检索结果-内蒙古大学图书馆

graph-based methods for Multimodal Indoor Activity Recognition: A Comprehensive Survey

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2025年

作者： Javadi, Saeedeh Riboni, Daniele Borzi, Luigi Zolfaghari, Samaneh Polytech Univ Turin Dept Comp & Control Engn I-10129 Turin Italy Univ Cagliari Dept Math & Comp Sci I-09124 Cagliari Italy Malardalen Univ Sch Innovat Design & Engn S-72123 Vasteras Sweden

This survey article explores graph-based approaches to multimodal human activity recognition in indoor environments, emphasizing their relevance to advancing multimodal representation and reasoning. With the growing importance of integrating diverse data sources such as sensor events, contextual information, and spatial data, effective human activity recognition methods are essential for applications in smart homes, digital health, and more. We review various graph-based techniques, highlighting their strengths in encoding complex relationships and improving activity recognition performance. Furthermore, we discuss the computational efficiencies and generalization capabilities of these methods across different environments. By providing a comprehensive overview of the state-of-the-art in graph-based human activity recognition, this article aims to contribute to the development of more accurate, interpretable, and robust multimodal systems for understanding human activities in indoor settings.

关键词： graph-based methods human activity recognition indoor environments interpretable models multimodal learning reasoning techniques sensor data graph-based methods human activity recognition indoor environments interpretable models multimodal learning reasoning techniques sensor data

来源：评论

学校读者我要写书评

暂无评论

Automatic Keyphrase Extraction using graph-based methods 18

Automatic Keyphrase Extraction using Graph-based Methods

引用

33rd Annual ACM Symposium on Applied Computing (ACM SAC)

作者： Mothe, Josiane Ramiandrisoa, Faneva Rasolomanana, Michael Univ Toulouse EPSE CNRS IRITUMR5505 Toulouse France Univ Toulouse CNRS IRIT UMR5505 Toulouse France Univ Antananarivo Antananarivo Madagascar

This paper analyses various unsupervised automatic keyphrase extraction methods based on graphs as well as the impact of word embedding. Evaluation is made on three datasets. We show that there is no differences when ... 详细信息

ISBN: (纸本)9781450351911

关键词： Information systems Information retrieval Automatic keyphrase extraction graph-based methods Word-embedding Word2Vec

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Visual and Textual Information Fusion in CBMIR Using graph-based methods

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2015年第2期33卷 9-9页

作者： Ah-Pine, Julien Csurka, Gabriela Clinchant, Stephane Univ Lyon ERIC Lab F-69676 Bron France Xerox Res Ctr Europe F-38240 Meylan France

Multimedia collections are more than ever growing in size and diversity. Effective multimedia retrieval systems are thus critical to access these datasets from the end-user perspective and in a scalable way. We are interested in repositories of image/text multimedia objects and we study multimodal information fusion techniques in the context of content-based multimedia information retrieval. We focus on graph-based methods, which have proven to provide state-of-the-art performances. We particularly examine two such methods: cross-media similarities and random-walk-based scores. From a theoretical viewpoint, we propose a unifying graph-based framework, which encompasses the two aforementioned approaches. Our proposal allows us to highlight the core features one should consider when using a graph-based technique for the combination of visual and textual information. We compare cross-media and random-walk-based results using three different real-world datasets. From a practical standpoint, our extended empirical analyses allow us to provide insights and guidelines about the use of graph-based methods for multimodal information fusion in content-based multimedia information retrieval.

关键词： Algorithms Theory Content-based multimedia information retrieval information fusion graph-based methods cross-media similarity random walk Visual reranking

来源：评论

学校读者我要写书评

暂无评论

A survey on graph-based methods for similarity searches in metric spaces

引用

INFORMATION SYSTEMS 2021年 95卷 101507-101507页

作者： Shimomura, Larissa C. Oyamada, Rafael Seidi Vieira, Marcos R. Kaster, Daniel S. Eindhoven Univ Technol Eindhoven Netherlands Univ Londrina Londrina Parana Brazil Google Mountain View CA 94043 USA

Technology development has accelerated the volume growth of complex data, such as images, videos, time series, and georeferenced data. Similarity search is a widely used approach to retrieve complex data, which aims at retrieving similar data according to intrinsic characteristics of the data. Therefore, to facilitate the retrieval of complex data using similarity searches, one needs to organize large collections of data in a way that similar data can be retrieved efficiently. Many access methods were proposed in the literature to speed up similarity data retrieval from large databases. Recently, graph-based methods have emerged as a very efficient alternative for similarity retrieval, with reports indicating those methods outperformed other non-graph-based methods in several scenarios. However, to the best of our knowledge, there is no previous work with experimental analysis on a comprehensive number of graph-based methods using the same search algorithm and execution environment. Our main contribution is a survey on graph-based methods used for similarity searches. We present a review on graph-based methods (types of graphs and search algorithms) as well as a detailed discussion on the applicability of search algorithms (with exact or approximate answers) in each graph type. Our main focus is on static methods in metric spaces. This survey also includes an experimental evaluation of representative graphs implemented in a common platform. We evaluate the relative performance behavior of these graphs concerning the main construction and query parameters for a variety of real-world datasets. We also show results using synthetic datasets evaluating the performance of different graph types according to different dataset features. Our experimental results reinforce the tradeoff between graph construction cost and search performance according to the construction and search parameters. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： graph-based methods Proximity graphs Similarity searches Metric spaces Experimental survey

来源：评论

学校读者我要写书评

暂无评论

Make graph-based Referring Expression Comprehension Great Again Through Expression-Guided Dynamic Gating and Regression

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2025年 27卷 1950-1961页

作者： Ke, Jingcheng Wang, Dele Chen, Jun-Cheng Jhuo, I-Hong Lin, Chia-Wen Lin, Yen-Yu Natl Tsing Hua Univ Dept Elect Engn Hsinchu 300044 Taiwan Natl Tsing Hua Univ Inst Commun Engn Hsinchu 300044 Taiwan Acad Sinica Res Ctr Informat Technol Innovat Taipei 115201 Taiwan Microsoft Seattle WA 98039 USA Natl Yang Ming Chiao Tung Univ Dept Comp Sci Hsinchu 300093 Taiwan

One common belief is that with complex models and pre-training on large-scale datasets, transformer-based methods for referring expression comprehension (REC) perform much better than existing graph-based methods. We observe that since most graph-based methods adopt an off-the-shelf detector to locate candidate objects (i.e., regions detected by the object detector), they face two challenges that result in subpar performance: (1) the presence of significant noise caused by numerous irrelevant objects during reasoning, and (2) inaccurate localization outcomes attributed to the provided detector. To address these issues, we introduce a plug-and-adapt module guided by sub-expressions, called dynamic gate constraint (DGC), which can adaptively disable irrelevant proposals and their connections in graphs during reasoning. We further introduce an expression-guided regression strategy (EGR) to refine location prediction. Extensive experimental results on the RefCOCO, RefCOCO+, RefCOCOg, Flickr30 K, RefClef, and Ref-reasoning datasets demonstrate the effectiveness of the DGC module and the EGR strategy in consistently boosting the performances of various graph-based REC methods. Without any pretaining, the proposed graph-based method achieves better performance than the state-of-the-art (SOTA) transformer-based methods.

关键词： Visualization Cognition Feature extraction Transformers Detectors Semantics Logic gates Electronic mail Proposals Long short term memory Transformer-based methods graph-based methods dynamic gate constraint expression-guided regression

来源：评论

学校读者我要写书评

暂无评论

RankUp: Enhancing graph-based keyphrase extraction methods with error-feedback propagation

引用

COMPUTER SPEECH AND LANGUAGE 2018年 47卷 112-131页

作者： Figueroa, Gerardo Chen, Po-Chi Chen, Yi-Shin Natl Tsing Hua Univ Inst Informat Syst & Applicat Dept Comp Sci Hsinchu 30013 Taiwan

In recent years, unsupervised, graph-based ranking algorithms have been successfully applied to keyphrase extraction tasks. These methods have the advantage of taking into account global information, such as text structure and relations between words, phrases, and sentences, rather than relying solely on local, vertex-specific information. graph-based approaches for keyphrase extraction, however, have a particular drawback, which comes from their frequency-based analysis methods. The weakness is that many common, less relevant terms may get a higher ranking, particularly in short articles. The converse situation also occurs, where less common (and possibly more relevant) terms obtain lower rankings. We propose an unsupervised method RankUp-that- enhances graph-based keyphrase extraction approaches by applying an error-feedback mechanism similar to the concept of backpropagation. Experiments have been performed on almost 3,300 short texts from a variety of domains. Our experiments show that error-feedback propagation can boost the quality of keyphrases in graph-based keyphrase extraction techniques. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Keyphrase extraction graph-based methods Backpropagation Error feedback Short articles

来源：评论

学校读者我要写书评

暂无评论

LaplaceNet: A Hybrid graph-Energy Neural Network for Deep Semisupervised Classification

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第4期35卷 5306-5318页

作者： Sellars, Philip Aviles-Rivero, Angelica, I Schonlieb, Carola-Bibiane Univ Cambridge Dept Theoret Phys & Appl Math Cambridge CB3 0WA England

Semisupervised learning (SSL) has received a lot of recent attention as it alleviates the need for large amounts of labeled data which can often be expensive, requires expert knowledge, and be time consuming to collect. Recent developments in deep semisupervised classification have reached unprecedented performance and the gap between supervised and SSL is ever-decreasing. This improvement in performance has been based on the inclusion of numerous technical tricks, strong augmentation techniques, and costly optimization schemes with multiterm loss functions. We propose a new framework, LaplaceNet, for deep semisupervised classification that has a greatly reduced model complexity. We utilize a hybrid approach where pseudolabels are produced by minimizing the Laplacian energy on a graph. These pseudolabels are then used to iteratively train a neural-network backbone. Our model outperforms state-of-the-art methods for deep semisupervised classification, over several benchmark datasets. Furthermore, we consider the application of strong augmentations to neural networks theoretically and justify the use of a multisampling approach for SSL. We demonstrate, through rigorous experimentation, that a multisampling augmentation approach improves generalization and reduces the sensitivity of the network to augmentation.

关键词： Data models Neural networks Perturbation methods Deep learning Complexity theory Training Interpolation Data augmentation deep learning graph-based methods image classification pseudolabeling semisupervised learning (SSL)

来源：评论

学校读者我要写书评

暂无评论

Consistent Semi-Supervised graph Regularization for High Dimensional Data

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2021年第1期22卷 1-48页

作者： Mai, Xiaoyi Couillet, Romain Univ Paris Saclay Cent Supelec Lab Signaux & Syst 3 Rue Joliot Curie F-91192 Gif Sur Yvette France Univ Grenoble Alpes GSTATS DataSci Chair GIPSA Lab 11 Rue Math F-38400 St Martin Dheres France

Semi-supervised Laplacian regularization, a standard graph-based approach for learning from both labelled and unlabelled data, was recently demonstrated to have an insignificant high dimensional learning efficiency with respect to unlabelled data (Mai and Couillet, 2018), causing it to be outperformed by its unsupervised counterpart, spectral clustering, given sufficient unlabelled data. Following a detailed discussion on the origin of this inconsistency problem, a novel regularization approach involving centering operation is proposed as solution, supported by both theoretical analysis and empirical results.

关键词： semi-supervised learning graph-based methods centered similarities distance concentration random matrix theory

来源：评论

学校读者我要写书评

暂无评论

In-Memory graph Databases for Web-Scale Data

引用

COMPUTER 2015年第3期48卷 24-35页

作者： Castellana, Vito Giovanni Morari, Alessandro Weaver, Jesse Tumeo, Antonino Haglin, David Villa, Oreste Feo, John Pacific NW Natl Lab High Performance Comp Grp Richland WA 99352 USA Pacific NW Natl Lab Data Sci Grp Richland WA 99352 USA Pacific NW Natl Lab Data Intens Sci Comp Grp Richland WA 99352 USA

A software stack relies primarily on graph-based methods to implement scalable resource description framework databases on top of commodity clusters, providing an inexpensive way to extract meaning from volumes of het... 详细信息

关键词： Internet database management systems graph theory pattern clustering Web-scale data commodity clusters graph-based methods heterogeneous data inmemory graph databases scalable resource description framework databases software stack Algorithm design and analysis Clustering algorithms Data structures Pattern matching Resource description framework Resource management Software development RDF databases SPARQL big data graph databases high-performance computing multithreading

来源：评论

学校读者我要写书评

暂无评论

Hybrid system for video game recommendation based on implicit ratings and social networks

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2020年第11期11卷 4525-4535页

作者： Perez-Marcos, Javier Martin-Gomez, Lucia Jimenez-Bravo, Diego M. Lopez, Vivian F. Moreno-Garcia, Maria N. Univ Salamanca Dept Comp Sci & Automat Plaza Merced S-N E-37008 Salamanca Spain Univ Pontificia Salamanca Dept Comp Sci C Compania 5 Salamanca 37002 Spain

The digital entertainment sector is one of the fastest growing in recent years. In the case of video games, the productions of some of the most popular titles are on a par with film productions. The sale of video games is in the millions, and yet there are few works on the recommendation of video games. In this work a hybrid system of video game recommendation is presented, through the use of collaborative filtering and content-based filtering, and the construction of relationship graphs. In order to improve the recommendations, a new method for estimating implicit ratings is proposed that takes into account the hours of play. The proposed recommender system improves the results of other techniques presented in the state of the art.

关键词： Recommender systems Colaborative filtering Content-based filtering Rating estimation graph-based methods Video games

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：