中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共19条，第1-10条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
SOZIL: Self-Optimal Zero-shot Imitation Learning 期刊论文
IEEE Trans on Cognitive and Developmental System, 2021, 卷号: 15, 期号: 1, 页码: 1
作者:  Peng Hao;  Tao Lu;  Shaowei Cui;  Junhang Wei;  Yinghao Cai;  Shuo Wang
Adobe PDF(13840Kb)  |  收藏  |  浏览/下载：179/30  |  提交时间：2022/04/08
imitation learning  learning from observation  keyframe demonstration  
Beyond Crack: Fine-Grained Pavement Defect Segmentation Using Three-Stream Neural Networks 期刊论文
IEEE Transactions on Intelligent Transportation Systems, 2021, 卷号: /, 期号: /, 页码: /
作者:  Zhang, Yujia;  Wu, Junxian;  Li, Qianzhong;  Zhao, Xiaoguang;  Tan, Min
Adobe PDF(12585Kb)  |  收藏  |  浏览/下载：362/59  |  提交时间：2022/04/02
Fine-grained defect segmentation  Crack detection  Semantic segmentation  Pavement inspection  
Question-Guided Erasing-Based Spatiotemporal Attention Learning for Video Question Answering 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 0
作者:  Liu, Fei;  Liu, Jing;  Hong, Richang;  Lu, Hanqing
Adobe PDF(3550Kb)  |  收藏  |  浏览/下载：365/93  |  提交时间：2022/01/27
video question answering  attention mechanism  metric learning  
Efficient Pairwise 3-D Registration of Urban Scenes via Hybrid Structural Descriptors 期刊论文
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 页码: 17
作者:  Zhang, Long;  Guo, Jianwei;  Cheng, Zhanglin;  Xiao, Jun;  Zhang, Xiaopeng
Adobe PDF(13657Kb)  |  收藏  |  浏览/下载：269/6  |  提交时间：2022/01/27
Three-dimensional displays  Shape  Feature extraction  Semantics  Robustness  Cloud computing  Virtual reality  Descriptor  hybrid structure  point cloud  registration  urban scene  
ECBC: Efficient Convolution via Blocked Columnizing 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 页码: 13
作者:  Zhao, Tianli;  Hu, Qinghao;  He, Xiangyu;  Xu, Weixiang;  Wang, Jiaxing;  Leng, Cong;  Cheng, Jian
Adobe PDF(3003Kb)  |  收藏  |  浏览/下载：331/40  |  提交时间：2022/01/27
Convolution  Tensors  Layout  Memory management  Indexes  Transforms  Performance evaluation  Convolutional neural networks (CNNs)  direct convolution  high performance computing for mobile devices  im2col convolution  memory-efficient convolution (MEC)  
Multitask Learning for Ship Detection From Synthetic Aperture Radar Images 期刊论文
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 卷号: 14, 页码: 8048-8062
作者:  Zhang, Xin;  Huo, Chunlei;  Xu, Nuo;  Jiang, Hangzhi;  Cao, Yong;  Ni, Lei;  Pan, Chunhong
Adobe PDF(12575Kb)  |  收藏  |  浏览/下载：300/50  |  提交时间：2021/11/03
Task analysis  Feature extraction  Radar polarimetry  Object detection  Marine vehicles  Detectors  Synthetic aperture radar  Multitask learning  synthetic aperture radar (SAR)  SAR ship detection  
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：347/69  |  提交时间：2021/11/03
Feature extraction  Training  Optimization  Semantics  Recurrent neural networks  Task analysis  Graph neural network  unsupervised learning  video summarization  
Learning Coarse-to-Fine Graph Neural Networks for Video-Text Retrieval 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 23, 页码: 2386-2397
作者:  Wang, Wei;  Gao, Junyu;  Yang, Xiaoshan;  Xu, Changsheng
Adobe PDF(2165Kb)  |  收藏  |  浏览/下载：355/47  |  提交时间：2021/11/02
Feature extraction  Encoding  Task analysis  Semantics  Data models  Cognition  Focusing  Video-text retrieval  graph neural network  coarse-to-fine strategy  
Heterogeneous Relational Graph Neural Networks with Adaptive Objective for End-to-End Task-Oriented Dialogue 期刊论文
KNOWLEDGE-BASED SYSTEMS, 2021, 卷号: 227, 期号: 2021, 页码: 107186
作者:  Liu, Qingbin;  Bai, Guirong;  He, Shizhu;  Liu, Cao;  Liu, Kang;  Zhao, Jun
Adobe PDF(1021Kb)  |  收藏  |  浏览/下载：345/73  |  提交时间：2021/11/02
End-to-end task-oriented dialogue  Heterogeneous relational graph neural networks  Shared-private parameterization  Hierarchical attention mechanism  Adaptive objective  
Improving Domain-adaptive Person Re-identification by Dual-alignment Learning with Camera-aware Image Generation 期刊论文
IEEE Transactions on Circuits and Systems for Video Technology, 2021, 卷号: 31, 期号: 11, 页码: 4334 - 4346
作者:  Chenyang Zhang;  Yongqiang Tang;  Zhizhong Zhang;  Ding Li;  Xuebing Yang;  Wensheng Zhang
Adobe PDF(2538Kb)  |  收藏  |  浏览/下载：380/92  |  提交时间：2021/06/23
Person Re-identification  Convolutional Neural Networks  Generative Adversarial Networks  Mutual Information