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39条，第1-10条 帮助

限定条件            
已选(0)清除 条数/页：   排序方式：
AHDet: A dynamic coarse-to-fine gaze strategy for active object detection 期刊论文
NEUROCOMPUTING, 2022, 卷号: 491, 页码: 522-532
作者:  Xu, Nuo;  Huo, Chunlei;  Zhang, Xin;  Pan, Chunhong
Adobe PDF(2664Kb)  |  收藏  |  浏览/下载：268/56  |  提交时间：2022/09/19
Object detection  Active object detection  Deep reinforcement learning  Convolutional neural networks  
PSNet: Perspective-sensitive convolutional network for object detection 期刊论文
NEUROCOMPUTING, 2022, 卷号: 468, 页码: 384-395
作者:  Zhang, Xin;  Liu, Yicheng;  Huo, Chunlei;  Xu, Nuo;  Wang, Lingfeng;  Pan, Chunhong
Adobe PDF(8656Kb)  |  收藏  |  浏览/下载：274/36  |  提交时间：2021/12/28
Object detection  Perspective-sensitive  Structural neural network  
TR-MISR: Multiimage super-resolution based on feature fusion with transformers 期刊论文
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 卷号: 15, 页码: 1373-1388
作者:  An T(安泰);  Zhang X(张鑫);  Huo CL(霍春雷);  Xue B(薛斌);  Wang LF(汪凌峰);  Pan CH(潘春洪)
Adobe PDF(6058Kb)  |  收藏  |  浏览/下载：78/6  |  提交时间：2024/01/17
Deep learning  end-to-end networks  feature extraction and fusion  multiimage super-resolution (MISR)  remote sensing  transformers  
3D-SceneCaptioner: Visual Scene Captioning Network for Three-Dimensional Point Clouds 会议论文
, 广东省珠海市, 2021-12
作者:  Yu, Qiang;  Pan, Xianbing;  Xiang, Shiming;  Pan, Chunhong
Adobe PDF(3412Kb)  |  收藏  |  浏览/下载：143/25  |  提交时间：2022/01/14
Scene Captioning  Three-Dimensional Vision  Point Cloud  
Decoupled Representation Learning for Character Glyph Synthesis 期刊论文
IEEE Transactions on Multimedia, 2021, 卷号: 2021, 期号: 2021, 页码: 1-13
作者:  Xiyan Liu;  Gaofeng Meng;  Jianlong Chang;  Ruiguang Hu;  Shiming Xiang;  Chunhong Pan
Adobe PDF(4588Kb)  |  收藏  |  浏览/下载：167/45  |  提交时间：2022/01/24
Character glyph synthesis  Decoupled representation  generative adversarial networks  
Handwritten Text Generation via Disentangled Representations 期刊论文
IEEE SIGNAL PROCESSING LETTERS, 2021, 卷号: 28, 期号: 2021, 页码: 1838-1842
作者:  Liu, Xiyan;  Meng, Gaofeng;  Xiang, Shiming;  Pan, Chunhong
Adobe PDF(1272Kb)  |  收藏  |  浏览/下载：235/57  |  提交时间：2021/11/04
Disentangled representation  Handwritten text generation  
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：320/61  |  提交时间：2020/06/22
Domain adaptation (DA)  pixel-level classification  self-training  triplet adversarial learning  very high resolution (VHR)  
Baselines Extraction from Curved Document Images via Slope Fields Recovery 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2020, 卷号: 42, 期号: 4, 页码: 793-808
作者:  Meng, Gaofeng;  Pan, Chunhong;  Xiang, Shiming;  Wu, Ying
Adobe PDF(15645Kb)  |  收藏  |  浏览/下载：207/44  |  提交时间：2020/06/02
Estimation  Image segmentation  Layout  Distortion  Strips  Image quality  Degradation  Document image processing  curved baselines extraction  slope fields recovery  geometric distortion rectification  
Deep Hierarchical Encoder-Decoder Network for Image Captioning 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 卷号: 21, 期号: 11, 页码: 2942-2956
作者:  Xiao, Xinyu;  Wang, Lingfeng;  Ding, Kun;  Xiang, Shiming;  Pan, Chunhong
收藏  |  浏览/下载：284/0  |  提交时间：2020/03/30
Visualization  Semantics  Hidden Markov models  Decoding  Logic gates  Training  Computer architecture  Deep hierarchical structure  encoder-decoder  LSTM  image captioning  retrieval  vision-sentence  
Nonlinear Asymmetric Multi-Valued Hashing 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2019, 卷号: 41, 期号: 11, 页码: 2660-2676
作者:  Da, Cheng;  Meng, Gaofeng;  Xiang, Shiming;  Ding, Kun;  Xu, Shibiao;  Yang, Qing;  Pan, Chunhong
浏览  |  Adobe PDF(2583Kb)  |  收藏  |  浏览/下载：469/115  |  提交时间：2018/10/07
Asymmetric hashing  multi-valued embeddings  binary sparse representation  nonlinear transformation