTRONIC IMAGING, 2019, 卷号: 28, 期号: 3
作者:  Li, Yanshan;  Li, Qingteng;  Huang, Qinghua;  Xia, Rongjie;  Li, Xuelong
Adobe PDF(3095Kb)  |  收藏  |  浏览/下载:170/0  |  提交时间:2019/07/19
spatiotemporal interest point detector  spatiotemporal interest point  geometric algebra  video  
Histograms of Gaussian normal distribution for 3D feature matching in cluttered scenes 期刊论文
VISUAL COMPUTER, 2019, 卷号: 35, 期号: 4, 页码: 489-505
作者:  Zhou, Wei;  Ma, Caiwen;  Yao, Tong;  Chang, Peng;  Zhang, Qi;  Kuijper, Arjan
Adobe PDF(3114Kb)  |  收藏  |  浏览/下载:184/3  |  提交时间:2019/04/30
Local surface patch  Local reference frame  Local feature descriptor  Point cloud  
Skeleton-Based Action Recognition with Key-Segment Descriptor and Temporal Step Matrix Model 期刊论文
IEEE Access, 2019, 卷号: 7, 页码: 169782-169795
作者:  Li, Ruimin;  Fu, Hong;  Lo, Wai-Lun;  Chi, Zheru;  Song, Zongxi;  Wen, Desheng
Adobe PDF(2563Kb)  |  收藏  |  浏览/下载:131/0  |  提交时间:2020/02/28
Skeleton-based action recognition  view alignment  scale normalization  key-segment descriptor  temporal step matrix model  
Sample and Structure-Guided Network for Road Crack Detection 期刊论文
IEEE ACCESS, 2019, 卷号: 7, 页码: 130032-130043
作者:  Wu, Siyuan;  Fang, Jie;  Zheng, Xiangtao
Adobe PDF(4285Kb)  |  收藏  |  浏览/下载:189/2  |  提交时间:2019/10/11
Road crack detection  neural network  representation capability  sample imbalance  structural information  
Skeleton-Based Action Recognition With Key-Segment Descriptor and Temporal Step Matrix Model 期刊论文
IEEE ACCESS, 2019, 卷号: 7, 页码: 169782-169795
作者:  Li, Ruimin;  Fu, Hong;  Lo, Wai-Lun;  Chi, Zheru;  Song, Zongxi;  Wen, Desheng
Adobe PDF(2559Kb)  |  收藏  |  浏览/下载:121/0  |  提交时间:2020/10/30
Skeleton  Motion segmentation  Hidden Markov models  Feature extraction  Three-dimensional displays  Image segmentation  Computational modeling  Skeleton-based action recognition  view alignment  scale normalization  key-segment descriptor  temporal step matrix model