检索结果-内蒙古大学图书馆

Overview of the Tenth Dialog System Technology Challenge: DSTC10

学校读者我要写书评

暂无评论

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 765-778页

作者： Yoshino, Koichiro Chen, Yun-Nung Crook, Paul Kottur, Satwik Li, Jinchao Hedayatnia, Behnam Moon, Seungwhan Fei, Zhengcong Li, Zekang Zhang, Jinchao Feng, Yang Zhou, Jie Kim, Seokhwan Liu, Yang Jin, Di Papangelis, Alexandros Gopalakrishnan, Karthik Hakkani-Tur, Dilek Damavandi, Babak Geramifard, Alborz Hori, Chiori Shah, Ankit Zhang, Chen Li, Haizhou Sedoc, Joao D'haro, Luis F. Banchs, Rafael Rudnicky, Alexander Guardian Robot Project R-IH RIKEN 2-2-2 Hikaridai Seika Shoraku619-0288 Japan Information Science Nara Institute of Science and Technology Ikoma630-0101 Japan Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Inc. Palo AltoCA95054 United States Alexa AI *** Inc. SunnyvaleCA94089 United States Meta Seattle RedmondWA98052 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Tencent AI Lab Beijing Beijing China Kexueyuan South Road Zhongguancun Beijing100190 China Beijing 100190 China Alexa AI *** Inc. SunnyvaleCA United States 1120 Enterprise way Sunnyvale94089 United States *** Inc. SeattleWA United States Menlo Park CA United States Audio and Speech Group Mitsubishi Electric Research Laboratories CambridgeMA02139-1955 United States Carnegie Mellon University Department of Language and Information Technologies or just Carnegie Mellon University Pittsburgh United States National University of Singapore Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Shenzhen Research Institute of Big Data School of Data Science Chinese University of Hong Kong Shenzhen518172 China New York University New YorkNY United States ETSI de Telecomunicacion - Speech Technology and Machine Learning Group Universidad Politecnica de Madrid Ciudad Universitaria Madrid28040 Spain Nanyang Technological University Singapore Singapore Carnegie Mellon University PittsburghPA United States

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio Visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks. © 2023 The Authors.

关键词： Job analysis

An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yang, Yiju Zhang, Tianxiao Li, Guanyu Kim, Taejoon Wang, Guanghui Department of Electrical Engineering and Computer Science University of Kansas LawrenceKS66045 United States Department of Computer Science Ryerson University TorontoONM5B 2K3 Canada

In this paper, we propose a dual-module network architecture that employs a domain discriminative feature module to encourage the domain invariant feature module to learn more domain invariant features. The proposed architecture can be applied to any model that utilizes domain invariant features for unsupervised domain adaptation to improve its ability to extract domain invariant features. We conduct experiments with the Domain-Adversarial Training of Neural Networks (DANN) model as a representative algorithm. In the training process, we supply the same input to the two modules and then extract their feature distribution and prediction results respectively. We propose a discrepancy loss to find the discrepancy of the prediction results and the feature distribution between the two modules. Through the adversarial training by maximizing the loss of their feature distribution and minimizing the discrepancy of their prediction results, the two modules are encouraged to learn more domain discriminative and domain invariant features respectively. Extensive comparative evaluations are conducted and the proposed approach outperforms the state-of-the-art in most unsupervised domain adaptation tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Forecasting

Few-shot learning by integrating spatial and frequency representation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Xiangyu Wang, Guanghui Department of Electrical Engineering and Computer Science University of Kansas LawrenceKS66045 United States Department of Computer Science Ryerson University TorontoONM5B 2K3 Canada

Human beings can recognize new objects with only a few labeled examples, however, few-shot learning remains a challenging problem for machine learning systems. Most previous algorithms in few-shot learning only utilize spatial information of the images. In this paper, we propose to integrate the frequency information into the learning model to boost the discrimination ability of the system. We employ Discrete Cosine Transformation (DCT) to generate the frequency representation, then, integrate the features from both the spatial domain and frequency domain for classification. The proposed strategy and its effectiveness are validated with different backbones, datasets, and algorithms. Extensive experiments demonstrate that the frequency information is complementary to the spatial representations in few-shot classification. The classification accuracy is boosted significantly by integrating features from both the spatial and frequency domains in different few-shot learning tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Image classification

Digital Innovation in Faculty Development: Crafting Academic Portfolios for the Next Era 28th

学校读者我要写书评

暂无评论

Digital Innovation in Faculty Development: Crafting Academic...

28th International Conference on Knowledge Based and Intelligent information and engineering Systems, KES 2024

作者： Kanematsu, Hideyuki Ogawa, Akiko Kogo, Takeshi Kawai, Risa Barry, Dana M. Ogawa, Nobuyuki Suzuki, Shin-Nosuke Hagiwara, Goichi Kurita, Kayoko Suzuka College Shiroko-cho Mie Suzuka510-0294 Japan Dept. Materials & Manufacturing Science Graduate School of Engineering Osaka University 2-1 Yamada-Oka Suita Osaka565-0871 Japan Facuity of Science Nara Women's University Uoya Nishimachi Nara Pref Nara630-8506 Japan Department of Electrical & Computer Engineering Clarkson University Potsdam/SUNY Canton CantonNY United States Gifu College Kami-makuwa Gifu Motosu510-0495 Japan 771 Nakakuki Tochigi Oyama323-0806 Japan Faculty of Human Sciences Kyushu Sangyo University Matsukadai 2-chome Higashi-ku Fukuoka-shi Fukuoka813-8503 Japan Centerfor Research andDevelopment in Higher Education the University of Tokyo 7-3-1 Hongo Bunkyo-ku 113-0033m Japan

This paper presents one project on integrating digital innovation in faculty development by creating academic portfolios. Academic portfolios document the multifaceted achievements of faculty members and help them in their professional progress and self-evaluation. This initiative adopted a systematic approach following the TU guidelines, incorporating lectures, mentoring, and collaborative sessions, and guiding educators to create portfolios that integrate teaching, research, and service activities. The project's use of digital tools enabled time efficiency, accessibility, and iterative improvement and improved the transparency and scope of faculty performance. The digital platform also facilitated real-time feedback and integration of the portfolio with a wider digital repository, which aligns with environmentally sustainable practices. Participant feedback highlighted increased motivation and a deeper understanding of the interaction between teaching and research. The project demonstrated that the digital portfolio powerfully aligned teachers' activities with their professional ethos and promoted continuous development and personal growth goals. This approach suggests the potential for transforming faculty development in the academic community. © 2024 The Authors.

关键词： Teaching

Towards More Effective PRM-based Crowd Counting via A Multi-resolution Fusion and Attention Network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sajid, Usman Wang, Guanghui Department of Electrical Engineering and Computer Science University of Kansas LawrenceKS66045 United States Department of Computer Science Ryerson University TorontoONM5B 2K3 Canada

The paper focuses on improving the recent plug-and-play patch rescaling module (PRM) based approaches for crowd counting. In order to make full use of the PRM potential and obtain more reliable and accurate results for challenging images with crowd-variation, large perspective, extreme occlusions, and cluttered background regions, we propose a new PRM based multi-resolution and multi-task crowd counting network by exploiting the PRM module with more effectiveness and potency. The proposed model consists of three deep-layered branches with each branch generating feature maps of different resolutions. These branches perform a feature-level fusion across each other to build the vital collective knowledge to be used for the final crowd estimate. Additionally, early-stage feature maps undergo visual attention to strengthen the later-stage channel's understanding of the foreground regions. The integration of these deep branches with the PRM module and the early-attended blocks proves to be more effective than the original PRM based schemes through extensive numerical and visual evaluations on four benchmark datasets. The proposed approach yields a significant improvement by a margin of 12.6% in terms of the RMSE evaluation criterion. It also outperforms state-of-the-art methods in cross-dataset evaluations. © 2021, CC BY.

关键词： Behavioral research

Single-Photon Generation: Materials, Techniques, and the Rydberg Exciton Frontier

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Keni, Arya Barua, Kinjol Heshami, Khabat Javadi, Alisa Alaeian, Hadiseh Elmore Family School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States National Research Council of Canada 100 Sussex Drive OttawaONK1N 5A2 Canada Department of Physics University of Ottawa ONK1N 6N5 Canada Institute for Quantum Science and Technology Department of Physics and Astronomy University of Calgary ABT2N 1N4 Canada Department of Electrical and Computer Engineering University of Oklahoma NormanOK73069 United States Department of Physics University of Oklahoma NormanOK73069 United States Department of Physics and Astronomy Purdue University West LafayetteIN47907 United States

Due to their quantum nature, single-photon emitters generate individual photons in bursts or streams. They are paramount in emerging quantum technologies such as quantum key distribution, quantum repeaters, and measurement-based quantum computing. Many such systems have been reported in the last three decades, from Rubidium atoms coupled to cavities to semiconductor quantum dots and color centers implanted in waveguides. This review article highlights different material systems with deterministic and controlled single photon generation. We discuss and compare the performance metrics, such as purity and indistinguishability, for these sources and evaluate their potential for different applications. Finally, a new potential single-photon source, based on the Rydberg exciton in solid−state metal oxide thin films, is introduced, briefly discussing its promising qualities and advantages in fabricating quantum chips for quantum photonic applications. © 2024, CC BY.

关键词： Semiconductor quantum dots

Towards Bilateral Client Selection in Federated Learning Using Matching Game Theory

学校读者我要写书评

暂无评论

Towards Bilateral Client Selection in Federated Learning Usi...

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Osama Wehbi Sarhad Arisdakessian Omar Abdel Wahab Hadi Otrok Safa Otoum Azzam Mourad Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Department of Computer Science & Engineering Université du Québec en Outaouais Gatineau Canada Department of EECS Center of Cyber-Physical Systems (C2PS) Khalifa University Abu Dhabi UAE College of Technological Innovation Zayed University Dubai UAE Division of Science New York University Abu Dhabi UAE

ISBN: (纸本)9781665435413

Federated Learning (FL) is a novel distributed privacy-preserving learning paradigm, which enables the collaboration among several devices. However, selecting the participants that would contribute to this collaborative training is highly challenging. Adopting a random selection strategy would entail substantial problems due to the heterogeneity in terms of data quality and resources across the participants. To overcome this problem, we propose an intelligent client selection approach for federated learning on IoT devices using matching game theory. Our solution involves the design of: (1) preference functions for the client IoT devices and federated servers to allow them to rank each other according to several criteria such as accuracy and price, and (2) intelligent matching algorithms that take into account the preferences of both parties in their design. Based on our simulation findings, our strategy surpasses the VanillaFL selection approach in terms of maximizing both the revenues of the client devices and accuracy of the global federated learning model.

关键词： Training Federated learning Simulation Data integrity Collaboration Games Servers

Low Rank Reduced Biquaternion Tensor Ring Decomposition and Tensor Completion

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Luo, Hui Liu, Xin Liu, Wei Zhang, Yang School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology Avenida Wai Long TaiPa 999078 China Macau Institute of Systems Engineering Faculty of Innovation Engineering Macau University of Science and Technology Avenida Wai Long TaiPa 999078 China School of Artificial Intelligence Sun Yat-sen University The Guangdong Key Laboratory of Big Data Analysis and Processing No.135 West Xingang Road Guangdong Provience Guangzhou510275 China Department of Mathematics University of Manitoba No.135 West Xingang Road WinnipegMBR3T 2N2 Canada

Reduced biquaternions (RBs), as an extension of complex numbers, have demonstrated exceptional capabilities in digital signal and image processing. They not only excel particularly in encoding color information but also feature multiplicative commutativity, which simplify the theoretical analysis of related algorithms. Concurrently, tensor completion methods based on tensor ring decomposition in the real domain have been proven effective in exploiting low-rank structures. Building upon these insights, this paper first introduces the Reduced Biquaternion Tensor Ring (RBTR) decomposition, along with a detailed exposition of the corresponding algorithm RBTR-SVD. Leveraging RBTR decomposition, we propose a novel low-rank tensor completion algorithm RBTR-TV integrating RBTR rank with Total Variation (TV) regularization to optimize the process. In color image completion tasks, our method exhibits remarkable stability and robustness, outperforming traditional methods, especially if there are a lot of missing data in the image. © 2024, The Authors. All rights reserved.

关键词： Tensors

A fast and accurate tube diameter visualization method for digestive system medical images

学校读者我要写书评

暂无评论

IEEJ Transactions on Electronics, Information and Systems

IEEJ Transactions on Electronics, Information and Systems 2021年第9期141卷 982-991页

作者： Ueda, Mitsuru Kondo, Masafumi Kayano, Isao Sejima, Yoshihiro Yokogawa, Tomoyuki Sato, Yoichiro Sugihara, Yuusaku Matsumoto, Kazuyuki Graduate School of Computer Science and Systems Engineering Okayama Prefectural University 111 Kuboki Soja Okayama719-1197 Japan Faculty of Health Science and Technology Kawasaki University of Medical Welfare 288 Matsushima Kurashiki Okayama701-0193 Japan Faculty of Informatics Kansai University 2-1-1 Ryozenji-cho Osaka Takatsuki569-1095 Japan Department of Gastroenterology Okayama University Hospital 2-5-1 Shikata-cho Kita-ku Okayama700-8558 Japan

Although the tube diameter and stenosis rate are important observations in the diagnosis using medical images of digestive organ, such as digestive systems, the diagnosis is based on the physician’s subjective evaluation. On the other hand, automatic measurement of tube diameters by image processing has been used for blood vessels, which are tubular tissues similar to digestive systems, and it is also possible to visualize the vessel diameter by assigning pseudo-colors according to the length of the vessel. However, it is difficult to apply the existing diameter visualization methods directly to digestive system medical images due to the processing time and accuracy problems because the tubes are large and tortuous, unlike blood vessels. In this paper, we propose a method to measure the tube diameter quickly by dynamically calculating the next featured pixel using the history of the midpoints of the tube diameter line. Furthermore, we derive an approximate curve corresponding to the centerline of the tube from the history of the featured pixels and measure the tube diameter with high accuracy. We applied the proposed method to various types of digestive system medical images and confirmed that the proposed method could accurately measure and visualize the tube diameter along the shape of the tube and reduce the processing time by up to 99%. 2021 The Institute of Electrical Engineers of Japan.

关键词： Pixels