第 1 条，共 207 条
标题: A novel strategy to prepare 2D YBO3: Ce3+-Yb3+ nanosheets with enhanced near-infrared (NIR) emission properties
作者: Miao, H (Miao, Hui); Zhang, GW (Zhang, Guowei); Hu, XY (Hu, Xiaoyun); Liu, EZ (Liu, Enzhou); Bai, JT (Bai, Jintao); Hou, X (Hou, Xun)
来源出版物: JOURNAL OF CONTROLLED RELEASE 卷: 259 页: E49-E49 DOI: 10.1016/j.jconrel.2017.03.121 出版年: AUG 10 2017
入藏号: WOS:000407591400080
会议名称: 4th Symposium on Innovative Polymers for Controlled Delivery (SIPCD)
会议日期: SEP 23-26, 2016
会议地点: Suzhou, PEOPLES R CHINA
ISSN: 0168-3659
eISSN: 1873-4995
________________________________________
第 2 条，共 207 条
标题: Collective Representation for Abnormal Event Detection
作者: Ye, RZ (Ye, Renzhen); Li, XL (Li, Xuelong)
来源出版物: JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 卷: 32 期: 3 页: 470-479 DOI: 10.1007/s11390-017-1737-8 出版年: MAY 2017
摘要: Abnormal event detection in crowded scenes is a hot topic in computer vision and information retrieval community. In this paper, we study the problems of detecting anomalous behaviors within the video, and propose a robust collective representation with multi-feature descriptors for abnormal event detection. The proposed method represents different features in an identical representation, in which different features of the same topic will show more common properties. Then, we build the intrinsic relation between different feature descriptors and capture concept drift in the video sequence, which can robustly discriminate between abnormal events and normal events. Experimental results on two benchmark datasets and the comparison with the state-of-the-art methods validate the effectiveness of our method.
入藏号: WOS:000401069100006
会议名称: 5th International Conference on Computational Visual Media (CVM)
会议日期: APR 12-14, 2017
会议地点: Nankai Univ, Tianjin, PEOPLES R CHINA
会议主办方: Nankai Univ
作者识别号:
作者        Web of Science ResearcherID        ORCID 号
Li, Xuelong         Z-3785-2019         
Li, Xuelong                  0000-0002-0019-4197

ISSN: 1000-9000
eISSN: 1860-4749
________________________________________
第 3 条，共 207 条
标题: Experimental studies on CO2, NOX, SOX adsorbing capacity of polyaniline-based materials
作者: Huang, J (Huang, Jia); Gao, L (Gao, Lin); Shan, LY (Shan, Liyuan); Meng, BL (Meng, Binglu); Xu, DL (Xu, Delong); Yu, YH (Yu, Youhai); Min, Y (Min, Yong)
来源出版物: ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY 会议摘要: 398 卷: 253 出版年: APR 2 2017
入藏号: WOS:000430568502528
会议名称: 253rd National Meeting of the American-Chemical-Society (ACS) on Advanced Materials, Technologies, Systems, and Processes
会议日期: APR 02-06, 2017
会议地点: San Francisco, CA
会议赞助商: Amer Chem Soc
ISSN: 0065-7727
________________________________________
第 4 条，共 207 条
标题: A PARALLEL LINEARIZED ADMM WITH APPLICATION TO MULTICHANNEL TGV-BASED IMAGE RESTORATION
作者: He, CA (He, Chuan); Hu, CH (Hu, Changhua); Li, XL (Li, Xuelong)
书籍团体作者: IEEE
来源出版物: 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) 丛书: IEEE International Conference on Image Processing ICIP 页:1187-1191 出版年: 2017
摘要: A parallel linearized alternating direction method of multipliers (PLADMM) is proposed to solve large-scale imaging inverse problems, which involve the sum of several linear operator-coupled nonsmooth terms. In the proposed method, the proximity operators of the nonsmooth terms arc called individually at each iteration and the auxiliary variables existing in the classical ADMM are excluded. Therefore, the proposed method possesses a highly parallel structure and most of its substeps can be executed simultaneously. The application to multichannel total generalized variation (TGV) based image restoration shows the effectiveness of the proposed method.
入藏号: WOS:000428410701063
会议名称: 24th IEEE International Conference on Image Processing (ICIP)
会议日期: SEP 17-20, 2017
会议地点: Beijing, PEOPLES R CHINA
会议赞助商: Inst Elect & Elect Engineers, Inst Elect & Elect Engineers Signal Proc Soc
作者识别号:
作者        Web of Science ResearcherID        ORCID 号
Li, Xuelong         Z-3785-2019         

ISSN: 1522-4880
ISBN: 978-1-5090-2175-8
________________________________________
第 5 条，共 207 条
标题: Embedded Measurement System of Two-dimensional Autocollimator based on FPGA
作者: Gao, X (Gao, Xiang); Hu, XD (Hu, Xiaodong); Yang, DL (Yang, Donglai); Zhang, J (Zhang, Jian)
编者: Xu B
来源出版物: 2017 IEEE 3RD INFORMATION TECHNOLOGY AND MECHATRONICS ENGINEERING CONFERENCE (ITOEC) 页: 304-308 出版年: 2017
摘要: For the miniaturization of two-dimensional autocollimator, a method of using embedded measurement system instead of special host computer is presented. This system integrates CMOS image sensor's driving circuit, frame processing, adaptive exposure control, centroid subdivision and localization of cross, misalignment angle calculation, display driver and other functions within a FPGA chip, and the sampling image and measurement results are displayed through the TFT-LCD mounted on the device body. The engineering prototype shows that the system has characters of high precision, high integration and high reliability.
入藏号: WOS:000422907300064
会议名称: 3rd IEEE Information Technology and Mechatronics Engineering Conference (ITOEC)
会议日期: OCT 03-05, 2017
会议地点: Chongqing, PEOPLES R CHINA
会议赞助商: IEEE, IEEE Beijing Sect, Global Union Acad Sci & Technol, Chongqing Global Union Acad Sci & Technol, Chongqing Geeks Educ Technol Co Ltd
ISBN: 978-1-5090-5363-6
________________________________________
第 6 条，共 207 条
标题: ANCHOR-BASED GROUP DETECTION IN CROWD SCENES
作者: Chen, ML (Chen, Mulin); Wang, Q (Wang, Qi); Li, XL (Li, Xuelong)
书籍团体作者: IEEE
来源出版物: 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) 丛书: International Conference on Acoustics Speech and Signal Processing ICASSP 页: 1378-1382 出版年: 2017
摘要: Group detection aims to classify pedestrians into categories according to their motion dynamics. It's fundamental for analyzing crowd behaviors and involves a wide range of applications. In this paper, we propose a Anchor-based Manifold Ranking (AMR) method to detect groups in crowd scenes. Our main contributions are threefold: (1) the topological relationship of individuals are effectively investigated with a manifold ranking method; (2) global consistency in crowds are accurately recognized by a coherent merging strategy; (3) the number of groups is decided automatically based on the similarity graph of individuals. Experimental results show that the proposed framework is competitive against the stateof- the-art methods.
入藏号: WOS:000414286201113
会议名称: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
会议日期: MAR 05-09, 2017
会议地点: New Orleans, LA
会议赞助商: IEEE, Inst Elect & Elect Engineers, Signal Proc Soc
作者识别号:
作者        Web of Science ResearcherID        ORCID 号
Li, Xuelong         Z-3785-2019         
Wang, Qi                  0000-0002-7028-4956
Li, Xuelong                  0000-0002-0019-4197

ISSN: 1520-6149
ISBN: 978-1-5090-4117-6
________________________________________
第 7 条，共 207 条
标题: Image2song: Song Retrieval via Bridging Image Content and LyricWords
作者: Li, XL (Li, Xuelong); Hu, D (Hu, Di); Lu, XQ (Lu, Xiaoqiang)
书籍团体作者: IEEE
来源出版物: 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) 丛书: IEEE International Conference on Computer Vision 页: 5650-5659 DOI: 10.1109/ICCV.2017.602 出版年: 2017
摘要: Image is usually taken for expressing some kinds of emotions or purposes, such as love, celebrating Christmas. There is another better way that combines the image and relevant song to amplify the expression, which has drawn much attention in the social network recently. Hence, the automatic selection of songs should be expected. In this paper, we propose to retrieve semantic relevant songs just by an image query, which is named as the image2song problem. Motivated by the requirements of establishing correlation in semantic/content, we build a semantic-based song retrieval framework, which learns the correlation between image content and lyric words. This model uses a convolutional neural network to generate rich tags from image regions, a recurrent neural network to model lyric, and then establishes correlation via a multi-layer perceptron. To reduce the content gap between image and lyric, we propose to make the lyric modeling focus on the main image content via a tag attention. We collect a dataset from the social-sharing multimodal data to study the proposed problem, which consists of (image, music clip, lyric) triplets. We demonstrate that our proposed model shows noticeable results in the image2song retrieval task and provides suitable songs. Besides, the song2image task is also performed.
入藏号: WOS:000425498405077
会议名称: 16th IEEE International Conference on Computer Vision (ICCV)
会议日期: OCT 22-29, 2017
会议地点: Venice, ITALY
会议赞助商: IEEE, IEEE Comp Soc
作者识别号:
作者        Web of Science ResearcherID        ORCID 号
Li, Xuelong         Z-3785-2019         
Li, Xuelong                  0000-0002-0019-4197

ISSN: 1550-5499
ISBN: 978-1-5386-1032-9
________________________________________
第 8 条，共 207 条
标题: HDPA: HIERARCHICAL DEEP PROBABILITY ANALYSIS FOR SCENE PARSING
作者: Yuan, Y (Yuan, Yuan); Jiang, ZY (Jiang, Zhiyu); Wang, Q (Wang, Qi)
书籍团体作者: IEEE
来源出版物: 2017 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME) 丛书: IEEE International Conference on Multimedia and Expo 页:313-318 出版年: 2017
摘要: Scene parsing is an important task in computer vision and many issues still need to be solved. One problem is about the non-unified framework for predicting things and stuff and the other one refers to the inadequate description of contextual information. In this paper, we address these issues by proposing a Hierarchical Deep Probability Analysis(HDPA) method which particularly exploits the power of probabilistic graphical model and deep convolutional neural network on pixel-level scene parsing. To be specific, an input image is initially segmented and represented through a CNN framework under Gaussian pyramid. Then the graphical models are built under each scale and the labels are ultimately predicted by structural analysis. Three contributions are claimed: unified framework for scene labeling, hierarchical probabilistic graphical modeling and adequate contextual information consideration. Experiments on three benchmarks show that the proposed method outperforms the state-of-the-arts in scene parsing.
入藏号: WOS:000426984300052
会议名称: IEEE International Conference on Multimedia and Expo (ICME)
会议日期: JUL 10-14, 2017
会议地点: Hong Kong, HONG KONG
会议赞助商: IEEE
作者识别号:
作者        Web of Science ResearcherID        ORCID 号
jiang, zhiyu         L-2934-2018         
Wang, Qi                  0000-0002-7028-4956

ISSN: 1945-7871
ISBN: 978-1-5090-6067-2
________________________________________
第 9 条，共 207 条
标题: HYPERSPECTRAL IMAGE BAND SELECTION VIA GLOBAL OPTIMAL CLUSTERING
作者: Zhang, FH (Zhang, Fahong); Wang, Q (Wang, Qi); Li, XL (Li, Xuelong)
书籍团体作者: IEEE
来源出版物: 2017 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) 丛书: IEEE International Symposium on Geoscience and Remote Sensing IGARSS 页: 1-4 出版年: 2017
摘要: Band selection, by choosing a set of representative bands in hyperspectral images (HSI), is concerned to be an effective method to eliminate the "Hughes phenomenon". In this paper, we present a global optimal clustering-based band selection (GOC) algorithm based on the hypothesis that all the bands in a cluster are continuous at their wavelengths. After the clustering result is obtained, we propose a greedy-based method to select representative bands in each cluster, trying to minimize the linear reconstruction error. Experiment on a real HSI dataset shows that the proposed method outperforms the state-of-the-art competitors.
入藏号: WOS:000426954600001
会议名称: IEEE International Geoscience & Remote Sensing Symposium
会议日期: JUL 23-28, 2017
会议地点: Fort Worth, TX
会议赞助商: Institute of Elect & Electron Engineers Geoscience & Remote Sensing Soc, IEEE, IEEE GRSS
作者识别号:
作者        Web of Science ResearcherID        ORCID 号
Li, Xuelong         Z-3785-2019         
Wang, Qi                  0000-0002-7028-4956
Li, Xuelong                  0000-0002-0019-4197

ISSN: 2153-6996
ISBN: 978-1-5090-4951-6
________________________________________
第 10 条，共 207 条
标题: A SPARSE DICTIONARY LEARNING METHOD FOR HYPERSPECTRAL ANOMALY DETECTION WITH CAPPED NORM
作者: Ma, DD (Ma, Dandan); Yuan, Y (Yuan, Yuan); Wang, Q (Wang, Qi)
书籍团体作者: IEEE
来源出版物: 2017 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) 丛书: IEEE International Symposium on Geoscience and Remote Sensing IGARSS 页: 648-651 出版年: 2017
摘要: Hyperspectral anomaly detection is playing an important role in remote sensing field. Most conventional detectors based on the Reed-Xiaoli (RX) method assume the background signature obeys a Gaussian distribution. However, it is definitely hard to be satisfied in practice. Moreover, background statistics is susceptible to contamination of anomalies in the processing windows, which may lead to many false alarms and sensitiveness to the size of windows. To solve these problems, a novel sparse dictionary learning hyperspectral anomaly detection method with capped norm constraint is proposed. Contributions are claimed in threefold: 1) requiring no assumptions on the background distribution makes the method more adaptive to different scenes; 2) benefiting from the capped norm our method has a stronger distinctiveness to anomalies; and 3) it also has better adaptability to detect different sizes of anomalies without using the sliding dual window. The extensive experimental results demonstrate the desirable performance of our method.
入藏号: WOS:000426954600160
会议名称: IEEE International Geoscience & Remote Sensing Symposium
会议日期: JUL 23-28, 2017
会议地点: Fort Worth, TX
会议赞助商: Institute of Elect & Electron Engineers Geoscience & Remote Sensing Soc, IEEE, IEEE GRSS
作者识别号:
作者        Web of Science ResearcherID        ORCID 号
Wang, Qi                  0000-0002-7028-4956

ISSN: 2153-6996
ISBN: 978-1-5090-4951-6
________________________________________
第 11 条，共 207 条
标题: Projected Clustering via Robust Orthogonal Least Square Regression with Optimal Scaling
作者: Zhang, R (Zhang, Rui); Nie, FP (Nie, Feiping); Li, XL (Li, Xuelong)
书籍团体作者: IEEE
来源出版物: 2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) 丛书: IEEE International Joint Conference on Neural Networks (IJCNN) 页: 2784-2791 出版年: 2017
摘要: The orthogonal least square regression (OLSR) serves as a pretty significant problem for the dimensionality reduction. Due to lack of the scale change in OLSR, the scaling term is at first introduced to OLSR to build up a novel orthogonal least square regression with optimal scaling (OLSR-OS) problem. However, OLSR-OS is still sensitive to the outliers, such that associated results could be fallacious. To strengthen the robustness of OLSR-OS, we propose an original robust OLSR-OS (ROLSR-OS) problem in l(2,1)-norm. To tackle a more ill-defined situation, ROLSR-OS in l(2,1)-norm can be further extended to ROLSR-OS in capped l(2)-norm. Besides, the associated ROLSR-OS methods could be derived by solving the re-weighted counterparts of ROLSR-OS problems in both norms. Moreover, the equivalence between the re-weighted counterparts and the original ROLSR-OS problems is also provided along with the convergence analysis of the proposed ROLSR-OS methods. Accordingly, both the optimal scaling and weight can be achieved automatically via the proposed ROLSR-OS approaches. Specifically, the proposed ROLSR-OS methods are self-adaptive, such that the smaller weight would be automatically assigned to the term with larger outliers to enhance the robustness. Consequently, projected clustering and modified projected clustering under the proposed ROLSR-OS problems are further investigated both theoretically and experimentally.
入藏号: WOS:000426968703005
会议名称: International Joint Conference on Neural Networks (IJCNN)
会议日期: MAY 14-19, 2017
会议地点: Anchorage, AK
会议赞助商: Int Neurol Network Soc, IEEE Computat Intelligence Soc, Intel, BMI, Budapest Semester Cognit Sci
作者识别号:
作者        Web of Science ResearcherID        ORCID 号
Nie, Feiping         B-3039-2012         
Li, Xuelong         Z-3785-2019         
Nie, Feiping                  0000-0002-0871-6519
Zhang, Rui         U-4639-2017         0000-0001-9418-0863
Li, Xuelong                  0000-0002-0019-4197

ISSN: 2161-4393
ISBN: 978-1-5090-6182-2
________________________________________
第 12 条，共 207 条
标题: Design of high precision temperature control system for TO packaged LD
作者: Liang, EJ (Liang, Enji); Luo, BK (Luo, Baoke); Zhuang, B (Zhuang, Bin); He, ZQ (He, Zhengquan)
编者: Asundi AK; Zhao H; Osten W
来源出版物: AOPC 2017: 3D MEASUREMENT TECHNOLOGY FOR INTELLIGENT MANUFACTURING 丛书: Proceedings of SPIE 卷: 10458 文献号: 104581Y DOI:10.1117/12.2283461 出版年: 2017
摘要: Temperature is an important factor affecting the performance of TO package LD. In order to ensure the safe and stable operation of LD, a temperature control circuit for LD based on PID technology is designed. The MAX1978 and an external PID circuit are used to form a control circuit that drives the thermoelectric cooler (TEC) to achieve control of temperature and the external load can be changed. The system circuit has low power consumption, high integration and high precision, and the circuit can achieve precise control of the LD temperature. Experiment results show that the circuit can achieve effective and stable control of the laser temperature.
入藏号: WOS:000425346300069
会议名称: Annual Conference of the Chinese-Society-for-Optical-Engineering (CSOE) on Applied Optics and Photonics China (AOPC) - 3D Measurement Technology for Intelligent Manufacturing
会议日期: JUN 04-06, 2017
会议地点: Beijing, PEOPLES R CHINA
会议赞助商: SPIE, Chinese Soc Opt Engn, Chinese Soc Astronaut, Photoelectron Technol Comm, CHIA, Dept Cooperat & Coordinat Ind Acad & Res, Sci & Technol Low Light Level Night Vis Lab, Sci & Technol Electro Opt Informat Secur Control Lab, Opt Soc Korea, Opt & Photon Soc Singapore, European Opt Soc, Opt Soc Japan
ISSN: 0277-786X
eISSN: 1996-756X
ISBN: 978-1-5106-1398-0; 978-1-5106-1397-3
________________________________________
第 13 条，共 207 条
标题: A modified topological derivative based background suppression for infrared dim small target detection
作者: Cheng, WX (Cheng, Wenxiong); Qin, HL (Qin, Hanlin); Wang, WT (Wang, Wanting); Wang, CM (Wang, Chunmei); Leng, HB (Leng, Hanbing); Zhou, HX (Zhou, Huixin)
编者: Jiang Y; Gong H; Chen W; Li J
来源出版物: AOPC 2017: OPTICAL SENSING AND IMAGING TECHNOLOGY AND APPLICATIONS 丛书: Proceedings of SPIE 卷: 10462 文献号: UNSP 1046256 DOI: 10.1117/12.2285726 子辑: 1 出版年: 2017
摘要: In the processing of infrared small target image which has low signal-to-noise ratio and complex background, the target detection and recognition are very hard. So, how to suppress infrared complex background in low signal-to-clutter addition becomes the key problem in the detection of infrared small target image. The topological derivative can quantify the sensitivity of a problem when the domain under consideration is perturbed by changing its topology. Considering the idea of topology optimization, a modified topological derivative based background suppression method for infrared dim small target detection was proposed. An appropriate functional and variational problem is related to the cost function. Thus, the corresponding topological derivative can be used as an indicator function leads to the processed image through a minimization process. Firstly, introduce perturbations to each pixel of the infrared image. Secondly, calculate the corresponding topological derivative. These pixels also have the least cost function. Finally, using the modified optimal diffusion coefficient to diffuse the pixels where the topological derivative is negative to make its background smooth and achieve the purpose of removing the background clutter while enhancing the small target. Compared with other several experiment results of existing background suppressing methods in indexes, the method the paper proposed has innovative ideas and gets well effects of background suppressing and are practical methods. All of above have the important research value for the related work in future.
入藏号: WOS:000425515000184
会议名称: Annual Conference of the Chinese-Society-for-Optical-Engineering (CSOE) on Applied Optics and Photonics China (AOPC) - Optical Sensing and Imaging Technology and Applications
会议日期: JUN 04-06, 2017
会议地点: Beijing, PEOPLES R CHINA
会议赞助商: SPIE, Chinese Soc Opt Engn, Chinese Soc Astronaut, Photoelectron Technol Comm, CHIA, Acad & Res, Dept Cooperat & Coordinat Ind, Sci & Technol Low Light Level Night Vis Lab, Sci & Technol Electro Opt Informat Secur Control Lab, Opt Soc Korea, Opt & Photon Soc Singapore, European Opt Soc, Opt Soc Japan
ISSN: 0277-786X
eISSN: 1996-756X
ISBN: 978-1-5106-1406-2; 978-1-5106-1405-5
________________________________________
第 14 条，共 207 条
标题: Design of An Off-Axis Reflective Zoom Optical System
作者: Guo, ZL (Guo, Zhanli); Yang, HT (Yang, Hongtao); Mei, C (Mei, Chao); Yan, AQ (Yan, Aqi)
编者: Jiang Y; Gong H; Chen W; Li J
来源出版物: AOPC 2017: OPTICAL SENSING AND IMAGING TECHNOLOGY AND APPLICATIONS 丛书: Proceedings of SPIE 卷: 10462 文献号: UNSP 104623M DOI: 10.1117/12.2285188 子辑: 1 出版年: 2017
摘要: With the limit of optical materials, it is difficult to design zoom optical systems which have long focal length by refractive systems with a simple configuration. All-reflective zoom optical systems could be lightweighted, compact and free of chromatic aberrations, and reflective optical systems can be unobscured by off-axis mirrors and have very good application foreground. In this paper, an all-reflective zoom optical system was designed, the all-reflective zoom optical system worked in the band of 400 similar to 1000nm, the diameter of the pupil was 100mm, the F number was 6 similar to 15, focal length varied from 600 similar to 1500mm, field of view (FOV) was 2 degrees x0.8 degrees similar to 0.8 degrees x0.48 degrees. The pixel size of detector was 10x10 mu m. The result showed that MTF was higher than 0.3 at 50lp/mm and the quality of the optical system approached the diffraction limit, which met the design demand.
入藏号: WOS:000425515000128
会议名称: Annual Conference of the Chinese-Society-for-Optical-Engineering (CSOE) on Applied Optics and Photonics China (AOPC) - Optical Sensing and Imaging Technology and Applications
会议日期: JUN 04-06, 2017
会议地点: Beijing, PEOPLES R CHINA
会议赞助商: SPIE, Chinese Soc Opt Engn, Chinese Soc Astronaut, Photoelectron Technol Comm, CHIA, Acad & Res, Dept Cooperat & Coordinat Ind, Sci & Technol Low Light Level Night Vis Lab, Sci & Technol Electro Opt Informat Secur Control Lab, Opt Soc Korea, Opt & Photon Soc Singapore, European Opt Soc, Opt Soc Japan
ISSN: 0277-786X
eISSN: 1996-756X
ISBN: 978-1-5106-1406-2; 978-1-5106-1405-5
________________________________________
第 15 条，共 207 条
标题: Fast Triangle Star Identification Algorithm Based on Uncertain Sign
作者: Wei, X (Wei Xin); Wen, DS (Wen Desheng); Song, ZX (Song Zongxi)
编者: Jiang Y; Gong H; Chen W; Li J
来源出版物: AOPC 2017: OPTICAL SENSING AND IMAGING TECHNOLOGY AND APPLICATIONS 丛书: Proceedings of SPIE 卷: 10462 文献号: UNSP 104624U DOI: 10.1117/12.2285591 子辑: 1 出版年: 2017
摘要: As a fine star-field identification algorithm, triangle algorithm is used far and wide currently, but there are some defects in triangle algorithm, such as low search efficiency and high mismatches probability. In allusion to these defects, a new triangle algorithm based on uncertain sign is presented. This algorithm extracted F and R features of star triangle, and then built a guidance characteristic catalogue which was searched by means of k-vector, promoting the search efficiency, moreover, in order to avoid the occurrence of mismatch, this algorithm would verify guide star triangle's auxiliary information if its uncertain sign is 1. Simulation shows that: compared to the traditional triangle algorithm, this algorithm has a couple of advantages, including the higher rate of correct star recognition, lower mismatches probability, and better real-time adaptability and robustness. And this algorithm can reach 97% on identification rate when the position error is 2 pixels, and average identification time is 38.74ms; the traditional algorithm is 75% when the position error is 2 pixels, and average identification time is 187.26ms.
入藏号: WOS:000425515000172
会议名称: Annual Conference of the Chinese-Society-for-Optical-Engineering (CSOE) on Applied Optics and Photonics China (AOPC) - Optical Sensing and Imaging Technology and Applications
会议日期: JUN 04-06, 2017
会议地点: Beijing, PEOPLES R CHINA
会议赞助商: SPIE, Chinese Soc Opt Engn, Chinese Soc Astronaut, Photoelectron Technol Comm, CHIA, Acad & Res, Dept Cooperat & Coordinat Ind, Sci & Technol Low Light Level Night Vis Lab, Sci & Technol Electro Opt Informat Secur Control Lab, Opt Soc Korea, Opt & Photon Soc Singapore, European Opt Soc, Opt Soc Japan
ISSN: 0277-786X
eISSN: 1996-756X
ISBN: 978-1-5106-1406-2; 978-1-5106-1405-5
________________________________________
第 16 条，共 207 条
标题: Brownian Dynamics of the optically trapped spinning microparticles in low pressures
作者: Lang, MJ (Lang, Mengjiao); Xiong, W (Xiong, Wei); Xiao, GZ (Xiao, Guangzong); Han, X (Han, Xiang); Tang, JX (Tang, Jianxun)
编者: Qiu M; Gu M; Yuan X; Zhou Z
来源出版物: AOPC 2017: OPTOELECTRONICS AND MICRO/NANO-OPTICS 丛书: Proceedings of SPIE 卷: 10460 文献号: UNSP 1046010 DOI:10.1117/12.2284450 出版年: 2017
摘要: Optical trap has become a powerful tool of biology and physics, since it has some useful functions such as optical rotator, optical spanner and optical binding. We present the translational motions in the transverse plane of a 4.4 mu m-diameter vaterite particle which is optically trapped in low pressures utilizing the Monte-Carlo method. We find that the air pressure around the microparticle plays an important part in the determination of dynamics of the trapped particle. According to the energy equipartition theorem, the position fluctuations of the optically trapped particle satisfy Maxwell-Bolzmann distributions. We present the features of particles' displacements and velocities changing with air pressures in detail, and find that the modulation of the trap stiffness makes a higher position variance. The mechanical quality factor Q larger than 10 induces a high peak of power spectral density. Our research presents a powerful tool towards further discovery of dynamical characteristics of optically trapped Brownian particles in low air pressures.
入藏号: WOS:000425344700035
会议名称: Annual Conference of the Chinese-Society-for-Optical-Engineering (CSOE) on Applied Optics and Photonics China (AOPC) - Optoelectronics and Micro/Nano-Optics
会议日期: JUN 04-06, 2017
会议地点: Beijing, PEOPLES R CHINA
会议赞助商: SPIE, Chinese Soc Opt Engn, Chinese Soc Astronaut, Photoelectron Technol Comm, CHIA, Dept Cooperat & Coordinat Ind Acad & Res, Sci & Technol Low Light Level Night Vis Lab, Sci & Technol Electro Opt Informat Secur Control Lab, Opt Soc Korea, Opt & Photon Soc Singapore, European Opt Soc, Opt Soc Japan
ISSN: 0277-786X
eISSN: 1996-756X
ISBN: 978-1-5106-1402-4; 978-1-5106-1401-7
________________________________________
第 17 条，共 207 条
标题: FFGS: Feature Fusion with Gating Structure for Image Caption Generation
作者: Yuan, AH (Yuan, Aihong); Li, XL (Li, Xuelong); Lu, XQ (Lu, Xiaoqiang)
编者: Yang J; Hu Q; Cheng MM; Wang L; Liu Q; Bai X; Meng D
来源出版物: COMPUTER VISION, PT I 丛书: Communications in Computer and Information Science 卷: 771 页: 638-649 DOI: 10.1007/978-981-10-7299-4_53 出版年: 2017
摘要: Automatically generating a natural language to describe the content of the given image is a challenging task in the interdisciplinary between computer vision and natural language processing. The task is challenging because computers not only need to recognize objects, their attributions and relationships between them in an image, but also these elements should be represented into a natural language sentence. This paper proposed a feature fusion with gating structure for image caption generation. First, the pre-trained VGG-19 is used as the image feature extractor. We use the FC-7 and CONV5-4 layer's outputs as the global and local image feature, respectively. Second, the image features and the corresponding sentence are imported into LSTM to learn their relationship. The global image feature is gated at each time-step before imported into LSTM while the local image feature used the attention model. Experimental results show our method outperform the state-of-the-art methods.
入藏号: WOS:000449835200053
会议名称: 2nd CCF Chinese Conference on Computer Vision (CCCV)
会议日期: OCT 11-14, 2017
会议地点: China Comp Federat, Tianjin, PEOPLES R CHINA
会议赞助商: China Comp Federat, Profess Comm Comp Vis, Civil Aviat Univ, Tianjin Univ, Nankai Univ, CCF Tech Comm Comp Vis, Megvii Face++, Sensetime, Isecure Technol, Ali A I Labs, Hiscene, Riseye, Tupu, Nvidia, Pingan Technol, Pinnacle, Vrview, Xilinx, Athena Eyes, Watrix Technol, Extreme Vis, Shanghai Acad Artificial Intelligence, Segway Robot, Percipio XYZ, AN
会议主办方: China Comp Federat
作者识别号:
作者        Web of Science ResearcherID        ORCID 号
Li, Xuelong         Z-3785-2019         
Li, Xuelong                  0000-0002-0019-4197

ISSN: 1865-0929
eISSN: 1865-0937
ISBN: 978-981-10-7299-4; 978-981-10-7298-7
________________________________________
第 18 条，共 207 条
标题: Deep Temporal Architecture for Audiovisual Speech Recognition
作者: Tian, CL (Tian, Chunlin); Yuan, Y (Yuan, Yuan); Lu, XQ (Lu, Xiaoqiang)
编者: Yang J; Hu Q; Cheng MM; Wang L; Liu Q; Bai X; Meng D
来源出版物: COMPUTER VISION, PT I 丛书: Communications in Computer and Information Science 卷: 771 页: 650-661 DOI: 10.1007/978-981-10-7299-4_54 出版年: 2017
摘要: The Audiovisual Speech Recognition (AVSR) is one of the applications of multimodal machine learning related to speech recognition, lipreading systems and video classification. In recent and related work, increasing efforts are made in Deep Neural Network (DNN) for AVSR, moreover some DNN models including Multimodal Deep Autoencoder, Multimodal Deep Belief Network and Multimodal Deep Boltzmann Machine perform well in experiments owing to the better generalization and nonlinear transformation. However, these DNN models have several disadvantages: (1) They mainly deal with modal fusion while ignoring temporal fusion. (2) Traditional methods fail to consider the connection among frames in the modal fusion. (3) These models aren't end-to-end structure. We propose a deep temporal architecture, which has not only classical modal fusion, but temporal modal fusion and temporal fusion. Furthermore, the overfitting and learning with small size samples in the AVSR are also studied, so that we propose a set of useful training strategies. The experiments show the superiority of our model and necessity of the training strategies in three datasets: AVLetters, AVLetters2, AVDigits. In the end, we conclude the work.
入藏号: WOS:000449835200054
会议名称: 2nd CCF Chinese Conference on Computer Vision (CCCV)
会议日期: OCT 11-14, 2017
会议地点: China Comp Federat, Tianjin, PEOPLES R CHINA
会议赞助商: China Comp Federat, Comp Vis Comm, Civil Aviat Univ, Tianjin Univ, Nankai Univ, CCF Tech Comm Comp Vis, Megvii Face++, Sensetime, Isecure Technol, Ali A I Labs, Hiscene, Riseye, Tupu, Nvidia, Pingan Technol, Pinnacle, Vrview, Xilinx, Athena Eyes, Watrix Technol, Extreme Vis, Shanghai Acad Artificial Intelligence, Segway Robot, Percipio XYZ, AN
会议主办方: China Comp Federat
ISSN: 1865-0929
eISSN: 1865-0937
ISBN: 978-981-10-7299-4; 978-981-10-7298-7
________________________________________
第 19 条，共 207 条
标题: Bidirectional Adaptive Feature Fusion for Remote Sensing Scene Classification
作者: Ji, WJ (Ji, Weijun); Li, XL (Li, Xuelong); Lu, XQ (Lu, Xiaoqiang)
编者: Yang J; Hu Q; Cheng MM; Wang L; Liu Q; Bai X; Meng D
来源出版物: COMPUTER VISION, PT II 丛书: Communications in Computer and Information Science 卷: 772 页: 486-497 DOI: 10.1007/978-981-10-7302-1_40 出版年: 2017
摘要: Convolutional neural networks (CNN) have been excellent for scene classification in nature scene. However, directly using the pre- trained deep models on the aerial image is not proper, because of the spatial scale variability and rotation variability of the HSR remote sensing images. In this paper, a bidirectional adaptive feature fusion strategy is investigated to deal with the remote sensing scene classification. The deep learning feature and the SIFT feature are fused together to get a discriminative image presentation. The fused feature can not only describe the scenes effectively by employing deep learning feature but also overcome the scale and rotation variability with the usage of the SIFT feature. By fusing both SIFT feature and global CNN feature, our method achieves state-of-the-art scene classification performance on the UCM and the AID datasets.
入藏号: WOS:000449831600040
会议名称: 2nd CCF Chinese Conference on Computer Vision (CCCV)
会议日期: OCT 11-14, 2017
会议地点: China Comp Federat, Tianjin, PEOPLES R CHINA
会议赞助商: China Comp Federat, Profess Comm Comp Vis, Civil Aviat Univ, Tianjin Univ, Nankai Univ, CCF Tech Comm Comp Vis, Megvii Face++, Sensetime, Isecure Technol, Ali A I Labs, Hiscene, Riseye, Tupu, Nvidia, Pingan Technol, Pinnacle, Vrview, Xilinx, Athena Eyes, Watrix Technol, Extreme Vis, Shanghai Acad Artificial Intelligence, Segway Robot, Percipio XYZ, AN
会议主办方: China Comp Federat
作者识别号:
作者        Web of Science ResearcherID        ORCID 号
Li, Xuelong         Z-3785-2019         
Li, Xuelong                  0000-0002-0019-4197

ISSN: 1865-0929
eISSN: 1865-0937
ISBN: 978-981-10-7302-1; 978-981-10-7301-4
________________________________________
第 20 条，共 207 条
标题: Efficient Supervised Hashing via Exploring Local and Inner Data Structure
作者: He, SY (He, Shiyuan); Ye, G (Ye, Guo); Hu, MQ (Hu, Mengqiu); Yang, Y (Yang, Yang); Shen, FM (Shen, Fumin); Shen, HT (Shen, Heng Tao); Li, XL (Li, Xuelong)
编者: Huang Z; Xiao X; Cao X
来源出版物: DATABASES THEORY AND APPLICATIONS, ADC 2017 丛书: Lecture Notes in Computer Science 卷: 10538 页: 98-109 DOI: 10.1007/978-3-319-68155-9_8 出版年: 2017
摘要: Recent years have witnessed the promising capacity of hashing techniques in tackling nearest neighbor search because of the high efficiency in storage and retrieval. Data-independent approaches (e.g., Locality Sensitive Hashing) normally construct hash functions using random projections, which neglect intrinsic data properties. To compensate this drawback, learning-based approaches propose to explore local data structure and/or supervised information for boosting hashing performance. However, due to the construction of Laplacian matrix, existing methods usually suffer from the unaffordable training cost. In this paper, we propose a novel supervised hashing scheme, which has the merits of (1) exploring the inherent neighborhoods of samples; (2) significantly saving training cost confronted with massive training data by employing approximate anchor graph; as well as (3) preserving semantic similarity by leveraging pair-wise supervised knowledge. Besides, we integrate discrete constraint to significantly eliminate accumulated errors in learning reliable hash codes and hash functions. We devise an alternative algorithm to efficiently solve the optimization problem. Extensive experiments on two image datasets demonstrate that our proposed method is superior to the state-of-the-arts.
入藏号: WOS:000439775500008
会议名称: 28th Australasian Database Conference (ADC)
会议日期: SEP 25-28, 2017
会议地点: Univ Queensland, St Lucia Campus, Brisbane, AUSTRALIA
会议主办方: Univ Queensland, St Lucia Campus
作者识别号:
作者        Web of Science ResearcherID        ORCID 号
Li, Xuelong         Z-3785-2019         
Li, Xuelong                  0000-0002-0019-4197

ISSN: 0302-9743
eISSN: 1611-3349
ISBN: 978-3-319-68155-9; 978-3-319-68154-2