中文版 | English

在结果中检索

CASIA OpenIR
（本次检索基于用户作品认领结果）

浏览/检索结果: 共10条，第1-10条 帮助

限定条件            
已选(0)清除 条数/页：   排序方式：
DATA: Differentiable ArchiTecture Approximation With Distribution Guided Sampling 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 卷号: 43, 期号: 9, 页码: 2905-2920
作者:  Zhang, Xinbang;  Chang, Jianlong;  Guo, Yiwen;  Meng, Gaofeng;  Xiang, Shiming;  Lin, Zhouchen;  Pan, Chunhong
Adobe PDF(1346Kb)  |  收藏  |  浏览/下载：305/50  |  提交时间：2021/11/02
Computer architecture  Search problems  Optimization  Task analysis  Bridges  Binary codes  Estimation  Neural architecture search(NAS)  ensemble gumbel-softmax  distribution guided sampling  
You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 卷号: 43, 期号: 9, 页码: 2891-2904
作者:  Zhang, Xinbang;  Huang, Zehao;  Wang, Naiyan;  Xiang, Shiming;  Pan, Chunhong
Adobe PDF(1271Kb)  |  收藏  |  浏览/下载：289/56  |  提交时间：2021/11/02
Computer architecture  Optimization  Learning (artificial intelligence)  Task analysis  Acceleration  Evolutionary computation  Convolution  Neural architecture search(NAS)  convolution neural network  sparse optimization  
Extracting Effective Image Attributes with Refined Universal Detection 期刊论文
SENSORS, 2021, 卷号: 21, 期号: 1, 页码: 16
作者:  Yu, Qiang;  Xiao, Xinyu;  Zhang, Chunxia;  Song, Lifei;  Pan, Chunhong
Adobe PDF(2391Kb)  |  收藏  |  浏览/下载：326/59  |  提交时间：2021/03/01
attribute extraction  Refined Universal Detection  word tree  image captioning  
Geometric Rectification of Document Images using Adversarial Gated Unwarping Network 期刊论文
Pattern Recognition, 2020, 卷号: 108, 期号: 108, 页码: 1-13
作者:  Xiyan Liu;  Gaofeng MENG;  Bin FAN;  Shiming Xiang;  Chunhong PAN
浏览  |  Adobe PDF(7916Kb)  |  收藏  |  浏览/下载：272/88  |  提交时间：2020/10/20
Distorted document image  Geometric rectification  Gated module  Deep learning  
Triplet Adversarial Domain Adaptation for Pixel-Level Classification of VHR Remote Sensing Images 期刊论文
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 卷号: 58, 期号: 5, 页码: 3558-3573
作者:  Yan, Liang;  Fan, Bin;  Liu, Hongmin;  Huo, Chunlei;  Xiang, Shiming;  Pan, Chunhong
Adobe PDF(6348Kb)  |  收藏  |  浏览/下载：352/68  |  提交时间：2020/06/22
Domain adaptation (DA)  pixel-level classification  self-training  triplet adversarial learning  very high resolution (VHR)  
AugFPN: Improving Multi-scale Feature Learning for Object Detection 会议论文
, online meeting, 2020-06-14
作者:  Guo, Chaoxu;  Fan, Bin;  Zhang, Qian;  Xiang, Shiming;  Pan, Chunhong
浏览  |  Adobe PDF(631Kb)  |  收藏  |  浏览/下载：480/132  |  提交时间：2020/06/11
AugFPN, Object Detection  
Progressive Sparse Local Attention for Video Object Detection 会议论文
, Seoul, Korea, 2019-10-27
作者:  Guo, Chaoxu;  Fan, Bin;  Gu, Jie;  Zhang, Qian;  Xiang, Shiming;  Prinet, Veronique;  Pan, Chunhong
浏览  |  Adobe PDF(1461Kb)  |  收藏  |  浏览/下载：317/90  |  提交时间：2020/06/09
Blind image quality assessment via learnable attention-based pooling 期刊论文
PATTERN RECOGNITION, 2019, 卷号: 91, 页码: 332-344
作者:  Gu, Jie;  Meng, Gaofeng;  Xiang, Shiming;  Pan, Chunhong
浏览  |  Adobe PDF(3081Kb)  |  收藏  |  浏览/下载：503/189  |  提交时间：2019/05/15
Image quality assessment  Perceptual image quality  Visual attention  Convolutional neural network  Learnable pooling  
Weakly Semantic Guided Action Recognition 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 卷号: 21, 期号: 10, 页码: 2504-2517
作者:  Yu, Tingzhao;  Wang, Lingfeng;  Da, Cheng;  Gu, Huxiang;  Xiang, Shiming;  Pan, Chunhong
浏览  |  Adobe PDF(18774Kb)  |  收藏  |  浏览/下载：437/112  |  提交时间：2019/05/15
Semantic guided module  action recognition  cross domain  3D convolution  attention model  
Semantic labeling in very high resolution images via a self-cascaded convolutional neural network 期刊论文
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 卷号: 145, 期号: 1, 页码: 78-95
作者:  Liu, Yongcheng;  Fan, Bin;  Wang, Lingfeng;  Bai, Jun;  Xiang, Shiming;  Pan, Chunhong
浏览  |  Adobe PDF(1679Kb)  |  收藏  |  浏览/下载：487/101  |  提交时间：2019/01/08
Semantic labeling  Convolutional neural networks (CNNs)  Multi-scale contexts  End-to-end