Search

Your search keyword '"Wu, Xuecheng"' showing total 581 results
Start Over Author "Wu, Xuecheng"
581 results on '"Wu, Xuecheng"'

2. Affective Video Content Analysis: Decade Review and New Perspectives

Author

Xue, Junxiao, Wang, Jie, Wu, Xuecheng, and Zhang, Qian

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Video content is rich in semantics and has the ability to evoke various emotions in viewers. In recent years, with the rapid development of affective computing and the explosive growth of visual data, affective video content analysis (AVCA) as an essential branch of affective computing has become a widely researched topic. In this study, we comprehensively review the development of AVCA over the past decade, particularly focusing on the most advanced methods adopted to address the three major challenges of video feature extraction, expression subjectivity, and multimodal feature fusion. We first introduce the widely used emotion representation models in AVCA and describe commonly used datasets. We summarize and compare representative methods in the following aspects: (1) unimodal AVCA models, including facial expression recognition and posture emotion recognition; (2) multimodal AVCA models, including feature fusion, decision fusion, and attention-based multimodal models; (3) model performance evaluation standards. Finally, we discuss future challenges and promising research directions, such as emotion recognition and public opinion analysis, human-computer interaction, and emotional intelligence.

Published
2023

3. Spatial distribution and influencing factors of villages and towns with characteristic industries in China(中国乡村特色产业村镇空间分布及影响因素)

Author

李练练(LI Lianlian), 陈国磊(CHEN Guolei), 张纪莎(ZHANG Jisha), 马太佳(MA Taijia), and 吴学成(WU Xuecheng)

Subjects
rural characteristic industries(乡村特色产业), spatial distribution(空间分布), influencing factors(影响因素), Electronic computers. Computer science, QA75.5-76.95, Physics, QC1-999
Abstract

Promoting industrial prosperity is the primary task of implementing the rural revitalization strategy. Taking villages and towns with rural characteristic industries in China from 2020 to 2022 as the research object, the spatiotemporal characteristics and influencing factors of rural characteristic industry villages and towns were analyzed by using the methods such as nearest proximity index, kernel density estimation, spatial autocorrelation analysis, geographic detector and other spatial analytic methods. The results show that: The villages and towns with rural characteristic industries exhibit an overall excessive agglomeration in space, with a spatial distribution trend of "dense in the southeast of China, sparse in the northwest" and "cold in the west and hot in the east"; The population and transportation facility have the strongest influence on the spatial distribution, while the influence of the land resources is the weakest; The interaction detection results of influencing factors show a dual factor enhancement or non-linear enhancement, with the strongest interaction effect between population size and economic development level.(推进产业兴旺是实施乡村振兴战略的首要任务，以2020—2022年中国乡村特色产业产值超十亿元镇和超亿元村为研究对象，运用最近邻指数法、核密度估计法、空间自相关分析法、熵值法、地理探测器等方法，分析乡村特色产业村镇的时空格局演化特征及影响因素。结果表明：乡村特色产业村镇在空间上呈过度集聚，并呈现“东南密西北疏”“西冷东热”的分布态势；乡村特色产业村镇空间分布格局受人口数量、交通运输能力的影响显著，受土地资源的影响较弱；影响因素的交互探测结果呈双因子增强或非线性增强，其中人口数量与经济发展水平的交互影响最强。)

Published
2024
Full Text
View/download PDF

4. Research on Mask Wearing Detection of Natural Population Based on Improved YOLOv4

Author

Wu, Xuecheng, Tian, Mengmeng, and Zhai, Lanhang

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Recently, the domestic COVID-19 epidemic situation has been serious, but in some public places, some people do not wear masks or wear masks incorrectly, which requires the relevant staff to instantly remind and supervise them to wear masks correctly. However, in the face of such important and complicated work, it is necessary to carry out automated mask wearing detection in public places. This paper proposes a new mask wearing detection method based on the improved YOLOv4. Specifically, firstly, we add the Coordinate Attention Module to the backbone to coordinate feature fusion and representation. Secondly, we conduct a series of network structural improvements to enhance the model performance and robustness. Thirdly, we deploy the K-means clustering algorithm to make the nine anchor boxes more suitable for our NPMD dataset. The experimental results show that the improved YOLOv4 performs better, exceeding the baseline by 4.06% AP with a comparable speed of 64.37 FPS., Comment: 4 pages, 1 figures

Published
2022

5. ICANet: A Method of Short Video Emotion Recognition Driven by Multimodal Data

Author

Wu, Xuecheng, Tian, Mengmeng, and Zhai, Lanhang

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

With the fast development of artificial intelligence and short videos, emotion recognition in short videos has become one of the most important research topics in human-computer interaction. At present, most emotion recognition methods still stay in a single modality. However, in daily life, human beings will usually disguise their real emotions, which leads to the problem that the accuracy of single modal emotion recognition is relatively terrible. Moreover, it is not easy to distinguish similar emotions. Therefore, we propose a new approach denoted as ICANet to achieve multimodal short video emotion recognition by employing three different modalities of audio, video and optical flow, making up for the lack of a single modality and then improving the accuracy of emotion recognition in short videos. ICANet has a better accuracy of 80.77% on the IEMOCAP benchmark, exceeding the SOTA methods by 15.89%., Comment: 4 pages, 5 figures

Published
2022

49. Effects of low temperature on near-nozzle breakup and droplet size distribution in airblast kerosene spray.

Author

Zhao, Yue, Wang, Yu, Zhang, Hang, Li, Tianxiong, Song, Ge, Liu, Tao, Chen, Si, Wu, Yingchun, and Wu, Xuecheng

Abstract

Atomization of low-temperature fuel is encountered in extreme operating conditions of liquid propulsion systems such as cold start and high-altitude relight for aeroengines. Fuel temperature has a great impact on airblast spray characteristics by influencing fuel viscosity and thus the gas–liquid interaction, which raises the demand to clarify the temperature-dependent transition in near-nozzle breakup behavior and the corresponding droplet size distribution. A liquid-centered swirl coaxial injector is tested on the low-temperature swirl spray and combustion test rig at Zhejiang University, using 25 kHz high-speed digital off-axis holography. RP-3 aviation kerosene is atomized under ignition conditions at temperatures of 233, 253, and 301 K, fuel pressures of 0.03 and 0.69 MPa, and air pressure ranging from 0 to 4.0 kPa. Time-resolved near-nozzle dynamics suggest four types of elementary breakup processes: wavy-sheet breakup, pulsating breakup, membrane-type breakup, and nonaxisymmetric Rayleigh breakup. Each process alternately dominates the near field as fuel Reynolds number (R e f ) and aerodynamic Weber number (W e g ) decrease, corresponding to four primary breakup modes. A mode classification plot is summarized. Spray structures show an extended breakup length and reduced spray cone angle as fuel temperature ( T f ) decreases. Increasing air pressure ( P g ) promotes spray expansion at 0.03 MPa, but contracts spray cone at 0.69 MPa. Cross-sectional Sauter mean diameter (SMD) distribution indicates a solid-cone spray at 0.03 MPa and a hollow cone spray at 0.69 MPa. Lowering T f will rise the SMD in the spray center at 0.03 MPa and transform the toroidal SMD distribution at 0.69 MPa into a solid one. Finally, a temperature-related SMD model is derived considering the exponential viscosity–temperature relationship, and a good fit with R 2 > 0.95 is achieved. This research aims to deepen the understanding of the effects of low temperature on the transition of near-nozzle atomization characteristics for airblast sprays. Both spray visualization and SMD results provide reference for numerical simulations and near-nozzle spray modeling. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results