CASIA OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共4条,第1-4条 帮助

限定条件                    
已选(0)清除 条数/页:   排序方式:
Image captioning with triple-attention and stack parallel LSTM 期刊论文
NEUROCOMPUTING, 2018, 卷号: 319, 页码: 55-65
作者:  Zhu, Xinxin;  Li, Lixiang;  Liu, Jing;  Li, Ziyi;  Peng, Haipeng;  Niu, Xinxin
收藏  |  浏览/下载:252/0  |  提交时间:2019/12/16
Image caption  Deep learning  LSTM  CNN  Attention  
Collaborative Deconvolutional Neural Networks for Joint Depth Estimation and Semantic Segmentation 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 卷号: 29, 期号: 11, 页码: 5655-5666
作者:  Liu, Jing;  Wang, Yuhang;  Li, Yong;  Fu, Jun;  Li, Jiangyun;  Lu, Hanqing
收藏  |  浏览/下载:280/0  |  提交时间:2019/12/16
Deconvolutional neural network (DCNN)  depth estimation  fully connected conditional random field (CRF)  pointwise bilinear layer  semantic segmentation  soft mapping strategy  
Image Captioning with Word Gate and Adaptive Self-Critical Learning 期刊论文
APPLIED SCIENCES-BASEL, 2018, 卷号: 8, 期号: 6, 页码: 13
作者:  Zhu, Xinxin;  Li, Lixiang;  Liu, Jing;  Guo, Longteng;  Fang, Zhiwei;  Peng, Haipeng;  Niu, Xinxin
Adobe PDF(3312Kb)  |  收藏  |  浏览/下载:380/56  |  提交时间:2019/12/16
image caption  image understanding  deep learning  computer vision  
Captioning Transformer with Stacked Attention Modules 期刊论文
APPLIED SCIENCES-BASEL, 2018, 卷号: 8, 期号: 5
作者:  Zhu, Xinxin;  Li, Lixiang;  Liu, Jing;  Peng, Haipeng;  Niu, Xinxin
收藏  |  浏览/下载:215/0  |  提交时间:2018/10/10
Image Caption  Image Understanding  Deep Learning  Computer Vision