检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Hanlei Xu, Hua Long, Fei Wang, Xin Gao, Kai State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University China School of Information Science and Engineering Hebei University of Science and Technology China Technology Development Co. Ltd Nanchang330036 China

Discovering the semantics of multimodal utterances is essential for understanding human language and enhancing human-machine interactions. Existing methods manifest limitations in leveraging nonverbal information for discerning complex semantics in unsupervised scenarios. This paper introduces a novel unsupervised multimodal clustering method (UMC), making a pioneering contribution to this field. UMC introduces a unique approach to constructing augmentation views for multimodal data, which are then used to perform pre-training to establish well-initialized representations for subsequent clustering. An innovative strategy is proposed to dynamically select high-quality samples as guidance for representation learning, gauged by the density of each sample’s nearest neighbors. Besides, it is equipped to automatically determine the optimal value for the top-K parameter in each cluster to refine sample selection. Finally, both high- and low-quality samples are used to learn representations conducive to effective clustering. We build baselines on benchmark multimodal intent and dialogue act datasets. UMC shows remarkable improvements of 2-6% scores in clustering metrics over state-of-the-art methods, marking the first successful endeavor in this domain. The complete code and data are available at https://***/thuiar/UMC. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs

arXiv

引用

arXiv 2023年

作者： Wang, Jingyi Huang, Jinfa Zhang, Can Deng, Zhidong Department of Computer Science Tsinghua University Beijing100084 China School of Electronic and Computer Engineering Peking University China THUAI Department of Computer Science State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing100084 China

Dynamic scene graphs generated from video clips could help enhance the semantic visual understanding in a wide range of challenging tasks such as environmental perception, autonomous navigation, and task planning of self-driving vehicles and mobile robots. In the process of temporal and spatial modeling during dynamic scene graph generation, it is particularly intractable to learn time-variant relations in dynamic scene graphs among frames. In this paper, we propose a Time-variant Relation-aware TRansformer (TR2), which aims to model the temporal change of relations in dynamic scene graphs. Explicitly, we leverage the difference of text embeddings of prompted sentences about relation labels as the supervision signal for relations. In this way, cross-modality feature guidance is realized for the learning of time-variant relations. Implicitly, we design a relation feature fusion module with a transformer and an additional message token that describes the difference between adjacent frames. Extensive experiments on the Action Genome dataset prove that our TR2 can effectively model the time-variant relations. TR2 significantly outperforms previous state-of-the-art methods under two different settings by 2.1% and 2.6% respectively. © 2023, CC BY.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Low-Cost, High-Performance Algorithm and Hardware Architecture for SAO Mode Decision

Low-Cost, High-Performance Algorithm and Hardware Architectu...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Bingjing Hou Chang Liu Yuejun Zhang Leilei Huang Minge Jing Yibo Fan State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Institute of Microelectronic Circuits and Systems East China Normal University Shanghai China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Sample adaptive offset (SAO) is applied for reducing sample distortion and attenuating ringing artifacts in both HEVC and VVC standards. The rate-distortion optimization process is used to select the best SAO parameter. It accounts for the majority of SAO complexity and determines the SAO filtering performance. Therefore, the rate-distortion cost calculation should be well handled to achieve both low cost and high coding performance. In this paper, we propose a simplified and optimized rate estimation algorithm based on the characteristics of SAO parameter syntax and entropy coding process. And we propose a hierarchical flow for rate-distortion cost calculation to further reduce the computational cost and storage cost for SAO mode decision hardware. The results show that the proposed algorithm achieves an average YUV loss of -0.10%, and the proposed SAO mode decision hardware architecture can be implemented by only 21.8k gates using TSMC 65nm process under 400 MHz.

关键词： Video coding Costs Rate-distortion Estimation computer architecture Syntactics Logic gates Hardware Entropy coding Standards

来源：评论

学校读者我要写书评

暂无评论

Exploring the use of deep learning in task-flexible ILC

arXiv

引用

arXiv 2023年

作者： Vinjarapu, Anantha Sai Hariharan Broens, Yorick Butler, Hans Tóth, Roland The Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands The Systems and Control Laboratory Institute for Computer Science and Control Hungary Asml Veldhoven Netherlands

Growing demands in today's industry results in increasingly stringent performance and throughput specifications. For accurate positioning of high-precision motion systems, feedforward control plays a crucial role. Nonetheless, conventional model-based feedforward approaches are no longer sufficient to satisfy the challenging performance requirements. An attractive method for systems with repetitive motion tasks is iterative learning control (ILC) due to its superior performance. However, for systems with non-repetitive motion tasks, ILC is generally not applicable, despite of some recent promising advances. In this paper, we aim to explore the use of deep learning to address the task flexibility constraint of ILC. For this purpose, a novel Task Analogy based Imitation Learning (TAIL)-ILC approach is developed. To benchmark the performance of the proposed approach, a simulation study is presented which compares the TAIL-ILC to classical model-based feedforward strategies and existing learning-based approaches, such as neural network based feedforward *** Codes 37M15 © 2023, CC BY.

关键词： Feedforward control

来源：评论

学校读者我要写书评

暂无评论

Boolean matrix compressed sensing

Boolean matrix compressed sensing

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liu, Qiang Soleymani, Mahdi Mahdavifar, Hessam National Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China Halıcıoğlu Data Science Institute University of California La Jolla San DiegoCA92093 United States Department of Electrical and Computer Engineering Northeastern University BostonMA02115 United States

ISBN: (纸本)9798350368741

In real-world datasets, leveraging the low-rank and sparsity properties enables developing efficient algorithms across a diverse array of data-related tasks, including compression, compressed sensing, matrix completion, etc. Notably, these two properties often coexist in certain real-world datasets, especially in Boolean datasets and quantized real-valued datasets. To harness the advantages of low-rank and sparsity simultaneously, we adopt a technique inspired by compressed sensing and Boolean matrix completion. Our approach entails compressing a low-rank sparse Boolean matrix by performing inner product operations with a randomly generated Boolean matrix. We then propose a decoding algorithms based on message-passing techniques to recover the original matrix. Our experiments demonstrate superior recovery performance of our proposed algorithms compared to Boolean matrix completion, with equal measurement requirements. © 2025 IEEE.

关键词： Belief Propagation Boolean Matrix Compressed Sensing Matrix Completion

来源：评论

学校读者我要写书评

暂无评论

In-situ manipulation of wireless link with reinforcement-learningdriven programmable metasurface in indoor environment

引用

Journal of Information and Intelligence 2023年第3期1卷 217-227页

作者： Jiawen Xu Rong Zhang Jie Ma Hanting Zhao Lianlin Li School of Electronic Engineering and Computer Science Peking UniversityBeijing 100871China State Key Laboratory of Advanced Optical Communication Systems and Networks School of ElectronicsPeking UniversityBeijing 100871China

It is of great importance to control flexibly wireless links in the modern society,especially with the advent of the Internet of Things(IoT),fifth-generation communication(5G),and ***,we have witnessed that programmable metasurface(PM)or reconfigurable intelligent surface(RIS)has become a key enabling technology for manipulating flexibly the wireless link;however,one fundamental but challenging issue is to online design the PM's control sequence in a complicated wireless environment,such as the real-world indoor ***,we propose a reinforcement learning(RL)approach to online control of the PM and thus in-situ improve the quality of the underline wireless *** designed an inexpensive one-bit PM working at around 2.442 GHz and developed associated RL algorithms,and demonstrated experimentally that it is capable of enhancing the quality of commodity wireless link by a factor of about 10 dB and beyond in multiple scenarios,even if the wireless transmitter is in the glancing angle of the PM in the realworld indoor ***,we also prove that our RL algorithm can be extended to improve the wireless signals of receivers in dual-receiver *** faithfully expect that the presented technique could hold important potentials in future wireless communication,smart homes,and many other fields.

关键词： Programmable metasurface Reconfigurable intelligent surface Reinforcement learning Wireless link

来源：评论

学校读者我要写书评

暂无评论

Disentangling Local and Global Information for Light Field Depth Estimation

Disentangling Local and Global Information for Light Field D...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Yang, Xueting Deng, Junli Chen, Rongshan Cong, Ruixuan Ke, Wei Sheng, Hao Communication University of China School of Information and Communication Engineering Beijing100024 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang Hangzhou Innovation Institute Yuhang Xixi Octagon City Hangzhou310023 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

ISBN: (纸本)9798350302493

Accurate depth estimation from light field images is essential for various applications. Deep learning-based techniques have shown great potential in addressing this problem while still face challenges such as sensitivity to occlusions and difficulties in handling untextured areas. To overcome these limitations, we propose a novel approach that utilizes both local and global features in the cost volume for depth estimation. Specifically, our hybrid cost volume network consists of two complementary sub-modules: a 2D ContextNet for global context information and a matching cost volume for local feature information. We also introduce an occlusion-aware loss that accounts for occlusion areas to improve depth estimation quality. We demonstrate the effectiveness of our approach on the UrbanLF and HCInew datasets, showing significant improvements over existing methods, especially in occluded and untextured regions. Our method disentangles local feature and global semantic information explicitly, reducing the occlusion and untextured area reconstruction error and improving the accuracy of depth estimation. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning

arXiv

引用

arXiv 2023年

作者： Zhao, Yifan Zhang, Tong Li, Jia Tian, Yonghong The School of Computer Science Peking University Beijing100871 China The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The Pengcheng Laboratory Shenzhen518055 China The School of Electronic and Computer Engineering Peking University Shenzhen Granduate School Shenzhen518055 China

Few-shot learning aims to recognize novel queries with limited support samples by learning from base knowledge. Recent progress in this setting assumes that the base knowledge and novel query samples are distributed in the same domains, which are usually infeasible for realistic applications. Toward this issue, we propose to address the cross-domain few-shot learning problem where only extremely few samples are available in target domains. Under this realistic setting, we focus on the fast adaptation capability of meta-learners by proposing an effective dual adaptive representation alignment approach. In our approach, a prototypical feature alignment is first proposed to recalibrate support instances as prototypes and reproject these prototypes with a differentiable closed-form solution. Therefore feature spaces of learned knowledge can be adaptively transformed to query spaces by the cross-instance and cross-prototype relations. Besides the feature alignment, we further present a normalized distribution alignment module, which exploits prior statistics of query samples for solving the covariant shifts among the support and query samples. With these two modules, a progressive meta-learning framework is constructed to perform the fast adaptation with extremely few-shot samples while maintaining its generalization capabilities. Experimental evidence demonstrates our approach achieves new state-of-the-art results on 4 CDFSL benchmarks and 4 fine-grained cross-domain benchmarks. Copyright © 2023, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Skin-like cryogel electronics from suppressed-freezing tuned polymer amorphization

引用

Nature Communications 2023年第1期14卷 1-10页

作者： Zhang, Xiansheng Yan, Hongwei Xu, Chongzhi Dong, Xia Wang, Yu Fu, Aiping Li, Hao Lee, Jin Yong Zhang, Sheng Ni, Jiahua Gao, Min Wang, Jing Yu, Jinpeng Ge, Shuzhi Sam Jin, Ming Liang Wang, Lili Xia, Yanzhi State Key Laboratory of Bio-Fibers and Eco-Textiles College of Textiles and Clothing Qingdao University Qingdao 266071 China Institute for Future Shandong Key Laboratory of Industrial Control Technology School of Automation Qingdao University Qingdao 266071 China College of Materials Science and Engineering Qingdao University Qingdao 266071 China CAS Key Laboratory of Engineering Plastics Institute of Chemistry Chinese Academy of Sciences Beijing 100190 China Department of Chemistry SungKyunKwan University Suwon 16419 South Korea State Key Laboratory of Fluid Power and Mechatronic Systems College of Mechanical Engineering Zhejiang University Hangzhou 310027 China College of Biological Science and Medical Engineering Donghua University Shanghai 201620 China Institute of Environmental Engineering ETH Zürich Zürich 8093 Switzerland Department of Electrical and Computer Engineering National University of Singapore Singapore 117576 Singapore

The sole situation of semi-crystalline structure induced single performance remarkably limits the green cryogels in the application of soft devices due to uncontrolled freezing field. Here, a facile strategy for achieving multifunctionality of cryogels is proposed using total amorphization of polymer. Through precisely lowering the freezing point of precursor solutions with an antifreezing salt, the suppressed growth of ice is achieved, creating an unusually weak and homogenous aggregation of polymer chains upon freezing, thereby realizing the tunable amorphization of polymer and the coexistence of free and hydrogen bonding hydroxyl groups. Such multi-scale microstructures trigger the integrated properties of tissue-like ultrasoftness (Young’s modulus <10 kPa) yet stretchability, high transparency (~92%), self-adhesion, and instantaneous self-healing (<0.3 s) for cryogels, along with superior ionic-conductivity, antifreezing (−58 °C) and water-retention abilities, pushing the development of skin-like cryogel electronics. These concepts open an attractive branch for cryogels that adopt regulated crystallization behavior for on-demand functionalities. © 2023, Springer Nature Limited.

关键词： Gels and hydrogels Polymers

来源：评论

学校读者我要写书评

暂无评论

HealthEdge: A Machine Learning-Based Smart Healthcare Framework for Prediction of Type 2 Diabetes in an Integrated IoT, Edge, and Cloud Computing System 14

HealthEdge: A Machine Learning-Based Smart Healthcare Framew...

引用

14th International Conference on Ambient systems, Networks and Technologies Networks, ANT 2023 and The 6th International Conference on Emerging Data and Industry 4.0, EDI40 2023

作者： Hennebelle, Alain Materwala, Huned Ismail, Leila Melbourne Australia Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates National Water and Energy Center United Arab Emirates University United Arab Emirates Lab School of Computing and Information Systems The University of Melbourne Australia

Diabetes Mellitus has no permanent cure to date and is one of the leading causes of death globally. The alarming increase in diabetes calls for the need to take precautionary measures to avoid/predict the occurrence of diabetes. This paper proposes HealthEdge, a machine learning-based smart healthcare framework for type 2 diabetes prediction in an integrated IoT-edge-cloud computing system. Numerical experiments and comparative analysis were carried out between the two most used machine learning algorithms in the literature, Random Forest (RF) and Logistic Regression (LR), using two real-life diabetes datasets. The results show that RF predicts diabetes with 6% more accuracy on average compared to LR. © 2023 Elsevier B.V.. All rights reserved.

关键词： Edge computing

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：