中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页
机构
成果
学者
登录
注册
登陆
×
验证码:
换一张
忘记密码?
记住我
×
校外用户登录
CAS IR Grid
机构
长春光学精密机械与物... [2]
自动化研究所 [2]
计算技术研究所 [1]
中国科学院大学 [1]
采集方式
OAI收割 [5]
iSwitch采集 [1]
内容类型
期刊论文 [4]
会议论文 [2]
发表日期
2024 [1]
2023 [1]
2022 [1]
2012 [1]
2006 [2]
学科主题
筛选
浏览/检索结果:
共6条,第1-6条
帮助
条数/页:
5
10
15
20
25
30
35
40
45
50
55
60
65
70
75
80
85
90
95
100
排序方式:
请选择
题名升序
题名降序
发表日期升序
发表日期降序
提交时间升序
提交时间降序
作者升序
作者降序
Transformer-based stroke relation encoding for online handwriting and sketches
期刊论文
OAI收割
PATTERN RECOGNITION, 2024, 卷号: 148, 页码: 13
作者:
Liu, Jing-Yu
;
Zhang, Yan-Ming
;
Yin, Fei
;
Liu, Cheng-Lin
  |  
收藏
  |  
浏览/下载:46/0
  |  
提交时间:2024/02/22
Online stroke classification
Handwritten document analysis
Diagram recognition
Sketch semantic segmentation
Position encoding in transformer
Viewpoint-Adaptive Representation Disentanglement Network for Change Captioning
期刊论文
OAI收割
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 2620-2635
作者:
Tu, Yunbin
;
Li, Liang
;
Su, Li
;
Du, Junping
  |  
收藏
  |  
浏览/下载:28/0
  |  
提交时间:2023/12/04
Task analysis
Image coding
Adaptation models
Encoding
Computer science
Transformers
Semantics
Change captioning
representation disentanglement
viewpoint-adaptive
position-embedded representation learning
Position Encoding Based Convolutional Neural Networks for Machine Remaining Useful Life Prediction
期刊论文
OAI收割
IEEE/CAA Journal of Automatica Sinica, 2022, 卷号: 9, 期号: 8, 页码: 1427-1439
作者:
Ruibing Jin
;
Min Wu
;
Keyu Wu
;
Kaizhou Gao
;
Zhenghua Chen
  |  
收藏
  |  
浏览/下载:56/0
  |  
提交时间:2022/08/01
Convolutional neural network (CNN)
deep learning
position encoding
remaining useful life prediction
Optimum design of laser encoding and decoding on laser beam-riding guidance (EI CONFERENCE)
会议论文
OAI收割
2nd International Conference on Frontiers of Manufacturing and Design Science, ICFMD 2011, December 11, 2011 - December 13, 2011, Taichung, Taiwan
作者:
Yang L.
;
Yang L.
收藏
  |  
浏览/下载:37/0
  |  
提交时间:2013/03/25
Operating principle of laser beam-riding guidance was set forth. Based on the principle of spatial frequency-encoding
experimental results demonstrated that the receiver can receive correctly the encoded signal and can decode the signal
an optimum laser encoding mode was designed
measurement for the missdistance is feasible and all the performance parameters satisfy the demand. (2012) Trans Tech Publications
which can transfer continuous laser into pulse laser that represents different position information. Then the mathematic model of deviation from target is built
Switzerland.
a modified encoding pattern was presented
which is composed of two light paths crossed 90. Azimuth information of target is given in orthogonal coordinate system and deviation from target is linearity. As well as
characteristic distribution of spatial laser field is analyzed. Corresponding decoding mode was presented
by testing in 2 kilometers outdoor
Position multiplexing for multiple-image encryption
期刊论文
iSwitch采集
Journal of optics a-pure and applied optics, 2006, 卷号: 8, 期号: 5, 页码: 391-397
作者:
Situ, G
;
Zhang, JJ
收藏
  |  
浏览/下载:32/0
  |  
提交时间:2019/05/10
Multiple-image encryption
Position multiplexing
Double random-phase encoding
Fresnel transform
A new spaceborne compression approach for remote sensing imagery (EI CONFERENCE)
会议论文
OAI收割
ICO20: Remote Sensing and Infrared Devices and Systems, August 21, 2005 - August 26, 2005, Changchun, China
作者:
Xu S.
收藏
  |  
浏览/下载:31/0
  |  
提交时间:2013/03/25
After analyzing advantages and disadvantages of these typical encoding methods: SPIHT and VQ
a "DWT+MRLE" approach for spaceborne data compression was proposed in this paper. This approach includes two steps: Discrete Wavelet Transform (DWT) and Modified Run Length Encoding (MRLE). The former used CDF9/7 biorthogonal wavelet filters to powerfully get rid of correlation between pixels in imagery. The later put enlightening information into the lowest bit of some key-position transform coefficients. Consequently
CDF9/7 and MRLE together make hardware platform remain high real-time capability
and help reconstructed images keep good fidelity with PSNR being about 40dB
compared with the original ones. Comparison between experimentations on SPOT4's low-spatial-resolution (10m) imagery and Ikonos2's high-spatial-resolution (1m) imagery
shows this "DWT+MRLE" method having better performance for remote-sensed imagery
especially those of higher resolution. Although inferior to 8:1
Compression Ration (CR) here near 5:1 is greater than France SPOT5's 3:1 and American Ikonos2's 11:2.6 on-board data compression. More important
this method having less computational amount is good for spaceborne capability of real time. The consumed time of different image size is also presented in this paper
based on TI TMSC6416 DSP chip with 600MHz CPU cycle clock.