检索结果-南通市图书馆

Emotion recognition for human-computer interaction

在线全文

学校读者我要写书评

暂无评论

Virtual Reality & Intelligent Hardware 2021年第1期3卷 I0003-I0004页

作者： jianhua tao National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100081China CAS Center for Excellence in Brain Science and Intelligence Technology Beijing 100081China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100081China

Emotion recognition is to quantify,describe and recognize different emotional states through the behavioral and physiological responses generated from emotional *** recognition is an important field due to its wide applications in many tasks,such as dialogue generation,social media analysis and intelligent *** builds a harmonious human-computer environment by enabling the computer systems and devices to recognize and interpret human *** recognition models are built using multimodal information such as audio,video,text and so *** is important to consider emotion characteristics of humans in the design and presentation of intelligent *** have selected seven papers that provide the latest updates on the development of emotion recognition technology covering micro-expression spotting and recognition,speech emotion recognition,physiological signal emotion recognition,emotional dialog generation and so on.

关键词： computer recognition emotional

Learning long-term temporal contexts using skip RNN for continuous emotion recognition

在线全文

学校读者我要写书评

暂无评论

Virtual Reality & Intelligent Hardware 2021年第1期3卷 55-64页

作者： Jian HUANG Bin LIU jianhua tao National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100049China CAS Center for Excellence in Brain Science and Intelligence Technology Beijing 100049China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China

Background Continuous emotion recognition as a function of time assigns emotional values to every frame in a *** long-term temporal context information is essential for continuous emotion recognition *** For this purpose,we employ a window of feature frames in place of a single frame as inputs to strengthen the temporal modeling at the feature *** ideas of frame skipping and temporal pooling are utilized to alleviate the resulting *** the model level,we leverage the skip recurrent neural network to model the long-term temporal variability by skipping trivial information for continuous emotion *** The experimental results using the AVEC 2017 database demonstrate that our proposed methods are beneficial to a performance ***,the skip long short-term memory(LSTM)model can focus on the critical emotional state when training the models,thereby achieving a better performance than the LSTM model and other methods.

关键词： Continuous emotion recognition Skip RNN Temporal contexts Redundancy

MATHEMATICAL MODELING OF CIRCULATION AND ITS VERIFICATION

在线全文

学校读者我要写书评

暂无评论

Acta Mechanica Sinica 1986年第1期2卷 34-42页

作者： tao jianhua (Department of Mechanics,Tianjin University) 1. Department of Mechanics Tianjin University Tianjin China

In this study,the mechanism of circulation generation in channel with stopexpansion is *** circulation results from the balance between inertia force andbed-induced shear ***,the convective inertia term and the bottom resistance inthe momentum equation are essential to the simulation of *** means of acorresponding 2-D model,the velocity fields of unsteady circulating are *** of the results with the velocity fields measured data is made and the agreement issatisfactory.

关键词： mathematical simulation circulation channel with step expansion

Review of micro-expression spotting and recognition in video sequences

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Virtual Reality & Intelligent Hardware 2021年第1期3卷 1-17页

作者： Hang PAN Lun XIE Zhiliang WANG Bin LIU Minghao YANG jianhua tao School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China

Facial micro-expressions are short and imperceptible expressions that involuntarily reveal the true emotions that a person may be attempting to suppress,hide,disguise,or *** expressions can reflect a person's real emotions and have a wide range of application in public safety and clinical *** analysis of facial micro-expressions in video sequences through computer vision is still relatively *** this research,a comprehensive review on the topic of spotting and recognition used in micro expression analysis databases and methods,is conducted,and advanced technologies in this area are *** addition,we discuss challenges that remain unresolved alongside future work to be completed in the field of micro-expression analysis.

关键词： Facial expression Micro-expression spotting Micro-expression recognition Database Review

Numerical study of pollutant transport in the sea-bay with mild slope beach

在线全文

学校读者我要写书评

暂无评论

Acta Oceanologica Sinica 1998年第3期17卷 399-408页

作者： Wang Zeliang and tao jianhua(Received December 22, 1996 accepted January 5, 1997) Department of Mechanics Tianjin University Tianjin 300072 China

Using the slot method, the moving boundary problem caused by the change of the tide water elevation is treated. A two-dimensional advection - diffusion model with moving boundary is proposed, and the input pollutant is considered as moving source to meet the water level variation. The model given in this paper has been used to simulate the pollutant transport in the Bohai Gulf, the computational results are in good agreement with the measured data.

关键词： Slot method advection-diffusion mild slope beach moving source

Numerical simulation for the two-dimensional nonlinear shallow water waves

在线全文

学校读者我要写书评

暂无评论

Acta Oceanologica Sinica 1990年第3期9卷 449-457页

作者： tao jianhua and Zhang Yan Department of Mechanics, Tianjin University, Tianjin, China

This study deals with the general numerical model to simulate the two-dimensional tidal flow, flooding wave (long wave) and shallow water waves (short wave). The foundational model is based on nonlinear Boussinesq equations. Numerical method for modelling the short waves is investigated in detail. The forces, such as Coriolis forces, wind stress, atmosphere and bottom friction, are considered. A two-dimensional implicit difference scheme of Boussinesq equations is proposed. The low-reflection outflow open boundary is suggested. By means of this model,both velocity fields of circulation current in a channel with step expansion and the wave diffraction behind a semi-infinite breakwater are computed, and the results are satisfactory.

关键词： Numerical simulation for the two-dimensional nonlinear shallow water waves length than

Fusion of deep shallow features and models for speaker recognition

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Acoustics 2018年第4期37卷 477-490页

作者： ZHONG Weifeng FANG Xiang FAN Cunhang WEN Zhengqi tao jianhua School of Automation Harbin University of Science and Technology Harbin 150080 National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing 100190 CAS Center for Excellence in Brain Science and Intelligence Technology Beijiug 100190 School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing 100190

In order to further improve the performance of speaker recognition, features fusion and models fusion are proposed. The features fusion method is to fuse deep and shallow features. The fused feature describes speaker characteristics more comprehensively than a single feature because of the complementarity between different levels of features. The models fusion method is to fuse i-vectors extracted from different speaker recognition systems. The fused model can combine advantages of different speaker recognition systems. Experimental results show the effectiveness of the proposed methods. Compared with the state-of-the-art system on CASIA North and South dialect corpus,the proposed features fusion system and models fusion system achieved about 54.8% and 69.5% relative improvement on the equal error rate（EER）,respectively.

关键词： DBF EER DNN

Self-attention transfer networks for speech emotion recognition

在线全文

学校读者我要写书评

暂无评论

Virtual Reality & Intelligent Hardware 2021年第1期3卷 43-54页

作者： Ziping ZHAO Keru Wang Zhongtian BAO Zixing ZHANG Nicholas CUMMINS Shihuang SUN Haishuai WANG jianhua tao Björn WSCHULLER College of Computer and Information Engineering Tianjin Normal UniversityTianjin 300387China GLAM-Group on Language Audio&MusicImperial College LondonSW72AZUK Chair of Embedded Intelligence for Health Care and Wellbeing University of Augsburg86159Germany Department of Biostatistics and Health Informatics IoPPNKing's College LondonLondonSE58AFUK Department of Computer Science and Engineering Fairfield University 06824USA National Laboratory of Pattern Recognition CASIABeijing 100190China

Background A crucial element of human-machine interaction,the automatic detection of emotional states from human speech has long been regarded as a challenging task for machine learning *** vital challenge in speech emotion recognition(SER)is learning robust and discriminative representations from *** machine learning methods have been widely applied in SER research,the inadequate amount of available annotated data has become a bottleneck impeding the extended application of such techniques(e.g.,deep neural networks).To address this issue,we present a deep learning method that combines knowledge transfer and self-attention for SER ***,we apply the log-Mel spectrogram with deltas and delta-deltas as ***,given that emotions are time dependent,we apply temporal convolutional neural networks to model the variations in *** further introduce an attention transfer mechanism,which is based on a self-attention algorithm to learn long-term *** self-attention transfer network(SATN)in our proposed approach takes advantage of attention transfer to learn attention from speech recognition,followed by transferring this knowledge into *** evaluation built on Interactive Emotional Dyadic Motion Capture(IEMOCAP)dataset demonstrates the effectiveness of the proposed model.

关键词： Speech emotion recognition Attention transfer Self-attention Temporal convolutional neural networks(TCNs)

Distance-Dependent Modeling of Head-Related Transfer Functions Based on Spherical Fourier-Bessel Transform

在线全文

学校读者我要写书评

暂无评论

Distance-Dependent Modeling of Head-Related Transfer Functio...