检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Goodge, Adam Ng, Wee Siong Hooi, Bryan Ng, See-Kiong A*STAR Singapore School of Computing National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

Foundation models have revolutionized artificial intelligence, setting new benchmarks in performance and enabling transformative capabilities across a wide range of vision and language tasks. However, despite the prevalence of spatio-temporal data in critical domains such as transportation, public health, and environmental monitoring, spatio-temporal foundation models (STFMs) have not yet achieved comparable success. In this paper, we articulate a vision for the future of STFMs, outlining their essential characteristics and the generalization capabilities necessary for broad applicability. We critically assess the current state of research, identifying gaps relative to these ideal traits, and highlight key challenges that impede their progress. Finally, we explore potential opportunities and directions to advance research towards effective and broadly applicable STFMs. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedSM: A Practical Federated Shared Mobility System 50th

FedSM: A Practical Federated Shared Mobility System

引用

50th International Conference on Very Large data Bases, VLDB 2024

作者： Wei, Shuyue Zhang, Yuanyuan Zhou, Zimu Zhang, Tianlong Xu, Ke SKLCCSE Lab FBPC Beijing Advanced Innovation Center Beihang University China North China Institute of Computing Technology China School of Data Science City University of Hong Kong Hong Kong SKLCCSE Lab Beihang University China

Shared mobility leverages under-utilized vehicles to offer on-demand transport services by sharing vehicles among users. It strives to match supply with demand via a series of data-intensive opera- tions such as supply prediction and task assignment. However, its full potential is often compromised in practice as most shared mobility platforms operate in isolation, leading to sub-optimal re- source utilization. In this demonstration, we advocate a federated approach to shared mobility, which enhances its effectiveness by enabling optimizations across platforms while retaining their au- tonomy. We develop privacy-preserving operators and incentive mechanisms dedicated to supply prediction and task assignment in shared mobility and implement generic interfaces that support diverse prediction and assignment algorithms. We showcase the shared mobility system with real-world ride-hailing applications. © 2024, VLDB Endowment. All rights reserved.

关键词： Arctic vehicles

来源：评论

学校读者我要写书评

暂无评论

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning 7

Tensor Graph Convolutional Network for Dynamic Graph Represe...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Wang, Ling Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application For Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China College of Computer and Information Science Southwest University Chongqing400715 China

ISBN: (纸本)9798350363173

Dynamic graphs (DG) represent evolving interactions between entities in various real-world scenarios. Many existing DG representation learning models employ a combination of graph convolutional networks and sequence neural networks to capture spatial-temporal dependencies. However, this hybrid approach often fails to effectively capture the spatial-temporal continuity inherent in DGs. In this paper, we propose a novel approach called the Tensor Graph Convolutional Network (TGCN) to learn DG representations within a unified convolution framework based on tensor products. Our approach is founded on two key principles: (a) representing DG information in tensor form, and (b) leveraging tensor product operations to design a graph convolutional network that simultaneously models spatial and temporal features. Experimental results on three real-world DG datasets demonstrate that our proposed model achieves state-of-the-art performance. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Decreasing Word Error Rates in Paragraph Handwritten Text Recognition with Synthetic data

Decreasing Word Error Rates in Paragraph Handwritten Text Re...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ernest Yu-Kai Chew Adams Wai-Kin Kong Lim Joo-Hwee College of Computing and Data Science Nanyang Technological University Singapore Singapore Institute for Infocomm Research A*STAR Singapore Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Handwritten Text Recognition (HTR) faces a persistent challenge with the scarcity of data at the paragraph level, arising from the difficulty of acquiring diverse, cost-efficient, and cleanly labeled datasets for training. As such, works in HTR leverage segmentation, regularization techniques, and language modeling to excel in a low-data environment. While synthetic generation methods gain traction on the word and line-level recognition, this success has not translated to the paragraph level. Hence, our work seeks to mimic the nuances of paragraph-level text images with a custom synthetic data engine using Wikipedia texts. Experiments show that by using our synthetic dataset in tandem with a simple encoder-decoder Transformer, we can achieve the best Word Error Rate (WER) amongst the state-of-the-art methods for handwriting recognition on the IAM dataset. Additionally, we show the model pretrained on English texts can also recognize French and German texts with minimal finetuning.

关键词： Training Handwriting recognition Translation Text recognition Error analysis Speech recognition Transformers Speech processing Engines Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Sustainable Energy Efficient Routing Protocol using Chimp algorithm and SOM for Underwater Wireless Sensor Networks

Sustainable Energy Efficient Routing Protocol using Chimp al...

引用

2023 International Conference on Recent Advances in science and Engineering Technology, ICRASET 2023

作者： Philip Paul Arunodhayam, T. Vadde, Akhil Raj Kumar, Thimmampali Prasanna Silas, Salaja Gandu, Shalem Preetham Harshith Kumar, Chamarti Karunya Institute of Technology and Sciences Dept. of Computer Science and Engineering Coimbatore India College of Engineering and Computing George Mason University Data Analytics Engineering VA Fairfax22030 United States

ISBN: (纸本)9798350306927

Underwater Wireless Sensor Networks (UWSNs) are increasingly being used for various applications, such as environmental monitoring, underwater exploration, and oceanographic research. protocols that consume less energy for underwater wireless sensor networks (UWSNs) are still a difficult undertaking because of the harsh conditions present underwater and the restricted battery capacity of the sensor nodes. This research paper proposes an optimized multi-Hop routing protocol using Chimp Optimization and Self-Organizing Map (SOM). The proposed technique is compared with three popular routing protocols - AODV, DSDV, and DSR in terms of network lifetime and packet delivery ratio. Chimp Optimization algorithm as well as SOM are used to improve network performance. The findings indicate that the put-forward technique exceeds the performance of existing routing protocols, as it increases network lifetime, PDR and PLR while decreasing packet loss ratio. The network lifetime of the put-forward technique is 1039.42 seconds, which is higher than AODV, DSDV, and DSR. Similarly, the PDR of the proposed technique is 97.38%, which is comparatively higher than the three routing protocols. Moreover, the PLR of the proposed technique is 2.62%, which is much lower than AODV, DSDV, and DSR. The proposed technique based on Chimp Optimization and SOM can effectively optimize the multi-Hop routing protocol in underwater wireless sensor networks to achieve sustainable energy efficiency, thus providing important insights for researchers and practitioners to enhance the performance of underwater wireless sensor networks. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Sequential modeling of temporal timbre series for popular music sub-genres analyses using deep bidirectional encoder representations from transformers 150

Sequential modeling of temporal timbre series for popular mu...

引用

150th Audio Engineering Society Convention, AES 2021

作者： Geng, Shijia Ren, Gang Pan, Xu Zysman, Joel Ogihara, Mistu Institute for Data Science and Computing University of Miami Department of Computer Science University of Miami

ISBN: (纸本)9781713830672

The timbral analysis from spectrographic features of popular music sub-genres (or micro-genres) presents unique challenges to the field of the computational auditory scene analysis, which is caused by the adjacencies among sub-genres and the complex sonic scenes from sophisticated musical textures and production processes. This paper presents a timbral modeling tool based on a modified deep learning natural language processing model. It treats the time frames in spectrograms as words in natural languages to explore the temporal dependencies. The modeling performance metrics obtained from the fine-tuned classifier of the modified Deep Bidirectional Encoder Representations from Transformers (BERT) model show strong semantic modeling performances with different temporal settings. Designed as an automatic feature engineering tool, the proposed framework provides a unique solution to the semantic modeling and representation tasks for objectively understanding of subtle musical timbral patterns from highly similar musical genres. © 2021 150th Audio Engineering Society Convention, AES 2021. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

data-faithful feature attribution: mitigating unobservable confounders via instrumental variables 24

Data-faithful feature attribution: mitigating unobservable c...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Qiheng Sun Haocheng Xia Jinfei Liu Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Siebel School of Computing and Data Science University of Illinois Urbana-Champaign

ISBN: (纸本)9798331314385

The state-of-the-art feature attribution methods often neglect the influence of unobservable confounders, posing a risk of misinterpretation, especially when it is crucial for the interpretation to remain faithful to the data. To counteract this, we propose a new approach, data-faithful feature attribution, which trains a confounder-free model using instrumental variables. The cluttered effects of unobservable confounders in a model trained as such are decoupled from input features, thereby aligning the output of the model with the contribution of input features to the target feature in the data generation. Furthermore, feature attribution results produced by our method are more robust when focusing on attributions from the perspective of data generation. Our experiments on both synthetic and real-world datasets demonstrate the effectiveness of our approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study of Raising Students Level of Geometric Understanding with the Aid of Technology 23

Study of Raising Students Level of Geometric Understanding w...

引用

7th International Conference on Education and Multimedia Technology, ICEMT 2023

作者： Chen, Yuanhua Rao, Ailing Xu, Zhonglan Zhang, Chuanjun Guan, Hao Institute of Computing Science and Technology Guangzhou University China The Second Primary School of Zixi The Second Primary School of Zixi China School of Mathematics and Big Data Guizhou Education University Guiyang China

ISBN: (纸本)9798400709142

The ultimate goal of learning mathematics is mathematical understanding, which is why it is so important in mathematics education. It is critical to categorize the degrees of geometric understanding because geometry is both an important and challenging subject in secondary school mathematics. In this essay, the meaning of the term "geometric understanding"is defined along with the concept of "mathematical understanding"and related theories. The level of geometric understanding is divided into five categories: intuition, abstraction, connection, inventing, and civilizing. The geometry teaching strategy supported by NetPad is suggested to foster students' geometric understanding. It consists of five parts: Creating Situations and Posing Questions - Imagining, Exploring and Abstracting, Analyzing - Transferring and Connecting - Varying and Innovating - Appreciating Geometry and Penetrating Culture. Through examples, the precise operational procedure of the teaching strategy based on NetPad to advance students' geometric understanding is also covered. © 2023 ACM.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Situational Scene Graph for Structured Human-Centric Situation Understanding

Situational Scene Graph for Structured Human-Centric Situati...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Chinthani Sugandhika Chen Li Deepu Rajan Basura Fernando College of Computing and Data Science Nanyang Technological University Singapore Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High-Performance Computing Agency for Science Technology and Research Singapore

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Graph based representation has been widely used in modelling spatio-temporal relationships in video understanding. Although effective, existing graph-based approaches focus on capturing the human-object relationships while ignoring fine-grained semantic properties of the action components. These semantic properties are crucial for understanding the current situation, such as where does the action takes place, what tools are used and functional properties of the objects. In this work, we propose a graph-based representation called Situational Scene Graph (SSG) to encode both human-object relationships and the corresponding semantic properties. The semantic details are represented as predefined roles and values inspired by situation frame, which is originally designed to represent a single action. Based on our proposed representation, we introduce the task of situational scene graph generation and propose a multi-stage pipeline Interactive and Complementary Network (InComNet) to address the task. Given that the existing datasets are not applicable to the task, we further introduce a SSG dataset whose annotations consist of semantic role-value frames for human, objects and verb predicates of human-object relations. Finally, we demonstrate the effectiveness of our proposed SSG representation by testing on different downstream tasks. Experimental results show that the unified representation can not only benefit predicate classification and semantic role-value classification, but also benefit reasoning tasks on human-centric situation understanding. Code and data are available at https://***/LUNAProject22/SSG.

关键词： Computer vision Codes Annotations Semantics Pipelines Semisupervised learning Cognition Testing

来源：评论

学校读者我要写书评

暂无评论

Uniform-in-N log-Sobolev inequality for the mean-field Langevin dynamics with convex energy

arXiv

引用

arXiv 2024年

作者： Chewi, Sinho Nitanda, Atsushi Zhang, Matthew S. Department of Statistics and Data Science Yale University United States College of Computing and Data Science Nanyang Technological University Singapore Department of Computer Science University of Toronto Vector Institute Canada

We establish a log-Sobolev inequality for the stationary distribution of mean-field Langevin dynamics with a constant that is independent of the number of particles N. Our proof proceeds by establishing the existence of a Lipschitz transport map from the standard Gaussian measure via the reverse heat flow of Kim and Milman. © 2024, CC BY.

关键词： Heat transfer

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：