检索结果-内蒙古大学图书馆

Causal Attention Transformer for Video Text Retrieval

IET Image Processing 2025年第1期19卷

作者： Lan, Hua Lv, Chaohui School of Information and Communication Engineering Communication University of China Beijing China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism Beijing China

In the metaverse, video text retrieval is an urgent and challenging need for users in social entertainment. The current attention-based video text retrieval models have not fully explored the interaction between video and text, and only brute force feature embedding. Moreover, Due to the unsupervised nature of attention weight training, existing models have weak generalization performance for dataset bias. Essentially, the model learns that false relevant information in the data is caused by confounding factors. Therefore, this article proposes a video text retrieval method based on causal attention transformer. Assuming that the confounding factors affecting the performance of video text retrieval all come from the dataset, a structural causal model that conforms to the video text retrieval task is constructed, and the impact of confounding effects during data training is reduced by adjusting the front door. In addition, we use causal attention transformer to construct a causal inference network to extract causal features between video text pairs, and replace the similarity statistical probability with causal probability in the video text retrieval framework. Experiments are conducted on the MSR-VTT, MSVD, and LSMDC datasets, which proves the effectiveness of the retrieval model proposed in this paper. © 2025 The Author(s). IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and technology.

关键词： Interactive computer graphics

来源：评论

学校读者我要写书评

暂无评论

Subjective Evaluation and Objective Analysis of Timbre Fusion of Chinese and Western Musical Instruments

Subjective Evaluation and Objective Analysis of Timbre Fusio...

引用

2021 International Conference on culture-Oriented Science and technology, ICCST 2021

作者： Liu, Jingyu Ran, Can Chen, Yuqu Xiang, Huiling Lin, Jiayu Huang, Yongzhan Jiang, Wei Ministry of Culture and Tourism Key Laboratory of Acoustic Visual Technology and Intelligent Control System China

ISBN: (纸本)9781665442541

Timbre fusion is the theoretical basis for the study of musical instrument acoustics and orchestration acoustics. At present, most of the research on timbre fusion is carried out on Western musical instruments. There are very few studies on the timbre fusion of Chinese musical instruments. The studies done are mainly studied from a qualitative perspective. Quantitative research on the timbre fusion of Chinese musical instruments will provide important theoretical support for the symphony research of the Chinese orchestra. Taking Chinese and Western musical instruments as research object, this paper constructs a Chinese and Western musical instrument fusion timbre database;a subjective experiment on timbre fusion is designed and implemented based on this database;45-dimensional objective acoustic parameters are extracted from the database. We use multiple linear regression, random forest, and multi-layer perceptron to correlate subjective and objective data and eventually construct a fusion model of Chinese and Western musical instruments. The accuracy of the models is tested, which shows that the model can predict the fusion of Chinese and Western musical instruments well. This study also found that the contribution rate of each objective acoustic parameter to fusion is different, and there are also differences between the timbre fusion models of Chinese musical instruments and Western musical instruments. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

MovieEmotion-IMG: An Emotion Distribution Dataset of Movie Scene Images

MovieEmotion-IMG: An Emotion Distribution Dataset of Movie S...

引用

2021 International Conference on culture-Oriented Science and technology, ICCST 2021

作者： Zhang, Jingjing Lin, Chen Wang, Chunxiao Dong, Yicong Jiang, Wei Ministry of Culture and Tourism Key Laboratory of Acoustic Visual Technology and Intelligent Control System China

ISBN: (纸本)9781665442541

One of the biggest challenges in sentiment analysis is to predict the complex feelings that humans evoke when viewing images. Due to the limitation of the quality and quantity of the dataset, the current learning-based algorithm mainly analyzes a single dominant emotion. Based on the above, this paper introduces an emotion distribution dataset of movie scene images with rich emotional semantics and professional aesthetic design, called MovieEmotion-IMG. Firstly nine labels, including eight emotional words and a 'neutrality' label, were identified, and a set of emotional evaluation rules were designed. Then, the emotion distribution annotation experiment was carried out on 17140 movie images, and an emotion annotation system was developed to assist the annotation work. Finally, two reliability test methods were designed based on the external reliability test method to verify the reliability of the results and ensure the availability of the dataset. This is the first large-scale emotion dataset of movie scene images and annotated distributed emotions to our knowledge. © 2021 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Risk Assessment of Stage Machinery Based on Entropy Weight and Fuzzy Inference Method

Risk Assessment of Stage Machinery Based on Entropy Weight a...

引用

2023 International Conference on culture-Oriented Science and technology, CoST 2023

作者： Wang, Huiqin Yang, Qingqing Li, Zhen Wang, Huiqi Ministry of Culture and Tourism Key Laboratory of Acoustic Visual Technology and Intelligent Control System Beijing China

ISBN: (纸本)9798350357998

It is of great significance to find out the hidden hazards of the stage machinery in advance and formulate the corresponding protective measures to improve the safety of the stage performance. A comprehensive method that integrates entropy weights and the fuzzy inference is proposed. Firstly, the risk factors are identified through Failure Modes and Effects Analysis (FMEA) method, with the information obtained by field survey and research. Then, the entropy weight method and Fault Tree Analysis (FTA) methods are adopted to analyze the risk factors so as to obtain the probability of the hazardous events. Lastly, the risk level of different event is obtained by the fuzzy inference method. The simulation result proves that the model is reasonable, objective, and feasible. © 2023 IEEE.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

Human Reliability Analysis of Professional Theater Based on CREAM

Human Reliability Analysis of Professional Theater Based on ...

引用

2024 International Conference on culture-Oriented Science and technology, CoST 2024

作者： Wang, Huiqin Wang, Huiqi Ren, Hui Ministry of Culture and Tourism Key Laboratory of Acoustic Visual Technology and Intelligent Control System Beijing China

ISBN: (纸本)9798350380347

In the context of human/equipment interaction processes, human error has become a significant factor influencing performance risk in professional theaters. To address this issue, the Cognitive Reliability and Error Analysis Method (CREAM) is integrated with fuzzy inference to assess the human reliability of theater staff and predict the probability of human error (HEP). Additionally, Grey Relational Analysis (GRA) is introduced to determine the weights of Common Performance Conditions (CPCs) within CREAM. Through this methodological framework, human reliability analysis of theater operators is conducted, enabling the prediction of human error rates across various scenarios. Subsequently, corresponding measures are provided, culminating in an effective solution to enhance performance safety within theatrical environments. © 2024 IEEE.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Software Defined Traffic Engineering for Improving Quality of Service

引用

China Communications 2017年第10期14卷 12-25页

作者： Xiaoming Li Jinyao Yan Hui Ren Key Laboratory of Acoustic Visual Technology and Intelligent Control System (Ministry of Culture) and Beijing Key Laboratory of Modern Entertainment Technology Communication University of China Beijing 100024 China Key Lab of Media Audio and Video Communication University of China Beijing 100024 China

The Software Defined Networking(SDN) paradigm separates the control plane from the packet forwarding plane, and provides applications with a centralized view of the distributed network state. Thanks to the flexibility and efficiency of the traffic flow management, SDN based traffic engineering increases network utilization and improves Quality of Service(QoS). In this paper, an SDN based traffic scheduling algorithm called CATS is proposed to detect and control congestions in real time. In particular, a new concept of aggregated elephant flow is presented. And then a traffic scheduling optimization model is formulated with the goal of minimizing the variance of link utilization and improving QoS. We develop a chaos genetic algorithm to solve this NP-hard problem. At the end of this paper, we use Mininet, Floodlight and video traces to simulate the SDN enabled video networking. We simulate both the case of live video streaming in the wide area backbone network and the case of video file transferring among data centers. Simulation results show that the proposed algorithm CATS effectively eliminates network congestions in subsecond. In consequence, CATS improves the QoS with lower packet loss rate and balanced link utilization.

关键词： SDN traffic engineering/traffic scheduling aggregated elephant flow congestion link utilization QoS video streaming

来源：评论

学校读者我要写书评

暂无评论

Effects of disparity distribution on visual comfort for multiple objects of stereoscopic images

引用

High technology Letters 2019年第1期25卷 42-47页

作者： Su Zhibin Li Dongrui Zou Fangju Ren Hui Key Laboratory of Acoustic Visual Technology and Intelligent Control System & China Beijing Key Laboratory of Modern Entertainment Technology Communication University of China

With the development of stereoscopic technology, more attention is attracted on the stereoscopic three-dimensional(S3 D) content and service, and researches on images and videos have emerged in large numbers. This paper focuses mainly on visual comfort affected by characteristics of disparity for multiple objects. To find the relationship between disparity distribution and visual comfort perception, several subject evaluation experiments are done. The study contains two spatial distribution types of disparity: 1) only one of the foreground objects has zero disparity; 2) one of the foreground objects has positive disparity, while the other one has negative disparity. The experimental results and relative regression analysis provide appropriate relationship between disparity distribution and visual comfort for both conditions, which is significant to meet the applicant field in S3 D content acquisition, display adjustment and quality evaluation.

关键词： disparity distribution disparity magnitude stereoscopic images visual comfort regression analyses

来源：评论

学校读者我要写书评

暂无评论

Research on communication method of OPC UA client based on ARM 18

Research on communication method of OPC UA client based on A...

引用

18th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2019

作者： Ren, Hui Liu, Yang Wang, Huiqin Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture Communication University of China Beijing China

ISBN: (纸本)9781728108018

The OPC UA standard overcomes many disadvantages of the traditional OPC, and has significant advantages in platform independence, communication security and model construction, thus completing the information exchange under different platforms and interfaces. At present, the automation system equipment has the problems of complex protocols and interfaces and poor portability of industrial computer. To solve this problem, this paper develops the ARM embedded OPC UA client to complete the data communication with the automation system device server by porting the open62541 open source library on the ARM embedded device equipped with the FreeRTOS system. In this research, by building the OPC UA client on the embedded system, the connection and communication with the server are realized, which is also cheap and flexible to use. Experiments show that the system can be used in equipment debugging, field operation and emergency control, and has a wide range of application prospects and practical value. © 2019 IEEE.

关键词： Ethernet

来源：评论

学校读者我要写书评

暂无评论

Multiplexing technology: Multi Slot Amplitude Coding 9

Multiplexing Technology: Multi Slot Amplitude Coding

引用

2017 9th IEEE International Conference on Communication Software and Networks (ICCSN 2017)

作者： Chai Jia Bai Shilei Information Engineering School Communication University of China Beijing Key Laboratory of Modern Entertainment Technology Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture

ISBN: (纸本)9781509038237;9781509038220

We presented a combination of a new coding technique called Multi Slot Amplitude Coding(MSAC). By jointing Optisystem and Matlab, the coding and decoding of MSAC, Duty Cycle Division Multiplexing(DCDM) and Absolute Polar Duty Cycle Division Multiplexing(APDCDM) all are achieved in a same Free Space Optical(FSO) communication system. By comparing average energy of each symbol, different mapping rules of MSAC are compared. The simulation results of a 3-tributaries FSO system shows that MSAC can adapt to different systems and weather environment by using optimized mapping rule. Besides, at the same aggregate bit rate of 3×10 Gbps, MSAC gives a spectral width of 60 GHz, which is 25% reduction than DCDM.

关键词： MSAC slot amplitude level mapping rule spectral efficiency

来源：评论

学校读者我要写书评

暂无评论

Non-parallel and Many-to-One Musical Timbre Morphing using DDSP-Autoencoder and Spectral Feature Interpolation

Non-parallel and Many-to-One Musical Timbre Morphing using D...

引用

2021 International Conference on culture-Oriented Science and technology, ICCST 2021

作者： Zou, Yi Liu, Jingyu Jiang, Wei Ministry of Culture and Tourism Communication University of China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Beijing China

ISBN: (纸本)9781665442541

Abstract - Timbre morphing is a signal processing technology that involves the use of an interpolation algorithm to gradually change the timbre of one instrument into that of another. However, the prepared target audio, which possesses the same music content (such as score and rhythm) as the original audio, is essential to the input used in the morphing technique. To meet the application requirements of non-parallel and many-to-one processing, we combined the signal processing technology of spectral feature interpolation with the deep learning technology of the autoencoder to provide the timbre morphing technology with a generalization ability. The complex framework, which focuses on the processing of harmonic information, is built using the pitch tracking, temporal signal processing, decoder, source-filter modeling, and spectral feature interpolation. Notably, unlike the neural vocoder that is commonly used in voice conversion, the decoder, which is trained using a data reconstruction method, is used to map the input audio features to the harmonic amplitude distribution with the target timbre. Experiments were conducted in which the clarinet timbre was morphed into a trumpet. An evaluation of the spectral features demonstrated the validity of the morphing technology. © 2021 IEEE.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：