检索结果-内蒙古大学图书馆

Discriminative Self-Paced Group-Metric Adaptation for Online Visual Identification

ieee TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第4期45卷 4368-4383页

作者： Zhou, Jiahuan Su, Bing Wu, Ying Peking Univ Wangxuan Inst Comp Technol Beijing 100080 Peoples R China Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Key Lab Big Data Management & Anal Methods Beijing 100872 Peoples R China Northwestern Univ Dept Elect & Comp Engn Evanston IL 60208 USA

Existing solutions to instance-level visual identification usually aim to learn faithful and discriminative feature extractors from offline training data and directly use them for the unseen online testing data. However, their performance is largely limited due to the severe distribution shifting issue between training and testing samples. Therefore, we propose a novel online group-metric adaptation model to adapt the offline learned identification models for the online data by learning a series of metrics for all sharing-subsets. Each sharing-subset is obtained from the proposed novel frequent sharing-subset mining module and contains a group of testing samples that share strong visual similarity relationships to each other. Furthermore, to handle potentially large-scale testing samples, we introduce self-paced learning (SPL) to gradually include samples into adaptation from easy to difficult which elaborately simulates the learning principle of humans. Unlike existing online visual identification methods, our model simultaneously takes both the sample-specific discriminant and the set-based visual similarity among testing samples into consideration. Our method is generally suitable to any off-the-shelf offline learned visual identification baselines for online performance improvement which can be verified by extensive experiments on several widely-used visual identification benchmarks.

关键词： visualization Testing Adaptation models Measurement Training data models Feature extraction Learning from sharing frequent pattern mining online adaptation person re-identification self-paced learning

来源：评论

学校读者我要写书评

暂无评论

DBiased-P: Dual-Biased Predicate Predictor for Unbiased Scene Graph Generation

引用

ieee TRANSACTIONS ON MULTIMEDIA 2023年 25卷 5319-5329页

作者： Han, Xianjing Song, Xuemeng Dong, Xingning Wei, Yinwei Liu, Meng Nie, Liqiang Shandong Univ Sch Comp Sci & Technol Qingdao 266237 Peoples R China Natl Univ Singapore Sch Comp Singapore 119077 Singapore Shandong Jianzhu Univ Sch Comp Sci & Technol Jinan 250101 Peoples R China

Scene Graph Generation (SGG) is to abstract the objects and their semantic relationships within a given image. Current SGG performance is mainly limited by the biased predicate prediction caused by the long-tailed data distribution. Though many unbiased SGG methods have emerged to enhance the prediction of the tail predicates, their improvements on the tail predicates are often accompanied by the deterioration on the head ones, leading the prediction overly debiased. Toward this end, in this work, we propose a Dual-Biased Predicate Predictor (DBiased-P) to boost the unbiased SGG, which comprises a re-weighted primary classifier and an unweighted auxiliary classifier. The former classifier is tail-biased and used for the final predicate prediction, while the latter one is head-biased and designed to boost the head predicate prediction of the primary classifier by a head-oriented soft regularization. Experiments conducted on Visual Genome and Open Image datasets indicate the superiority of our DBiased-P in unbiased SGG, which significantly improves the recall@50 of the state-of-the-art unbiased SGG method DT2-ACBS from 23.3% to 55.5% as well as the mean recall@50 from 35.9% to 37.7%.

关键词： Head Tail Decoding visualization Predictive models Detectors Training data Scene graph generation vision and language Re-weighting classification KL-divergence

来源：评论

学校读者我要写书评

暂无评论

RingMoGPT: A Unified Remote Sensing Foundation Model for Vision, Language, and Grounded Tasks

引用

ieee TRANSACTIONS ON GEOscience AND REMOTE SENSING 2025年 63卷

作者： Wang, Peijin Hu, Huiyang Tong, Boyuan Zhang, Ziqi Yao, Fanglong Feng, Yingchao Zhu, Zining Chang, Hao Diao, Wenhui Ye, Qixiang Sun, Xian Chinese Acad Sci Aerosp Informat Res Inst Key Lab Network Informat Syst Technol NIST Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Network Informat Syst Technol NIST Key Lab Target Cognit & Applicat Technol TCAT Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100190 Peoples R China

Recently, multimodal large language models (MLLMs) have shown excellent reasoning capabilities in various fields. Most of the existing remote sensing (RS) MLLMs solve image-level text generation problems (e.g., image captioning), but ignore the core issues of object-level recognition, location, and multitemporal changes in the field of RS. In this article, we propose RingMoGPT, a multimodal foundation model that unifies vision, language, and localization. Based on the idea of domain adaption, RingMoGPT can complete training by fine-tuning only a few parameters. To make the model capable of object detection and change captioning, we further propose a location- and instruction-aware querying transformer (Q-Former) and a change detection module, respectively. To improve the performance of RingMoGPT, we carefully design the pretraining dataset and the instruction-tuning dataset. The pretraining dataset contains over a half million high-quality image and text pairs, which are generated through a low-cost and efficient data generation paradigm. The instruction-tuning dataset contains more than 1.6 million question-answer pairs, including six downstream tasks: scene classification, object detection, visual question answering (VQA), image captioning, grounded image captioning, and change captioning. Our experiments show that RingMoGPT performs well on six tasks, especially its ability to analyze multitemporal data changes and identify dense objects. We also verified the model under a zero-shot setting, and the results show that the proposed RingMoGPT also has good generalization ability in the face of new data.

关键词： Remote sensing visualization data models Adaptation models Training Object detection Tuning Large language models Cognition Scene classification Foundation model instruction-tuning multimodal large language model (MLLM) pretraining remote sensing (RS)

来源：评论

学校读者我要写书评

暂无评论

MoneyVis: Open Bank Transaction data for visualization and Beyond

MoneyVis: Open Bank Transaction Data for Visualization and B...

引用

25th Eurographics Conference on visualization, EuroVis 2023

作者： Firat, Elif E. Vytla, Dharmateja Singh, Navya Vasudeva Jiang, Zhuoqun Laramee, Robert S. The Department of Computer Engineering Cukurova University Turkey The School of Computer Science The University of Nottingham United Kingdom

ISBN: (纸本)9783038682196

With the rapid evolution of financial technology (FinTech) the importance of analyzing financial transactions is growing in importance. As the prevalence and number of financial transactions grow, so does the necessity of visual analysis tools to study the behavior represented by these transactions. However, real bank transaction data is generally private for security and confidentiality reasons, thus preventing its use for visual analysis and research. We present Moneydata, an anonymized open bank data set spanning seven years worth of transactions for research and analysis purposes. To our knowledge, this is the first real-world retail bank transaction data that has been anonymized and made public for visualization and analysis by other researchers. We describe the data set, its characteristics, and the anonymization process and present some preliminary analysis and images as a starting point for future research. The transactions are also categorized to facilitate understanding. We believe the availability of this open data will greatly benefit the research community and facilitate further study of finance. © 2023 The Authors.

关键词： Finance

来源：评论

学校读者我要写书评

暂无评论

ASIFC: Auditable and Secure Information Flow Control for PaaS Cloud

ASIFC: Auditable and Secure Information Flow Control for Paa...

引用

2023 International Conference on Mobile Internet, Cloud Computing and Information Security, MICCIS 2023

作者： Zhou, Minghao Lu, Jintian Jin, Shuyuan Sun Yat-sen University School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798350300932

In the cloud, data security issues such as data leakage and maliciously access frequently occurs. Deploying strict security controls on the information flows in the cloud can effectively prevent such problems from happening. How to accurately control the information flows in the cloud and provide an intuitive way of auditing has become an indispensable need to enhance data security. This paper proposes an auditable and secure information flow control (ASIFC) module for PaaS cloud. By using decentralized information flow control model, ASIFC strictly controls the inter-process communication such as pipes, shared memory, and message queues, accurately and intuitively controlling the information flows in the cloud. Moreover, based on NetworkX, a log-driven visualization interface which can display flow direction of information in PaaS cloud is offered, providing understandable content for auditing. The performance evaluation results show that the module outperforms FlowK and Flume in micro-benchmark. © 2023 ieee.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Using Augmented Reality to enhance the experience of IoT-based Home Automation Systems

Using Augmented Reality to enhance the experience of IoT-bas...

引用

2023 ieee International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Kaur, Deepti Prit Sharma, Manmohan Sharma, Preeti Malik, Garvit Mehakdeep Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School of computer Science and Engineering Manipal University Jaipur Jaipur India

ISBN: (纸本)9798350305708

Internet of Things (IoT) is an integral part of home automation, where physical devices are interconnected such that, they enable communication amongst electronics, sensors, software, and network. The data collection and analysis in IoT, and unified framework in cloud computing strives to improve living standards and productive outcomes by interacting with smart devices. In various fields such as education, control, and entertainment, Augmented Reality (AR) technology attempts to improve user experiences through improved interactions within the available settings. This paper presents an IoT based Home Automation System, which uses Augmented Reality as an additional technology to enable utilization of real time visualization and interaction for better experience. The application is beneficial for children, elderly and differently abled persons as it would aid them with control of electrical appliances just by scan through a device camera, connected to internet. From a safety perspective also, it offers electrical isolation. © 2023 ieee.

关键词： Augmented Reality Home Automation IoT

来源：评论

学校读者我要写书评

暂无评论

EEG Channel Analysis for Energy data visualizations Using GAF Encoding and Deep Learning 4

EEG Channel Analysis for Energy Data Visualizations Using GA...

引用

4th International Conference on Electrical, Communication and Computer Engineering, ICECCE 2023

作者： Kucukler, Omer Faruk Amira, Abbes Malekmohamadi, Hossein Institute of Artificial Intelligence De Montfort University Leicester United Kingdom Department of Computer Science University of Sharjah United Arab Emirates

ISBN: (纸本)9798350369694

Electroencephalography (EEG) is a technique used to assess brain activity during cognitive tasks. EEG signals are generated by a variety of sensors, and due to their inherent complexity, analyzing EEGs can be difficult to retrieve task-related information. To improve the performance of EEG applications, selecting useful EEG channels and minimizing irrelevant channel information can improve the quality of analysis and results. This study focuses on the classification performance evaluation of EEG channels. A unique EEG dataset containing EEG signals is used in response to energy data visualization stimuli to capture users' emotions. To analyze valence emotion in data visualizations, EEG signals are transformed into Gramian Angular Fields (GAF) images, and Deep Learning (DL) features retrieved from GAFs using the Convolutional Neural Network (CNN) -Long-Short Term Memory (LSTM) model. To evaluate valence emotion, a boosting classifier is utilized using a DL feature set reduced by a Principal Component Analysis (PCA) approach. The results demonstrate the success of the technique employed to identify the best channels. The F3 channel has the highest accuracy of 99.76%, while the Fp2 channel has a comparable accuracy of 99.52%. Overall, the suggested technique shows promising outcomes in identifying valence emotion for energy data representations. © 2023 ieee.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

Assessing the Expressive Language Levels of Autistic Children in Home Intervention

引用

ieee TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2025年

作者： Pan, Yueran Chen, Biyuan Liu, Wenxing Cheng, Ming Zhang, Dong Deng, Hongzhu Zou, Xiaobing Li, Ming Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Duke Kunshan Univ Digital Innovat Res Ctr Kunshan 215316 Peoples R China Sun Yat Sen Univ Affiliated Hosp 3 Child Dev & Behav Ctr Guangzhou 510630 Peoples R China Sun Yat Sen Univ Sch Elect & Informat Technol Guangzhou 510006 Peoples R China

The World Health Organization (WHO) has established the caregiver skill training (CST) program, designed to empower families with children diagnosed with autism spectrum disorder the essential caregiving skills. The joint engagement rating inventory (JERI) protocol evaluates participants' engagement levels within the CST initiative. Traditionally, rating the expressive language level and use (EXLA) item in JERI relies on retrospective video analysis conducted by qualified professionals, thus incurring substantial labor costs. This study introduces a multimodal behavioral signal-processing framework designed to analyze both child and caregiver behaviors automatically, thereby rating EXLA. Initially, raw audio and video signals are segmented into concise intervals via voice activity detection, speaker diarization and speaker age classification, serving the dual purpose of eliminating nonspeech content and tagging each segment with its respective speaker. Subsequently, we extract an array of audio-visual features, encompassing our proposed interpretable, hand-crafted textual features, end-to-end audio embeddings and end-to-end video embeddings. Finally, these features are fused at the feature level to train a linear regression model aimed at predicting the EXLA scores. Our framework has been evaluated on the largest in-the-wild database currently available under the CST program. Experimental results indicate that the proposed system achieves a Pearson correlation coefficient of 0.768 against the expert ratings, evidencing promising performance comparable to that of human experts.

关键词： Feature extraction databases Autism visualization Pediatrics Predictive models Protocols Tablet computers Linear regression data models Autism spectrum disorder behavior signal processing expressive language home intervention

来源：评论

学校读者我要写书评

暂无评论

INCITEST 2023 - Proceedings of the 2023 International Conference on Informatics Engineering, science and Technology

INCITEST 2023 - Proceedings of the 2023 International Confer...

引用

2023 International Conference on Informatics Engineering, science and Technology, INCITEST 2023

ISBN: (纸本)9798350317862

The proceedings contain 59 papers. The topics discussed include: travel route recommendation system based on weather prediction and geolocation technology;unleashing the sea turtle recognition power: a battle of activation functions in resnet50;integration of function point and earned value management methods in information systems project development evaluation;communication-based train control simulator to optimize train headway;export import data visualization using GIS at the directorate general of agro industry with prototype methods;application of agglomerative hierarchical clustering (AHC) for grouping prospective scholarship recipients;and web based geographic information system (WebGIS) using prototype approach for mapping and management of land use in Merauke Regency South Papua Indonesia.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Causal Disentanglement: A Generalized Bearing Fault Diagnostic Framework in Continuous Degradation Mode

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第9期34卷 6250-6262页

作者： Li, Jie Wang, Yu Zi, Yanyang Zhang, Haijun Wan, Zhiguo Xian Jiaotong State Key Lab Mfg Syst Engn Xian 710049 Peoples R China Harbin Inst Technol Shenzhen 518055 Peoples R China Xian Shiyou Univ Sch Mech Engn Xian 710065 Peoples R China

In recent years, the identification of out-of-distribution faults has become a hot topic in the field of intelligent diagnosis. Existing researches usually adopt domain adaptation methods to complete the generalization of diagnostic knowledge with the aid of target domain data, but the acquisition of fault samples in real industries is extremely time-consuming and costly. Moreover, most researches focus on samples with fixed fault levels, ignoring the fact that system degradation is a continuous process. In response to the above intractable problems, this article proposed a causal disentanglement network (CDN) to realize cross-machine knowledge generalization and continuous degradation mode diagnosis. In CDN, multitask instance normalization and batch normalization structure was proposed to learn task-specific knowledge and enhance the informativeness of the extracted features. On this basis, a causal disentanglement loss was proposed, which minimized the mutual information of features between subtask structures and captured the causal invariant fault information for better generalization. The experimental results proved the superiority and generalization ability of CDN, and the visualization results proved the performance of CDN in causality mining.

关键词： Feature extraction Task analysis Fault diagnosis Degradation Knowledge engineering Industries data models Causal learning deep learning fault diagnosis rolling bearing

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：