OPT OpenIR
(本次检索基于用户作品认领结果)

浏览/检索结果: 共7条,第1-7条 帮助

限定条件            
已选(0)清除 条数/页:   排序方式:
3G structure for image caption generation 期刊论文
Neurocomputing, 2019, 卷号: 330, 页码: 17-28
作者:  Yuan, Aihong;  Li, Xuelong;  Lu, Xiaoqiang
Adobe PDF(3091Kb)  |  收藏  |  浏览/下载:161/1  |  提交时间:2019/03/04
Multi-modal gated recurrent units for image description 期刊论文
Multimedia Tools and Applications, 2018, 卷号: 77, 期号: 22, 页码: 29847-29869
作者:  Li, Xuelong;  Yuan, Aihong;  Lu, Xiaoqiang
Adobe PDF(2037Kb)  |  收藏  |  浏览/下载:132/0  |  提交时间:2018/12/18
Image Description  Gated Recurrent Unit  Convolutional Neural Network  Multi-modal Embedding  
Action recognition by jointly using video proposal and trajectory 会议论文
Proceedings of the 2nd International Conference on Vision, Image and Signal Processing, ICVISP 2018, Las Vegas, NV, United states, 2018-08-27
作者:  Qi, Lei;  Lu, Xiaoqiang;  Li, Xuelong
Adobe PDF(1410Kb)  |  收藏  |  浏览/下载:150/1  |  提交时间:2019/03/07
Learning to Predict Eye Fixations via Multiresolution Convolutional Neural Networks 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 卷号: 29, 期号: 2, 页码: 392-404
作者:  Liu, Nian;  Han, Junwei;  Liu, Tianming;  Li, Xuelong
Adobe PDF(2296Kb)  |  收藏  |  浏览/下载:188/1  |  提交时间:2018/12/11
Contrast  Convolutional Neural Network (Cnn)  Eye Fixation Prediction  Rgb-d  Saliency Detection  
Person Re-identification by Multi-hypergraph Fusion 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2017, 卷号: 28, 期号: 11, 页码: 2763-2774
作者:  An, Le;  Chen, Xiaojing;  Yang, Songfan;  Li, Xuelong;  Chen, Xiaojing (xchen010@ucr.edu)
Adobe PDF(3831Kb)  |  收藏  |  浏览/下载:299/2  |  提交时间:2016/10/10
Feature Fusion  Graph Learning  Hypergraph  Person Re-identification  Surveillance  
Principal Component 2-D Long Short-Term Memory for Font Recognition on Single Chinese Characters 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2016, 卷号: 46, 期号: 3, 页码: 756-765
作者:  Tao, Dapeng;  Lin, Xu;  Jin, Lianwen;  Li, Xuelong;  Tao, DP
Adobe PDF(4029Kb)  |  收藏  |  浏览/下载:282/2  |  提交时间:2016/03/18
Font Recognition  Long Short-term Memory  Neurodynamic Models  Optical Character Recognition  Recurrent Neural Networks (Rnns)  
Two-Stage Learning to Predict Human Eye Fixations via SDAEs 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2016, 卷号: 46, 期号: 2, 页码: 487-498
作者:  Han, Junwei;  Zhang, Dingwen;  Wen, Shifeng;  Guo, Lei;  Liu, Tianming;  Li, Xuelong;  Han, JW
Adobe PDF(1649Kb)  |  收藏  |  浏览/下载:246/2  |  提交时间:2016/03/18
Deep Networks  Eye Fixation Prediction  Saliency Detection  Stacked Denoising Autoencoders ( Sdaes)