模式识别与人工智能
Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence
22 Judgement and Disposal of Academic Misconduct Article
22 Copyright Transfer Agreement
22 Proof of Confidentiality
22 Requirements for Electronic Version
More....
22 Chinese Association of Automation
22 National ResearchCenter for Intelligent Computing System
22 Institute of Intelligent Machines,Chinese Academy of Sciences
More....
 
 
2020 Vol.33 Issue.5, Published 2020-05-25
Papers and Reports    Researches and Applications    Surveys and Reviews   
   
Papers and Reports
383 Two-Stream Gait Network for Cross-View Gait Recognition
WANG Kun, LEI Yiming, ZHANG Junping
With data augmentation and network feature map augmentation, a two-stream gait network is proposed to enhance the robustness of the model against the influence of belongings and clothing variations. Firstly,both global features and local discriminative information in gait videos are extracted by two-stream network. Then, the representation of gait feature is obtained by integrating outputs of two streams. The proposed restricted random mask is utilized to promote the network to learn more discriminative features and reduce the influence of belongings and clothing variations simultaneously. Furthermore, a triplet loss sampling algorithm is improved to accelerate the training convergence speed of the network model. Experiments on datasets, namely CASIA-B and OU-MVLP, indicate that the proposed method achieves a high gait recognition accuracy under different bagging and clothing walking conditions.
2020 Vol. 33 (5): 383-392 [Abstract] ( 502 ) [HTML 1KB] [ PDF 728KB] ( 348 )
393 Region Proposal Network Based on Effective Receptive Field
ZHANG Shengyu, DONG Shifeng, JIAO Lin, WANG Qijin, WANG Hongqiang
Object detection methods based on convolutional neural network(CNN) optimize region proposal to achieve a higher detection accuracy. Therefore, an effective receptive field(eRF) based region proposal network is proposed. A sample matching method based on eRF is introduced into regional proposal network. Thus, the intersection over union(IoU) based sample matching rule is improved. The representation ability of feature information in the region proposal generation stage is enhanced. The number of region proposal and anchor boxes is greatly reduced. The parameter settings of anchor boxes are also simplified. The detection accuracy on Pascal VOC datasets is improved in combination with Fast R-CNN detector. The effectiveness of proposed method is verified.
2020 Vol. 33 (5): 393-400 [Abstract] ( 436 ) [HTML 1KB] [ PDF 2829KB] ( 283 )
401 X-architecture Steiner Minimum Tree Algorithm Considering Routing Resource Relaxation
TANG Hao, LIU Genggeng, GUO Wenzhong, CHEN Guolong
To further study X-architecture and make full use of routing resources within the obstacle, an X-architecture Steiner minimum tree algorithm considering routing resource relaxation is proposed in this paper. Firstly, crossover and mutation operators are introduced in the update operation of particles to solve the discretization problem. Secondly, look-up tables are presented for the whole algorithm process to provide a fast information query. Thirdly, a corner point selection strategy is proposed to introduce some obstacle corner points and satisfy the constraints. Finally, a refinement strategy is implemented to further improve the quality of the final routing tree. Experimental results show that the proposed algorithm makes full use of the routing resources within the obstacle, shortens the total wirelength effectively and achieves a better total wirelength.
2020 Vol. 33 (5): 401-412 [Abstract] ( 382 ) [HTML 1KB] [ PDF 782KB] ( 314 )
413 Linguistic Interval-Valued Intuitionistic Fuzzy Frank Operators
LIU Limei, GONG Yinli, YANG Yi, WU Shaozhi
Aiming at the aggregation problem of linguistic interval-valued intuitionistic fuzzy information, Frank aggregation operator is proposed. A group decision-making method is constructed to solve the problem of supplier selection. Firstly, linguistic interval-valued intuitionistic fuzzy Frank operational laws are defined by introducing the extended Frank t-norms and s-norms, and linguistic interval-valued intuitionistic fuzzy Frank weighted averaging (LIVIFFWA) operator and geometric (LIVIFFWG) operator are proposed. Secondly, some properties of these operators are proved, such as idempotency, closeness and monotonicity, and the degeneracy of these operators with respect to parameters is analyzed. Then, based on the proposed LIVIFFWA operators and LIVIFFWG operators, a linguistic interval-valued intuitionistic fuzzy multi-attribute group decision-making method is constructed to solve the supplier decision-making problem. Finally, the feasibility and flexibility of the decision-making method are demonstrated through the case analysis of the selection of suppliers with shared bicycle recycling. The influence of parameter variation on decision-making results is discussed, and the ability of parameters to represent and feed back the attitudes of decision makers is verified.
2020 Vol. 33 (5): 413-425 [Abstract] ( 331 ) [HTML 1KB] [ PDF 795KB] ( 272 )
Surveys and Reviews
426 A Survey on Multimodal Sentiment Analysis
ZHANG Yazhou, RONG Lu, SONG Dawei, ZHANG Peng
Multimodal sentiment analysis is one of the core research topics in the field of natural language processing. Firstly, the research background of multimodal sentiment analysis is introduced. Two sub-topics of multimodal sentiment analysis, narrative multimodal sentiment analysis and interactive multimodal sentiment analysis, are proposed. Then, the development and the research progress at home and abroad are summarized based on the mentioned two sub-topics. Finally, the existing scientific problems of interactive modeling in this field are summarized, and the future development trend is discussed.
2020 Vol. 33 (5): 426-438 [Abstract] ( 1372 ) [HTML 1KB] [ PDF 912KB] ( 636 )
Researches and Applications
439 Multi-label Classification Algorithm Based on Label-Specific Features and Instance Correlations
ZHANG Yong, LIU Haoke, ZHANG Jie
The method for learning label-specific features reduces dimensions by selecting specific features for each label with the consideration of pairwise label correlations and it solves the problem of dimensions of multi-label classification effectively. However, instance correlations are not taken into account in the method. To solve this problem, a multi-label classification algorithm based on label-specific features and instance correlations is proposed. Both label correlations and the correlation of instance features are considered. The similarity map is constructed to learn the similarity of instance feature space. Experimental results on 8 datasets show that the proposed algorithm effectively extracts label-specific features with better classification performance.
2020 Vol. 33 (5): 439-448 [Abstract] ( 612 ) [HTML 1KB] [ PDF 633KB] ( 333 )
449 Lie Group Machine Learning Based on Sparse Dictionary
XIONG Xiaodong, LI Fanzhang, WANG Bangjun, LIANG Helan
Lie group machine learning(LML) theory is widely applied to data representation and processing in image set classification, and satisfactory results are obtained. Therefore, a method of Lie group dictionary learning based on sparse dictionary is proposed. Firstly, the covariance matrix is employed to model the image set, and the Lie group structure composed of covariance matrix is analyzed. Logarithmic map is applied to map the data into the linear space to obtain the distance matrix of the data. Then, landmark multi-dimensional scaling is employed to realize dimension reduction of data and reduce the computational cost. Finally, Fisher discriminant dictionary learning is applied for classification. The experiments on YTC dataset indicate the good performance of the proposed algorithm in robustness and accuracy.
2020 Vol. 33 (5): 449-457 [Abstract] ( 437 ) [HTML 1KB] [ PDF 756KB] ( 260 )
458 Multi-constraint Deep Distance Learning for Visual Loop Closure Detection
CHEN Liang, JIN Sheng, YANG Hui, GAO Yu, SUN Rongchuan, SUN Lining
In visual loop closure detection under strong scene changes, the feature descriptors extracted by the existing deep learning methods cannot be distinguished well. Aiming at this problem, the multi-constraint distance relationship is analyzed, and a multi-constraint deep distance learning method for visual loop closure detection is proposed. Firstly, the original images are mapped to feature descriptors by any convolutional neural network in the low-dimensional feature space. Then, a multi-constraint loss function is proposed to constrain the distance relationships among feature descriptors, and a multi-constraint training sample set is automatically constructed online to extract more discriminative low-dimensional feature descriptors. Experiments on New College and TUM datasets show that the proposed method improves the performance of loop closure detection under strong scene changes.
2020 Vol. 33 (5): 458-467 [Abstract] ( 315 ) [HTML 1KB] [ PDF 1947KB] ( 256 )
468 Self-circulation Intelligent Text Recognition Based on Multi-stage Data Generation
MA Xinqiang, LIU Lina, LI Xuewei, GU Ye, HUANG Yi, LIU Yong

There are few effective big data annotation methods for both English and Chinese recognition in complex and diverse scenarios. Therefore, multi-stage data generation self-circulation training algorithm(MSDG-OCR) for complex and diverse text recognition scenarios is proposed. Text data is generated randomly according to the defined generated data parameters, and the data annotation process is omitted. Grounded on convolutional recurrent neural network(CRNN) model, multi-stage self-circulation training is carried out, and the recognition accuracy of the samples is continuously improved by controlling the data generation strategy during the loop process. Experiments show that the proposed.
2020 Vol. 33 (5): 468-476 [Abstract] ( 315 ) [HTML 1KB] [ PDF 1029KB] ( 253 )
模式识别与人工智能
 

Supervised by
China Association for Science and Technology
Sponsored by
Chinese Association of Automation
NationalResearchCenter for Intelligent Computing System
Institute of Intelligent Machines, Chinese Academy of Sciences
Published by
Science Press
 
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech 　Email:support@magtech.com.cn