中国科学院机构知识库网格系统: 检索

SMART: Syntax-Calibrated Multi-Aspect Relation Transformer for Change Captioning 期刊论文 OAI收割
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 卷号: 46, 期号: 7, 页码: 4926-4943
作者: Tu, Yunbin; Li, Liang; Su, Li; Zha, Zheng-Jun; Huang, Qingming

|

收藏 | 浏览/下载：14/0 | 提交时间：2024/12/06

Semantics Visualization Transformers Decoding Switches Syntactics Image representation Change captioning multi-aspect relation learning part-of-speech visual switch transformer

Relation-Aware Facial Expression Recognition 期刊论文 OAI收割
IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2022, 卷号: 14, 期号: 3, 页码: 1143-1154
作者: Xia, Yifan; Yu, Hui; Wang, Xiao; Jian, Muwei; Wang, Fei-Yue

|

收藏 | 浏览/下载：56/0 | 提交时间：2022/11/14

Face recognition Feature extraction Mouth Image recognition Deep learning Databases Convolutional neural networks Deep convolutional neural networks facial expression in the wild facial expression recognition relation convolutional neural network (ReCNN) relation-aware

Super-resolution semantic segmentation with relation calibrating network 期刊论文 OAI收割
PATTERN RECOGNITION, 2022, 卷号: 124, 页码: 10
作者: Jiang, Jie; Liu, Jing; Fu, Jun; Wang, Weining; Lu, Hanqing

|

收藏 | 浏览/下载：45/0 | 提交时间：2022/02/16

Image semantic segmentation Super-resolution semantic segmentation Relation calibrating

Mixed Dish Recognition With Contextual Relation and Domain Alignment 期刊论文 OAI收割
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 卷号: 24, 页码: 2034-2045
作者: Deng, Lixi; Chen, Jingjing; Ngo, Chong-Wah; Sun, Qianru; Tang, Sheng

|

收藏 | 浏览/下载：31/0 | 提交时间：2022/12/07

Visualization Semantics Feature extraction Image recognition Training Testing Context modeling Mixed dish recognition Contextual relation Domain alignment

Image Representations With Spatial Object-to-Object Relations for RGB-D Scene Recognition 期刊论文 OAI收割
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 页码: 525-537
作者: Song, Xinhang; Jiang, Shuqiang; Wang, Bohan; Chen, Chengpeng; Chen, Gongwei

|

收藏 | 浏览/下载：48/0 | 提交时间：2020/12/10

Feature extraction Object detection Image recognition Layout Data models Recurrent neural networks Scene recognition object-to-object relation sequential representations RGB-D object detection

Context-Driven Image Caption With Global Semantic Relations of the Named Entities 期刊论文 OAI收割
IEEE ACCESS, 2020, 卷号: 8, 页码: 143584-143594
作者: Jing, Yun; Zhiwei Xu; Guanglai Gao

|

收藏 | 浏览/下载：21/0 | 提交时间：2020/12/10

Semantics Visualization Task analysis Computational modeling Knowledge based systems Correlation Organizations Image caption named entity semantic relation

The movement estimation of target and background by fourier phase spectrum difference (EI CONFERENCE) 会议论文 OAI收割
2010 6th International Conference on Wireless Communications, Networking and Mobile Computing, WiCOM 2010, September 23, 2010 - September 25, 2010, Chengdu, China
作者: Zhang X.; Zhang X.; Zhang X.; Wang J.; Zhang S.

收藏 | 浏览/下载：26/0 | 提交时间：2013/03/25

An algorithm for estimating displacement of the moving target and background by shift theory of Fourier transform is presented. According to the relation between the change and the Fourier transform of image sequence the method employs the displacement value of the moving target and background by the difference of Fourier phase spectrum. The algorithm estimates the movements from the whole field of the image with excellent global property. This paper provides the calculus and experiments of the algorithm which show the accuracy of 1 pixel. 2010 IEEE.

Inspection focus technology of space tridimensional mapping camera based on astigmatic method (EI CONFERENCE) 会议论文 OAI收割
5th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optoelectronic Materials and Devices for Detector, Imager, Display, and Energy Conversion Technology, April 26, 2010 - April 29, 2010, Dalian, China
作者:

收藏 | 浏览/下载：29/0 | 提交时间：2013/03/25

The CCD plane of the space tridimensional mapping camera will be deviated from the focal plane(including the CCD plane deviated due to camera focal length changed) under the condition of space environment and vibration impact when satellite is launching image resolution ratio will be descended because defocusing. For tridimensional mapping camera principal point position and focal length variation of the camera affect positioning accuracy of ground target conventional solution is under the condition of vacuum and focusing range calibrate the position of CCD plane with code of photoelectric encoder when the camera defocusing in orbit the magnitude and direction of defocusing amount are obtained by photoelectric encoder then the focusing mechanism driven by step motor to compensate defocusing amount of the CCD plane. For tridimensional mapping camera under the condition of space environment and vibration impact when satellite is launching if the camera focal length changes above focusing method has been meaningless. Thus the measuring and focusing method was put forward based on astigmation a quadrant detector was adopted to measure the astigmation caused by the deviation of the CCD plane refer to calibrated relation between the CCD plane poison and the asrigmation the deviation vector of the CCD plane can be obtained. This method includes all factors caused deviation of the CCD plane experimental results show that the focusing resolution of mapping camera focusing mechanism based on astigmatic method can reach 0.25 m. 2010 Copyright SPIE - The International Society for Optical Engineering.

Gray level correction algorithm of LED display panel based on least squares approximation (EI CONFERENCE) 会议论文 OAI收割
2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010, August 24, 2010 - August 26, 2010, Changchun, China
作者: Sun Z.-Y.

收藏 | 浏览/下载：25/0 | 提交时间：2013/03/25

Aiming at the problem that the linear characteristic of LED display panel is not compatible with the non-linear characteristic of image data this leads to appear the large deviation during grayscale rendition the gray level correction algorithm based on least squares approximation is provided. First the necessity of gray level correction is analyzed. Then the gray level correction algorithm model is constructed according to the principle of latest squares approximation. Next realization steps are described in accordance with this constructed algorithm model. Finally this algorithm is implemented in a LED display panel whose resolution is 128128. Experimental results show that this algorithm is able to reduce the deviation obviously during grayscale rendition and the problem of gray level deformation can be resolved perfectly because the linear relation between image data after correcting and gray level is good which satisfies the linear characteristic of LED display panel. 2010 IEEE.

Non-uniformity correction in multi-CCD imaging system (EI CONFERENCE) 会议论文 OAI收割
2010 2nd International Conference on Mechanical and Electronics Engineering, ICMEE 2010, August 1, 2010 - August 3, 2010, Kyoto, Japan
Tao M.; Ren J.

收藏 | 浏览/下载：35/0 | 提交时间：2013/03/25

The non-uniformity phenomenon exists in each channel of multi-CCD imaging systems. The factors which lead to the problem are complex. The conventional calibrating algorithms can not consider all of these factors and have poor effects. According to the characters of multi-CCD imaging systems a non-uniformity correction method based on the scene was proposed by adopting the traditional two-point correction theories. The correction coefficient of each channel image can be calculated via the linear relation between the two neighboring pixel lines in the two-channel images. Compared with the conventional two-point calibration and multi-point calibration methods contrastive calibrating results were obtained. This method does not need any standard lighted image as reference source which provides a real time way for calibrating the multi-CCD imaging systems in practical applications. 2010 IEEE.