检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Phaphuangwittayakul, Aniwat Guo, Yi Ying, Fangli Xu, Wentian Zheng, Zheng Department of Computer Science and Engineering East China University of Science and Technology China National Engineering Laboratory for Big Data Distribution and Exchange Technologies China Shanghai Engineering Research Center of Big Data and Internet Audience China

ISBN: (纸本)9781665438643

With the exponential growth of video data, video summarization techniques are urgently needed for reducing people's efforts in the videos' content exploration by generating succinct but informative summaries from original lengthy videos. Though supervised video summarization approaches have demonstrated the state-of-the-art performance, unsupervised methods are still highly demanded due to resourcefully expensive human annotations and the subjectiveness of video summarization tasks. In this paper, a novel unsupervised-based Deep Self-attention Recurrent summarization network with Reinforcement Learning (DSR-RL) for video summarization is proposed. The model can learn the input video sequence and suggest the key-shot summary without additional human annotations by integrating self-attention, BRNN, and reinforcement learning mechanisms. The DSR-RL improves not only importance score through the attention map vector of self-attention network but also the diversity of summaries via the reward function of reinforcement learning. Our method outperforms the state-of-the-art unsupervised video summarization methods on both SumMe and TVSum datasets. The source code is available at https://***/phaphuang/DSR-RL. © 2021 IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation with Source-free Unsupervised Domain Adaptation for BERT Model Compression

Knowledge Distillation with Source-free Unsupervised Domain ...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Jing Tian Juan Chen Ning Jiang Chen Lin Bai Suqun Huang School of Computer and Electronic Information Guangxi University Nanning China Guangxi Intelligent Digital Services Research Center of Engineering Technology Nanning China Education Department of Guangxi Zhuang Autonomous Region Key Laboratory of Parallel Distributed and Intelligent Computing (Guangxi University) Nanning China

The pre-training language model BERT has brought significant performance improvements to a series of natural language processing tasks, but due to the large scale of the model, it is difficult to be applied in many practical application scenarios. With the continuous development of edge computing, deploying the models on resource-constrained edge devices has become a trend. Considering the distributed edge environment, how to take into account issues such as data distribution differences, labeling costs, and privacy while the model is shrinking is a critical task. The paper proposes a new BERT distillation method with source-free unsupervised domain adaptation. By combining source-free unsupervised domain adaptation and knowledge distillation for optimization and improvement, the performance of the BERT model is improved in the case of cross-domain data. Compared with other methods, our method can improve the average prediction accuracy by up to around 4% through the experimental evaluation of the cross-domain sentiment analysis task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Temporal Shift for Personality Recognition with Pre-Trained Representations

Temporal Shift for Personality Recognition with Pre-Trained ...

引用

International Symposium on Chinese Spoken Language Processing

作者： Hanzhe Xu Xuefei Liu Cong Cai Kang Zhu Jizhou Cui Ruibo Fu Heng Xie Jianhua Tao Zhengqi Wen Ziping Zhao Guanjun Li Le Wang Hao Lin College of Computer and Information Engineering Tianjin Normal University Institute of Automation Chinese Academy of Sciences Beijing Institute of Technology School of Computer Science and Technology Anhui University School of Information Science and Technology ShanghaiTech University Department of Automation Tsinghua University Beijing National Research Center for Information Science and Technology Tsinghua University Migu Meland Co. Ltd.

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

Personality, as a reflection of our inner psychological traits, profoundly influences our behavioral patterns, decision-making processes, and the way we interact with the world. Therefore, personality recognition has gradually become an important research direction in the fields of psychology and human-computer interaction. However, most previous works have focused on using pre-trained models to construct more complex models for feature extraction, neglecting the integration of multi-channel information and the fusion between channel information. To address the issue of multi-channel information integration, we propose and validate an innovative method based on multi-scale convolutional feature extraction and a temporal shift module for personality recognition in the speech modality. We use the wav2vec pre-trained model to extract features and enhance information fusion between channels by introducing multi-scale convolutional kernels and a temporal shift module. It expands the model's perception range and sensitivity to personality. Experimental results show that this method performs well in terms of accuracy (ACC) and concordance correlation coefficient (CCC).

关键词： Human computer interaction Sensitivity Psychology Speech recognition Feature extraction Transformers Reflection Speech processing Kernel Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Naked-eye observation of water-forming reaction on palladium etalon:transduction of gas-matter reaction into light-matter interaction

引用

PhotoniX 2023年第1期4卷 349-363页

作者： Jongsu Lee Eui-Sang Yu Taehyun Kim In Soo Kim Seok Chung Seung Jae Kwak Won Bo Lee Yusin Pak Yong-Sang Ryu Sensor System Research Center Korea Institute of Science and TechnologySeoul 02792Republic of Korea Department of Electrical and Computer Engineering Seoul National UniversitySeoul 08826Republic of Korea Smart Materials Research Section Electronics and Telecommunications Research InstituteDaejeon 34129Republic of Korea Department of Micro/Nano Systems Korea University02841 SeoulRepublic of Korea Nanophotonics Research Center Korea Institute of Science and TechnologySeoul 02792Republic of Korea School of Mechanical Engineering Korea UniversitySeoul 02841Republic of Korea School of Chemical and Biological Engineering Seoul National UniversitySeoul 08826Republic of Korea Interdisciplinary Program in Precision Public Health Korea UniversitySeoul 02481Republic of Korea School of Biomedical Engineering Korea UniversitySeoul 02481Republic of Korea

Palladium is the most prominent material in both scientific and industrial research on gas storage,purification,detection,and catalysis due to its unique properties as a catalyst and hydrogen *** the dynamic optical phenomena of palladium reacting with hydrogen,transduction of the gas-matter reaction into light-matter interaction is attempted to visualize the dynamic surface chemistry and reaction *** simple geometry of the metal-dielectric-metal structure,Fabry-Perot etalon,is employed for a colorimetric reactor,to display the catalytic reaction of the exposed gas via water-film/bubble formation at the dielectric/palladium *** adsorption/desorption behavior and catalytic reaction of hydrogen and oxygen on the palladium surface display highly repeatable and dramatic color changes based on two distinct water formation trends:the foggy effect by water bubbles and the whiteout effect by water film *** and experiments demonstrate the robustness of the proposed Fabry-Perot etalon as an excellent platform for monitoring the opto-physical phenomena driven by heterogeneous catalysis.

关键词： Palladium Hydrogen Oxygen Fabry-Perot resonators Colorimetric sensors Water-forming reaction

来源：评论

学校读者我要写书评

暂无评论

IoT-based Green Transportation Technique for Sustainable Growth in Transportation Industry

IoT-based Green Transportation Technique for Sustainable Gro...

引用

Emerging research in Computational Science (ICERCS), International Conference on

作者： Ahmed R. Hassan Laith Fouad Naseer Ali Hussien Noora Hani Sherif Aqeel Ali Marwa Ibrahem Department of Medical Devices Engineering Technologies National University of Science and Technology Nasiriyah Iraq Medical Instruments Engineering Techniques Al-Farahidi University Baghdad Iraq Information and Communication Technology Research Group Scientific Research Center Al-Ayen University Thi-Qar Iraq Computer Technologies Engineering Al-Turath University College Baghdad Iraq Technical Computer Engineering Department Al-Kunooze University College Basrah Iraq Computer Technology Engineering Al-Maamoun University College Baghdad Iraq

The cutting-edge concept known as the Internet of Things (IoT) is responsible for transforming traditional existence into a high-tech society. The term " Transportation Industry" refers to the processes involved in moving and storing goods from the place of origin, through the manufacturing stage, to the point of sale or consumption, and back again (reverse logistics). Because logistics is so pervasive, has so many moving parts, and is driven mostly by fossil fuels, there is much room for introducing IoT-enabled sustainability measures. Long-term sustainability is significantly impacted by transportation infrastructure. Concerns over environmental integrity, socioeconomic vitality, and the planning of climate change strategies due to rising CO2 levels have all driven interest in alternative sustainability frameworks. It is crucial to address sustainable training because it is required in any pattern, especially in the twenty-first century. Society, the economy, and the environment are categorised for sustainable growth in the transportation sector. This study introduces the Internet of Things green transportation system (IoT-GTS), which can be used to build a dependable transportation network. Examples of sustainable transportation projects include capacity planning, price controls, advancements in vehicle technology, clean fuels, and efficient land use and transportation planning. This article examines several economic difficulties, like setting fair prices and creating a robust transport system. The study results serve as a roadmap for managers, transport modellers, and regulators to accept signals at the operational level, greatly simplifying the challenging task of selecting an indication. The simulation results demonstrate a lower consumption ratio, lower fuel consumption, higher scalability, lower noise, lower CO2 emissions, and a lower average delay.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Bayesian regularization-based solution predictive procedure for hybrid nanoparticles of AA7072-AA7075 oxide movement across a porous medium

引用

ZAMM Zeitschrift fur Angewandte Mathematik und Mechanik 2023年第10期103卷

作者： Awan, Saeed Ehsan Ali, Faizan Awais, Muhammad Shoaib, Muhammad Raja, Muhammad Asif Zahoor Department of Electrical and Computer Engineering COMSATS University Islamabad Attock Pakistan Department of Mathematics COMSATS University Islamabad Attock Pakistan Yuan Ze University Taoyuan City Taiwan Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan

The research community has shown great interest for investigation in the nanofluids models involving Aluminum Alloys AA7072 and AA7072 +AA7075 due to their advantageous impact on heat transfer, physical and mechanical characteristic exploiting in broad engineering applications such as manufacturing of spacecraft, aircraft parts and building testing. The hybrid nanomaterial AA7072-AA7075 based fluidic system is investigated in this paper using an artificial neural network with Bayesian regularization scheme (ANNs-BRS). The derived partial differential equations (PDEs) are transformed into ordinary differential equations system ODEs and obtained the reference datasets for the estimated solution dynamics of hybrid nanofluidic system. For prominent parameters, the influence of flow on the temperature distribution and velocity plot are investigated. The performance on 80% training samples, 5% testing and 15% validation dataset for ANNs-BRS is well-established in terms of error histogram plots, regression analysis, and MSE based statistics. The results for entropy generation, Eckert number Ec, magnetic interaction parameter M, suction parameter S, and heat generation parameter Q are also discussed. The results show that the Eckert number Ec has the effect of slowing down the rate of heat transfer while increasing the temperature and increases in suction parameter causes decrease in temperature while increase in temperature profile due to enhancement of suction parameter. © 2023 Wiley-VCH GmbH.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Ranking Aggregation with Interactive Feedback for Collaborative Person Re-identification 33

Ranking Aggregation with Interactive Feedback for Collaborat...

引用

33rd British Machine Vision Conference Proceedings, BMVC 2022

作者： Huang, Ji Liang, Chao Zhang, Yue Wang, Zhongyuan Zhang, Chunjie National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing Jiaotong University Beijing100044 China

Person re-identification (re-ID) aims to retrieve the same person from a group of networking cameras. Ranking aggregation (RA), a method to aggregates multiple ranking results, can further improve the retrieval accuracy in re-ID tasks. Existing RA work can be generally divided into unsupervised methods and fully-supervised methods. Unsupervised methods lack external supervision, can hardly achieve the optimal results. In contrast, fully-supervised methods need massive labeling data for training, which is prohibitively expensive in the practical application. This paper studies interactive RA (IRA) to address the above challenges in existing RA research. The core idea is to utilize a small amount of supervisory information, obtained from users' relevance feedback, to supervise RA method to produce better re-ranking results. Compared with unsupervised methods, IRA introduces supervisory information and thus has better aggregation accuracy. Compared with fully-supervision methods, the supervisory information of IRA is more readily available, and can be targeted to specific queries. Particularly, we propose two IRA implementations, based on ranking positions and scores respectively, to adapt to diverse application scenarios, where rankers only give rankings, or rankers give similarity scores. Experiments on three public re-ID datasets have shown that IRA significantly outperforms the-state-of-art unsupervised baselines, and achieves similar accuracy with less labeling cost than the fully-supervised RA method. © 2022. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Sensitivity Optimization of Impedance-Based Biosensor for Point-of-Care Applications

SSRN

引用

SSRN 2024年

作者： Jiang, Tianxiang Ye, Xuanjie Tian, Zuyuan Shaheen, Mohamed Abdelhamid, Ahmed Feng, Yiwei Li, Bingxuan Zhang, Yusheng Wang, Xihua Chen, Jie Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 1H9 Canada National Engineering Research Center for Biomaterials College of Biomedical Engineering Sichuan University Sichuan Chengdu610064 China Academy for Engineering & Technology Fudan University Shanghai200433 China

The introduction of advanced lab-on-chip technologies, such as electrochemical biosensors, is promising for point-of-care testing. Impedimetric biosensors are of particular interest for a wide range of applications due to their low-cost fabrication requirements. Enhancing the sensitivity of such devices is currently a major challenge in the field. Here we describe sensitivity enhancements of an interdigitated electrode (IDE) impedimetric biosensor. The unique IDE design of our device allows for surface modification of antigens within the electrode gaps to allow highly selective antigen capture in biological samples. We have constructed a 3D model to simulate and study the impact of electrode geometry on impedance sensitivity. Simulation results revealed a linear trend between electrode inner gap distance and sensitivity, while electrode height and width showed non-linear trends. To demonstrate proof-of-concept, three IDE chip designs were tested with electrode gaps of 3 µm, 4 µm, and 5 µm. The chips were used to detect human anti-SARS-CoV-2 monoclonal antibody (mAb) at concentrations ranging from 50 ng/mL to 500 ng/mL. The 3 µm design was shown to be the most sensitive, with successful detection of the mAb at the lowest tested concentration (50 ng/mL). This study provides a pathway to improving biosensor sensitivity through electrode geometric design, which can be further utilized in diverse electrode-based biosensors and optimization for multiple clinical and research applications beyond COVID-19. © 2024, The Authors. All rights reserved.

关键词： Electrochemical impedance spectroscopy

来源：评论

学校读者我要写书评

暂无评论

ReLeaPS : Reinforcement Learning-based Illumination Planning for Generalized Photometric Stereo

ReLeaPS : Reinforcement Learning-based Illumination Planning...

引用

International Conference on computer Vision (ICCV)

作者： Jun Hoong Chan Bohan Yu Heng Guo Jieji Ren Zongqing Lu Boxin Shi National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Engineering Research Center of Visual Technology School of Computer Science Peking University School of Artificial Intelligence Beijing University of Posts and Telecommunications Osaka University School of Mechanical Engineering Shanghai Jiao Tong University

Illumination planning in photometric stereo aims to find a balance between surface normal estimation accuracy and image capturing efficiency by selecting optimal light configurations. It depends on factors such as the unknown shape and general reflectance of the target object, global illumination, and the choice of photometric stereo backbones, which are too complex to be handled by existing methods based on handcrafted illumination planning rules. This paper proposes a learning-based illumination planning method that jointly considers these factors via integrating a neural network and a generalized image formation model. As it is impractical to supervise illumination planning due to the enormous search space for ground truth light configurations, we formulate illumination planning using reinforcement learning, which explores the light space in a photometric stereo-aware and reward-driven manner. Experiments on synthetic and real-world datasets demonstrate that photometric stereo under the 20-light configurations from our method is comparable to, or even surpasses that of using lights from all available directions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VIRES: Video Instance Repainting via Sketch and Text Guided Generation

arXiv

引用

arXiv 2024年

作者： Weng, Shuchen Zheng, Haojie Zhang, Peixuan Hong, Yuchen Jiang, Han Li, Si Shi, Boxin National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China OpenBayes Information Technology Co. Ltd. China School of Software and Microelectronics Peking University China School of Artificial Intelligence Beijing University of Posts and Telecommunications China

We introduce VIRES, a video instance repainting method with sketch and text guidance, enabling video instance repainting, replacement, generation, and removal. Existing approaches struggle with temporal consistency and accurate alignment with the provided sketch sequence. VIRES leverages the generative priors of text-to-video models to maintain temporal consistency and produce visually pleasing results. We propose the Sequential ControlNet with the standardized self-scaling, which effectively extracts structure layouts and adaptively captures high-contrast sketch details. We further augment the diffusion transformer backbone with the sketch attention to interpret and inject fine-grained sketch semantics. A sketch-aware encoder ensures that repainted results are aligned with the provided sketch sequence. Additionally, we contribute the VIRESET, a dataset with detailed annotations tailored for training and evaluating video instance editing methods. Experimental results demonstrate the effectiveness of VIRES, which outperforms state-of-the-art methods in visual quality, temporal consistency, condition alignment, and human ratings. Project page:https://***/projects/VIRES/ Copyright © 2024, The Authors. All rights reserved.

关键词： Video analysis

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：