检索结果-内蒙古大学图书馆

2024 Photonics and Electromagnetics Research symposium, PIERS 2024

作者： He, Sheng Zhang, Gang Southwest University of Science and Technology China

ISBN: (纸本)9798350375909

Geodetic electromagnetic methods have wide applications in geophysical exploration, but there are still some challenges for large-scale and complex geodetic electromagnetic data processing and interpretation. This paper introduces a Python-based open-source software library, resistics, which achieves significant optimization of the data processing effect through its application in geodetic electromagnetic data processing. There are many limitations in the traditional methods of geodetic electromagnetic data processing, including problems of data import, correction, noise suppression and model matching. The main functions and features of the resistics library, i.e., multi-threaded processing, efficient data import and pre-processing, and automated parameter optimization, can optimize data processing. These features make the resistics library perform well in large-scale geodetic electromagnetic data processing, and can significantly improve data processing efficiency and accuracy. In order to verify the advantages of the resistics library in geodetic electromagnetic data processing, we selected the geodetic electromagnetic data from the Xian Shui River area for experiments, and processed the data using the resistics library. The results show that, compared with the traditional method, the resistics library can process the data and model matching more quickly and accurately, and improve the accuracy of the data and obtain more reliable results. Not only that, in the process of using the resistics library to process data, it also realizes the visualization of data processing, and can be adjusted and optimized for the measured bad data to get more reliable data. In the processing of the Xian Shui river data, the use of the resistics library can effectively suppress the noise, extract the effective signals, and accurately restore the underground structure. © 2024 ieee.

关键词： data assimilation

来源：评论

学校读者我要写书评

暂无评论

Learning to Answer Visual Questions From Web Videos

引用

ieee TRANSACTIONS ON PATTERN analysis AND MACHINE INTELLIGENCE 2025年第5期47卷 3202-3218页

作者： Yang, Antoine Miech, Antoine Sivic, Josef Laptev, Ivan Schmid, Cordelia PSL Res Univ CNRS Inria Paris & Dept informat ENS F-75005 Paris France DeepMind London N1C 4AG England Czech Tech Univ Czech Inst Informat Robot & Cybernet Prague 16636 Czech Republic

Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and prevents scalability. In this work, we propose to avoid manual annotation and generate a large-scale training dataset for video question answering making use of automatic cross-modal supervision. We leverage a question generation transformer trained on text data and use it to generate question-answer pairs from transcribed video narrations. Given narrated videos, we then automatically generate the HowToVQA69M dataset with 69M video-question-answer triplets. To handle the open vocabulary of diverse answers in this dataset, we propose a training procedure based on a contrastive loss between a video-question multi-modal transformer and an answer transformer. We introduce the zero-shot VideoQA task and the VideoQA feature probe evaluation setting and show excellent results, in particular for rare answers. Furthermore, our method achieves competitive results on MSRVTT-QA, ActivityNet-QA, MSVD-QA and How2QA datasets. We also show that our VideoQA dataset generation approach generalizes to another source of web video and text data. We use our method to generate the WebVidVQA3M dataset from the WebVid dataset, i.e., videos with alt-text annotations, and show its benefits for training VideoQA models. Finally, for a detailed evaluation we introduce iVQA, a new VideoQA dataset with reduced language bias and high-quality manual annotations. Code, datasets and trained models are available on our project webpage (https://***/***).

关键词： Training visualization Annotations Zero shot learning Manuals Transformers Question answering (information retrieval) Question generation Probes Videos Video question answering cross-modal supervision question generation zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Predictive analysis of student enrollment on a faculty base on innovation research 23

Predictive analysis of student enrollment on a faculty base ...

引用

23rd International symposium INFOTEH-JAHORINA (INFOTEH)

作者： Lojic, Ana Kevric, Jasmin Jukic, Samed Int Burch Univ Dept Informat Technol Sarajevo Bosnia & Herceg

ISBN: (纸本)9798350329940;9798350307368

In research aimed at determining the level of interest of high school students in enrolling in colleges, predictive analysis models and comparisons are rarely applied during the classification and processing of various data. All of this leads to significant fluctuations in college admissions, where certain schools are unable to admit a large number of students who show interest in a specific field. On the other hand, high school students lose interest in certain schools, leading to the discontinuation of specific directions essential for today's job market needs. Institutions largely fail to conduct a comparison and linkage of teaching and non-teaching activities when analyzing the talents and interests of high school students from different fields. The goal of this paper is to use programming language classifiers to predict student enrollments in colleges based on the results students demonstrate during regular attendance in high schools through participation in innovation fairs.

关键词： data Mining Classification Prediction Innovation Random Forest Classifier Introduction

来源：评论

学校读者我要写书评

暂无评论

An RGB Color Image Steganography Scheme by Binary Lower Triangular Matrix

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第7期24卷 6865-6873页

作者： Prasad, Shiv Pal, Arup Kumar Mukherjee, Soumya Indian Sch Mines Indian Inst Technol Dept Comp Sci & Engn Dhanbad 826004 Jharkhand India

Steganography is an area where researchers focus on how to develop novel hiding techniques that are aided by the mathematical or computational model. In order to conceal the secret bits in a cover image, the imperceptible property and embedding payload capacity must be maintained. In most of the developed methods, some selective least significant bits (LSBs) of each pixel of the cover image is modified to hide the data which may lead to substantial distortion in the stego-image especially when the payload size is large. Therefore, to attain the trade-off between payload capacity and image quality, the authors have devised a binary lower triangular matrix-based secret message embedding process in which data can be hidden in the color pixel. In this secret message embedding process, the secret data is embedded aided by the binary lower triangular matrix. The formulated mathematical model for the secret message embedding process has ensured a secure embedding technique with reduced aberration on the stego-image. The proposed steganography scheme is preserving significant visual quality while emphasizing the security aspect by adopting an indirect data-hiding mechanism in contrast to the conventional mechanism. Furthermore, for the betterment of the visual properties of the stego-image, we have generically extended the formulation and tested it to check the visual quality. The empirical results of the proposed steganography scheme depict outcomes satisfactorily for the RGB color images. Researchers can explore and apply this novel data-hiding scheme in different data communication applications.

关键词： Steganography Color Image color analysis visualization Payloads Streaming media Genetic algorithms Color image steganography covert communication matrix-based data hiding stego-image

来源：评论

学校读者我要写书评

暂无评论

An Enriched visualization Tool based on Google Maps for Water Distribution Networks in Smart Cities 27

An Enriched Visualization Tool based on Google Maps for Wate...

引用

ieee symposium on Computers and Communications (ISCC)

作者： Lukaj, Valeria Martella, Francesco Celesti, Antonio Fazio, Maria Villari, Massimo Univ Messina Dept MIFT Messina Italy ALMA Digit SRL Messina Italy Grp Nazl Calcolo Sci GNCS INdAM Rome Italy Univ Messina Engn Dept Messina Italy

ISBN: (纸本)9781665497923

The innovation process for the management of a Water Distribution Network (WDN) in a Smart City starts from an efficient digital representation of the network itself. This paper presents a new visualization tool for WDN that overcomes current challenges and provides water companies with useful managing information. Existing visualization tools are self-contained systems that work independently from other visualization software and do not provide real-time analysis of the pipes and water flow status in the WDN. Using digital maps such as Google Maps it is possible to extend the traditional digital representation of the WDN based on EPANET software. Moreover, the WDN representation can be enriched with localized information (e.g. roads or buildings superimposed on the WDN), that is useful for planning maintenance and structural services. In presence of a WDN equipped with sensors and flowmeters, the proposed tool can be used for optimized visualization of the flow rate and the condition of the pipes in real-time. For these reasons, this tool can be a powerful instrument to help technicians quickly identify problems in the WDN. In this work, we used synthetic data generation techniques to obtain a data-set of values that updated over time. Finally, to evaluate the designed solution, we implemented the proposed visualization tool and performed some experiments to test its effectiveness.

关键词： Water Distribution Network WDNs Epanet data visualization Google maps FIWARE Smart City

来源：评论

学校读者我要写书评

暂无评论

Foundation Models Defining a New Era in Vision: A Survey and Outlook

引用

ieee TRANSACTIONS ON PATTERN analysis AND MACHINE INTELLIGENCE 2025年第4期47卷 2245-2264页

作者： Awais, Muhammad Naseer, Muzammal Khan, Salman Anwer, Rao Muhammad Cholakkal, Hisham Shah, Mubarak Yang, Ming-Hsuan Khan, Fahad Shahbaz MBZ Univ AI Abu Dhabi U Arab Emirates Georgia Inst Technol Comp Sci Dept Atlanta GA 30332 USA Khalifa Univ Comp Sci Dept Abu Dhabi U Arab Emirates Khalifa Univ Ctr Secure Cyber Phys Secur Syst Abu Dhabi U Arab Emirates Australian Natl Univ CECS Canberra ACT 0200 Australia Univ Cent Florida Ctr Res Comp Vis Orlando FL 32816 USA Univ Calif Merced Merced CA 95344 USA Yonsei Univ Seoul 03722 South Korea Google Res Mountain View CA 94043 USA Linkoping Univ Comp Vis Lab S-58183 Linkoping Sweden

Vision systems that see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The complex relations between objects and their locations, ambiguities, and variations in the real-world environment can be better described in human language, naturally governed by grammatical rules and other modalities such as audio and depth. The models learned to bridge the gap between such modalities and large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. These models are referred to as foundation models. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions. In this survey, we provide a comprehensive review of such emerging foundation models, including typical architecture designs to combine different modalities (vision, text, audio, etc.), training objectives (contrastive, generative), pre-training datasets, fine-tuning mechanisms, and the common prompting patterns;textual, visual, and heterogeneous. We discuss the open challenges and research directions for foundation models in computer vision, including difficulties in their evaluations and benchmarking, gaps in their real-world understanding, limitations of contextual understanding, biases, vulnerability to adversarial attacks, and interpretability issues. We review recent developments in this field, covering a wide range of applications of foundation models systematically and comprehensively.

关键词： Adaptation models Computational modeling Foundation models data models Surveys visualization Reviews Computer vision Computer architecture Context modeling Contrastive learning language and vision large language models masked modeling self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Event Graph Guided Compositional Spatial--Temporal Reasoning for Video Question Answering

引用

ieee TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 1109-1121页

作者： Bai, Ziyi Wang, Ruiping Gao, Difei Chen, Xilin Chinese Acad Sci Key Lab Intelligent Informat Proc Inst Comp Technol Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Video question answering (VideoQA) is challenging since it requires the model to extract and combine multi-level visual concepts from local objects to global actions from complex events for compositional reasoning. Existing works represent the video with fixed-duration clip features that make the model struggle in capturing the crucial concepts in multiple granularities. To overcome this shortcoming, we propose to represent the video with an Event Graph in a hierarchical structure whose nodes correspond to visual concepts of different levels (object, relation, scene and action) and edges indicate their spatial-temporal relationships. We further propose a Hierarchical S patial- Temporal Transformer (HSTT) which takes nodes from the graph as visual input to realize compositional reasoning guided by the event graph. To fully exploit the spatial-temporal context delivered from the graph structure, on the one hand, we encode the nodes in the order of their semantic hierarchy (depth) and occurrence time (breadth) with our improved graph search algorithm;On the other hand, we introduce edge-guided attention to combine the spatial-temporal context among nodes according to their edge connections. HSTT then performs QA by cross-modal interactions guaranteed by the hierarchical correspondence between the multi-level event graph and the cross-level question. Experiments on the recent challenging AGQA and STAR datasets show that the proposed method clearly outperforms the existing VideoQA models by a large margin, including those pre-trained with large-scale external data.

关键词： visualization Cognition Transformers Semantics Feature extraction Context modeling Task analysis VideoQA video representation transformer spatial-temporal reasoning compositional reasoning

来源：评论

学校读者我要写书评

暂无评论

MAD-Max Beyond Single-Node: Enabling large Machine Learning Model Acceleration on Distributed Systems 51

MAD-Max Beyond Single-Node: Enabling Large Machine Learning ...

引用

ACM/ieee 51st Annual International symposium on Computer Architecture (ISCA)

作者： Hsia, Samuel Golden, Alicia Acun, Bilge Ardalani, Newsha DeVito, Zachary Wei, Gu-Yeon Brooks, David Wu, Carole-Jean FAIR Meta Menlo Pk CA 94025 USA Harvard Univ Cambridge MA 02138 USA

ISBN: (纸本)9798350326598;9798350326581

Training and deploying large-scale machine learning models is time-consuming, requires significant distributed computing infrastructures, and incurs high operational costs. Our analysis, grounded in real-world large model training on datacenter-scale infrastructures, reveals that 14 similar to 32% of all GPU hours are spent on communication with no overlapping computation. To minimize this outstanding communication latency and other inherent at-scale inefficiencies, we introduce an agile performance modeling framework, MAD-Max. This framework is designed to optimize parallelization strategies and facilitate hardware-software co-design opportunities. Through the application of MAD-Max to a suite of real-world large-scale ML models on state-of-the-art GPU clusters, we showcase potential throughput enhancements of up to 2.24x for pre-training and up to 5.27x for inference scenarios, respectively.

关键词： data Center Distributed Inference Distributed Training GPU Hardware-Software Co-Design Machine Learning Parallelization Performance Model Simulator

来源：评论

学校读者我要写书评

暂无评论

Distributed Path Compression for Piecewise Linear Morse-Smale Segmentations and Connected Components

Distributed Path Compression for Piecewise Linear Morse-Smal...

引用

ieee symposium on large data analysis and visualization (LDAV)

作者： Michael Will Jonas Lukasczyk Julien Tierny Christoph Garth RPTU Kaiserslautern-Landau CNRS and Sorbonne Université

ISBN: (数字)9798331516925

ISBN: (纸本)9798331516932

This paper describes the adaptation to a distributed computational setting of a well-scaling parallel algorithm for computing Morse-Smale segmentations based on path compression. Additionally, we extend the algorithm to efficiently compute connected components in distributed structured and unstructured grids, based either on the connectivity of the underlying mesh or a feature mask. Our implementation is seamlessly integrated with the distributed extension of the Topology ToolKit (TTK), ensuring robust performance and scalability. To demonstrate the practicality and efficiency of our algorithms, we conducted a series of scaling experiments on large-scale datasets, with sizes of up to 4096 3 vertices on up to 64 nodes and 768 cores.

关键词： data analysis Instruction sets Scalability data visualization Solids Topology Global communication Parallel algorithms Distributed computing Optimization

来源：评论

学校读者我要写书评

暂无评论

Uncertainty Quantification and Sensitivity analysis of Crosstalk in PCB Lines via the Combination of Machine Learning and Polynomial Chaos Expansion

Uncertainty Quantification and Sensitivity Analysis of Cross...

引用

Joint International symposium on Electromagnetic Compatibility, Signal & Power Integrity: EMC Japan/AsiaPacific International symposium on Electromagnetic Compatibility (EMC/APEMC)

作者： Manfredi, Paolo Trinchero, Riccardo Politecn Torino Dept Elect & Telecommun I-10129 Turin Italy

ISBN: (纸本)9784885523472;9798350349498

Manufacturing tolerances are becoming one of the major limitations to achieving high data rates in modern integrated circuits. Polynomial chaos expansion (PCE) recently became a popular alternative to classical Monte Carlo for efficient uncertainty quantification (UQ). Statistical moments and sensitivity information are analytically derived from the PCE coefficients. However, computing the model coefficients typically requires a large amount of data samples from possibly expensive design simulations. On the other hand, kernel-based machine learning methods were recently employed to create efficient surrogate models with a limited amount of training data. In this paper, we combine the kernel Gaussian process regression (GPR) method and the PCE. The former is used to surrogate the expensive simulator in the calculation of PCE coefficients via numerical integration. The use of GPR also allows obtaining confidence levels of the estimated PCE coefficients and the relative statistical information. The proposed hybrid PCE-GPR method is applied to UQ of maximum crosstalk in a PCB interconnect, for which higher accuracy with a very limited amount of data is obtained compared to state-of-the-art approaches.

关键词： Crosstalk Gaussian process Kriging machine learning polynomial chaos regression signal integrity surrogate modeling training transmission lines uncertainty quantification

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：