期刊:
Multimedia Tools and Applications,2023年82(9):14091-14105 ISSN:1380-7501
通讯作者:
Shixin Peng
作者机构:
[Peng, Shixin; Tan, Lei; Chen, Chang; Chen, Jingying] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.
通讯机构:
[Shixin Peng] N;National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China
关键词:
Person re-identification;Cross modality;Channel decoupling
摘要:
Cross-modality person re-identification (CM-ReID) is a very challenging problem due to the discrepancy in data distributions between visible and near-infrared modalities. To obtain a robust sharing feature representation, existing methods mainly focus on image generation or feature constrain to decrease the modality discrepancy, which ignores the large gap between mixed-spectral visible images and single-spectral near-infrared images. In this paper, we address the problem by decoupling the mixed-spectral visible images into three single-spectral subspaces R, G, and B. By aligning the spectrum, we noted that even using a single spectral image instead of the VIS images could result in a better performance. Based on the above observation, we further introduce a clear and effective three-path channel decoupling network (CDNet) for combining the three spectral images. Extensive experiments implemented on the benchmark CM-ReID datasets, SYSU-MM01 and RegDB indicated that our method achieved state-of-the-art performance and outperformed existing approaches by a large margin. On the RegDB dataset, the absolute gain of our method in terms of rank-1 and mAP is well over 15.4% and 8.5%, respectively, compared with the state-of-the-art methods.
作者机构:
[Peng Shixin; Chen Kai; Tian Tian; Chen Jingying] National Engineering Research Center for E-Learning, National Engineering Laboratory for Educational Big Data, Central China Normal University, Hubei, 430079, China
通讯机构:
[Chen Jingying] N;National Engineering Research Center for E-Learning, National Engineering Laboratory for Educational Big Data, Central China Normal University, Hubei, 430079, China
摘要:
Although speech emotion recognition is challenging, it has broad application prospects in human-computer interaction. Building a system that can accurately and stably recognize emotions from human languages can provide a better user experience. However, the current unimodal emotion feature representations are not distinctive enough to accomplish the recognition, and they do not effectively simulate the inter-modality dynamics in speech emotion recognition tasks. This paper proposes a multimodal method that utilizes both audio and semantic content for speech emotion recognition. The proposed method consists of three parts: two high-level feature extractors for text and audio modalities, and an autoencoder-based feature fusion. For audio modality, we propose a structure called Temporal Global Feature Extractor (TGFE) to extract the high-level features of the time-frequency domain relationship from the original speech signal. Considering that text lacks frequency information, we use only a Bidirectional Long Short-Term Memory network (BLSTM) and attention mechanism to simulate an intra-modal dynamic. Once these steps have been accomplished, the high-level text and audio features are sent to the autoencoder in parallel to learn their shared representation for final emotion classification. We conducted extensive experiments on three public benchmark datasets to evaluate our method. The results on Interactive Emotional Motion Capture (IEMOCAP) and Multimodal EmotionLines Dataset (MELD) outperform the existing method. Additionally, the results of CMU Multi-modal Opinion-level Sentiment Intensity (CMU-MOSI) are competitive. Furthermore, experimental results show that compared to unimodal information and autoencoder-based feature level fusion, the joint multimodal information (audio and text) improves the overall performance and can achieve greater accuracy than simple feature concatenation.
作者机构:
[Peng, Shixin; Chen, Jingying] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.;[Chen, Xiaohui] State Grid Hunan Elect Power Co Ltd, Informat & Commun Branch, Changsha 410004, Peoples R China.;[Lu, Wei] Air Force Early Warning Acad, Wuhan 430019, Peoples R China.;[Deng, Chao] Huazhong Univ Sci & Technol, Sch Elect Informat & Commun, Wuhan 430074, Peoples R China.
通讯机构:
[Chen, JY ] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.
关键词:
Interference alignment;Limited feedback;MIMO;Precoding matrix;Smart grid;Spatial multiplexing gain
期刊:
FRONTIERS IN HUMAN NEUROSCIENCE,2021年15:656578 ISSN:1662-5161
通讯作者:
Xu, R.;Liu, L.
作者机构:
[Liu, Leyuan; Peng, Shixin; Liu, Lili; Yi, Xin; Xu, Ruyi; Hu, Xin] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Lab Educ Big Data, Wuhan, Peoples R China.;[Liu, Leyuan; Peng, Shixin; Liu, Lili; Yi, Xin; Xu, Ruyi; Hu, Xin] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.
通讯机构:
[Xu, R.; Liu, L.] N;National Engineering Laboratory for Education Big Data, China
关键词:
Early Screening 1;Autism Spectrum Disorder (ASD) 2;Electroencephalogram (EEG) Signal 3;Feature Selection 4;Event-Related Potential (ERP) 5
摘要:
Early screening is vital and helpful for implementing intensive intervention and rehabilitation therapy for children with autism spectrum disorder (ASD). Research has shown that electroencephalogram (EEG) signals can reflect abnormal brain function of children with ASD, and screening with EEG signals has the characteristics of good real-time performance and high sensitivity. However, the existing EEG screening algorithms mostly focus on the data analysis in the resting state, and the extracted EEG features have some disadvantages such as weak representation capacity and information redundancy. In this study, we utilized the event-related potential (ERP) technique to acquire the EEG data of the subjects under positive and negative emotional stimulation and proposed an EEG Feature Selection Algorithm based on L1-norm regularization to perform screening of autism. The proposed EEG Feature Selection Algorithm includes the following steps: (1) extracting 20 EEG features from the raw data, (2) classification with support vector machine, (3) selecting appropriate EEG feature with L1-norm regularization according to the classification performance. The experimental results show that the accuracy for screening of children with ASD can reach 93.8% and 87.5% under positive and negative emotional stimulation and the proposed algorithm can effectively eliminate redundant features and improve screening accuracy.
作者机构:
[Wen X.; Lu W.; Deng B.; Fang Q.] Air Force Early Warning Academy, Wuhan, 430072, China;[Peng S.] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, 430079, China
通讯机构:
[Lu, W.] A;Air Force Early Warning AcademyChina
期刊:
Wireless Personal Communications,2019年105(1):257-266 ISSN:0929-6212
通讯作者:
Lu, Wei
作者机构:
[Lu, Wei; Fang, Qiqing; Wang, Yongliang] Air Force Early Warning Acad, Wuhan, Hubei, Peoples R China.;[Peng, Shixin] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
通讯机构:
[Lu, Wei] A;Air Force Early Warning Acad, Wuhan, Hubei, Peoples R China.
摘要:
In this letter a weighted iteratively reweighted least-square (IRLS) algorithm is proposed for FDD massive MIMO channel estimation. The priori support information is merged into the weighted IRLS to improve the recovery performance. The priori support information is obtained from the uplink channel by reciprocity in angle domain, and a support estimation algorithm is proposed from the analysis of basis mismatch and angle deviation between uplink and downlink which is more practical in the real scenario. A brief convergence analysis of weighted IRLS is given out. Simulations show that the proposed weighted IRLS outperforms the standard IRLS, subspace pursuit (SP) and weighted SP.
作者机构:
[Lu, Wei; Wen, Xiaoqiao; Wang, Yongliang] Air Force Early Warning Acad, Wuhan 430072, Hubei, Peoples R China.;[Hua, Xiaoqiang] Natl Univ Def Technol, Changsha 410073, Hunan, Peoples R China.;[Peng, Shixin] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;[Zhong, Liang] China Univ Geosci, Dept Commun Syst, Wuhan 430074, Hubei, Peoples R China.
通讯机构:
[Lu, Wei] A;Air Force Early Warning Acad, Wuhan 430072, Hubei, Peoples R China.
作者机构:
[Lu, Wei; Wen, Xiaoqiao; Wang, Yongliang] Air Force Early Warning Acad, Wuhan 430019, Hubei, Peoples R China.;[Peng, Shixin] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;[Zhong, Liang] China Univ Geosci, Dept Commun Syst, Wuhan 430074, Hubei, Peoples R China.
通讯机构:
[Lu, Wei] A;Air Force Early Warning Acad, Wuhan 430019, Hubei, Peoples R China.
期刊:
EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING,2018年2018(1):1-12 ISSN:1687-1472
通讯作者:
Lu, Wei
作者机构:
[Lu, Wei; Fang, Qiqing; Wang, Yongliang] Air Force Early Warning Acad, Wuhan, Hubei, Peoples R China.;[Peng, Shixin] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
通讯机构:
[Lu, Wei] A;Air Force Early Warning Acad, Wuhan, Hubei, Peoples R China.