检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Saining Ye, Baijun Chen, Xiaoxue Chen, Yuantao Zhang, Zongzheng Peng, Cheng Shi, Yongliang Zhao, Hao Tsinghua University Beijing China College of Computing and Data Science Nanyang Technological University Singapore IIIS Tsinghua University Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China

Robust and realistic rendering for large-scale road scenes is essential in autonomous driving simulation. Recently, 3D Gaussian Splatting (3D-GS) has made groundbreaking progress in neural rendering, but the general fidelity of large-scale road scene renderings is often limited by the input imagery, which usually has a narrow field of view and focuses mainly on the street-level local area. Intuitively, the data from the drone’s perspective can provide a complementary viewpoint for the data from the ground vehicle’s perspective, enhancing the completeness of scene reconstruction and rendering. However, training naively with aerial and ground images, which exhibit large view disparity, poses a significant convergence challenge for 3D-GS, and does not demonstrate remarkable improvements in performance on road views. In order to enhance the novel view synthesis of road views and to effectively use the aerial information, we design an uncertainty-aware training method that allows aerial images to assist in the synthesis of areas where ground images have poor learning outcomes instead of weighting all pixels equally in 3D-GS training like prior work did. We are the first to introduce the cross-view uncertainty to 3D-GS by matching the car-view ensemble-based rendering uncertainty to aerial images, weighting the contribution of each pixel to the training process. Additionally, to systematically quantify evaluation metrics, we assemble a high-quality synthesized dataset comprising both aerial and ground images for road scenes. Through comprehensive results, (Figuire presented) we show that: (1) Jointly training aerial and ground images helps improve representation ability of 3D-GS when test views are shifted and rotated, but performs poorly on held-out road view test. (2) Our method reduces the weakness of the joint training, and out-performs other baselines quantitatively on both held-out tests and scenes involving view shifting and rotation on our datasets. (3) Qualitativ

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Deng, Songhe Zhuo, Wei Xie, Jinheng Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Class Activation Map (CAM) has emerged as a popular tool for weakly supervised semantic segmentation (WSSS), allowing the localization of object regions in an image using only image-level labels. However, existing CAM methods suffer from under-activation of target object regions and false-activation of background regions due to the fact that a lack of detailed supervision can hinder the model’s ability to understand the image as a whole. In this paper, we propose a novel Question-Answer Cross-Language-Image Matching framework for WSSS (QA-CLIMS), leveraging the vision-language foundation model to maximize the text-based understanding of images and guide the generation of activation maps. First, a series of carefully designed questions are posed to the VQA (Visual Question Answering) model with Question-Answer Prompt Engineering (QAPE) to generate a corpus of both foreground target objects and backgrounds that are adaptive to query images. We then employ contrastive learning in a Region Image Text Contrastive (RITC) network to compare the obtained foreground and background regions with the generated corpus. Our approach exploits the rich textual information from the open vocabulary as additional supervision, enabling the model to generate high-quality CAMs with a more complete object region and reduce false-activation of background regions. We conduct extensive analysis to validate the proposed method and show that our approach performs state-of-the-art on both PASCAL VOC 2012 and MS COCO datasets. Code is available at: https://***/CVI-SZU/QA-CLIMS Copyright © 2024, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Prompting Large Language Models for Few-Shot Named Entity Recognition

SSRN

引用

SSRN 2024年

作者： Zhong, Xiaoshi Zhao, Yufei Cambria, Erik Rajapakse, Jagath C. School of Computer Science and Technology Beijing Institute of Technology China China North Industries Computer Application Technology Institute NORINCO Group Co. Ltd. China College of Computing and Data Science Nanyang Technological University Singapore

Named entity recognition (NER) is a fundamental task in numerous downstream applications. Recently, researchers have employed pre-trained language models (PLMs) and large language models (LLMs) to address this task. However, fully leveraging the capabilities of PLMs and LLMs with minimal human effort remains challenging. In this paper, we propose GPT4NER, a method that prompts LLMs to resolve the few-shot NER task. GPT4NER constructs effective prompts using three key components: entity definition, few-shot examples, and chain-of-thought. By prompting LLMs with these effective prompts, GPT4NER transforms few-shot NER, traditionally considered as a sequence-labeling problem, into a sequence-generation problem. We conduct experiments on two benchmark datasets, CoNLL2003 and OntoNotes5.0, and compare the performance of GPT4NER to representative state-of-the-art models in both few-shot and fully supervised settings. Experimental results demonstrate that GPT4NER achieves the $F_1$ of 83.15% on CoNLL2003 and 70.37% on OntoNotes5.0, significantly outperforming few-shot baselines by an average margin of 7 points. Compared to fully-supervised baselines, GPT4NER achieves 87.9% of their best performance on CoNLL2003 and 76.4% of their best performance on OntoNotes5.0. © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Retinal Image Analysis for Early Deduction of Diabetic Retinopathy

Retinal Image Analysis for Early Deduction of Diabetic Retin...

引用

International Conference on Advanced computing and Communication Systems (ICACCS)

作者： A. Chinnasamy P. Selvakumari Department of Data Science and Business Systems School of Computing SRMIST Chennai India Department of Computer Science and Engineering Chennai Institute of Technology Anna University Chennai India

The prevalence of DR is steadily rising, which necessitates the automatic disease severity extraction and classification. About 2% of those with this illness are entirely blind because of the diabetic mellitus problem and 10% get vision impairment after 15 years of diabetes as a result of the DR complication. It is also a significant contributor to blindness in both middle aged and older age groups. The patient may develop to severe stages of irreversible blindness if the condition is not detected early. The growing number of diabetic patients face a major issue due to a lack of ophthalmologists. It is suggested that an automated DR screening system be created to aid the ophthalmologist in making decisions. One of the primary symptoms of the DR is hard exudates. The detection of hard exudates is crucial for screening purposes and aids in disease monitoring and diagnosis. Thus, utilising Lloyd’s clustering technique, this work offered a unique techniques to segment the exudates and irregularities in DR were found.

关键词： Support vector machines Image segmentation Visual impairment Blindness Blood vessels Retina Time measurement

来源：评论

学校读者我要写书评

暂无评论

The Prospect of Enhancing Large-Scale Heterogeneous Federated Learning with Foundation Models

The Prospect of Enhancing Large-Scale Heterogeneous Federate...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yulan Gao Zhaoxiang Hou Chengyi Yang Zengxiang Li Han Yu Xiaoxiao Li College of Computing and Data Science Nanyang Technological University Singapore Digital Research Institute ENN Group China Department of Electrical and Computer Engineering The University of British Columbia Canada

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Federated learning (FL) addresses data privacy concerns by enabling collaborative training of AI models across distributed data owners. Wide adoption of FL faces the fundamental challenges of data heterogeneity and the large scale of data owners involved. In this paper, we investigate the prospect of Foundation Model (e.g., transformers)-based FL for achieving generalization and personalization in this setting. Different from existing research efforts which mostly focus on studying Transformer-based FL on small scales, we conduct extensive comparative experiments involving FL with Transformers, ResNet, and personalized ResNet-based FL approaches under various large-scale scenarios. These experiments consider varying numbers of data owners to demonstrate Transformers’ advantages over deep neural networks in large-scale heterogeneous FL tasks. In addition, we analyze the superior performance of Transformers by comparing the Centered Kernel Alignment (CKA) representation similarity across different layers and FL models to gain insight into the reasons behind their promising capabilities.

关键词： Training Analytical models data privacy Accuracy Federated learning Distributed databases Transformers

来源：评论

学校读者我要写书评

暂无评论

Audio-Visual Target Speaker Extraction With Selective Auditory Attention

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 797-811页

作者： Ruijie Tao Xinyuan Qian Yidi Jiang Junjie Li Jiadong Wang Haizhou Li Department of Electrical and Computer Engineering National University of Singapore Singapore Department of Computer Science and Technology University of Science and Technology Beijing Beijing China Chinese University of Hong Kong Shenzhen China Guangdong Provincial Key Laboratory of Big Data Computing Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China University of Bremen Bremen Germany

Audio-visual target speaker extraction (AV-TSE) aims to extract the specific person's speech from the audio mixture given auxiliary visual cues. Previous methods usually search for the target voice through speech-lip synchronization. However, this strategy mainly focuseson the existence of target speech, while ignoring the variations of the noise characteristics, i.e., interference speaker and the background noise. That may result in extracting noisy signals from the incorrect sound source in challenging acoustic situations. To this end, we propose a novel selective auditory attention mechanism, which can suppress interference speakers and non-speech signals to avoid incorrect speaker extraction. By estimating and utilizing the undesired noisy signal through this mechanism, we design an AV-TSE framework named Subtraction-and-ExtrAction network (SEANet) to suppress the noisy signals. We conduct abundant experiments by re-implementing three popular AV-TSE methods as the baselines and involving nine metrics for evaluation. The experimental results show that our proposed SEANet achieves state-of-the-art results and performs well for all five datasets.

关键词： Noise measurement Lips Visualization Synchronization Noise Correlation data mining Speech processing Interference Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Rethinking the visual cues in audio-visual speaker extraction

arXiv

引用

arXiv 2023年

作者： Li, Junjie Ge, Meng Pan, Zexu Cao, Rui Wang, Longbiao Dang, Jianwu Zhang, Shiliang Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Department of Electrical and Computer Engineering National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore Shenzhen Research Institute of Big Data Shenzhen China

The Audio-Visual Speaker Extraction (AVSE) algorithm employs parallel video recording to leverage two visual cues, namely speaker identity and synchronization, to enhance performance compared to audio-only algorithms. However, the visual front-end in AVSE is often derived from a pre-trained model or end-to-end trained, making it unclear which visual cue contributes more to the speaker extraction performance. This raises the question of how to better utilize visual cues. To address this issue, we propose two training strategies that decouple the learning of the two visual cues. Our experimental results demonstrate that both visual cues are useful, with the synchronization cue having a higher impact. We introduce a more explainable model, the Decoupled Audio-Visual Speaker Extraction (DAVSE) model, which leverages both visual cues. Copyright © 2023, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Explainable AI in Blockchain System for Decentralized Governance

Explainable AI in Blockchain System for Decentralized Govern...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Suman Chahar Kawaljit Kaur Kuldeep Singh Kaswan Jagjit Singh Dhatterwal University Institute of Computing Chandigarh University Mohali India Department of Computer Science and Engineering Galgotias University Greater Noida India Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Andhra Pradesh India

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Decentralized governance is going through radical changes due to the innovative use of blockchain which allows decisions to be made in a transparent, secure and more im- portantly, immutable way, without the authority of a single individual or party. Thus, the introduction of artificial intelligence (AI) in blockchain governing systems complicates such thing as transparency and trust, especially in the case of deep AI systems. But more on this later – this is where Explainable AI or XAI comes into the picture. XAI methods enable understanding of the reasons behind the choices made by AI models and solves the "black box" problem that is predominant in machine learn- ing. When applied to decentralised governance, XAI provides clarifications of AI’s decision making in such areas as voting, resource distribution and the enactment of smart contracts. This way, the stakeholders are confident that the decision-making is fair and impartial and this is made possible by the use of XAI. This paper aims to find out more about the applicability of XAI concept in blockchain –based governance systems in terms of bias and fairness in automated decisions and explanation of the decisions made. The reasons why interpretability plays the crucial role in decentralized systems are explained with the help of the comparison between the classical artificial intelligence and the Xin Intelligent. The study also looks at various use cases such as, Decentralized Autonomous Organizations (DAOs), and voting systems implemented on blockchain platforms and how XAI can enhance the performance of the governance systems. As this study shows, XAI is vital in building trust, improving responsibility, and guaranteeing balanced majorities in decentralized blockchain governance structures.

关键词： Explainable AI Decentralized autonomous organization Computational modeling Smart contracts Decision making Blockchains Resource management Stakeholders Security Decision trees

来源：评论

学校读者我要写书评

暂无评论

Enabling Protection for Critical Infrastructure through Security and Privacy in the Industrial Internet of Things 9

Enabling Protection for Critical Infrastructure through Secu...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Yasotha, B. Vijayanandh, T. Thirumoorthy, P. Priya, M.Sangeetha Sasidaran, S. Prakalya, S.B. Srmist Department of Data Science and Business Systems Kattankulathur India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Avadi Tamil Nadu Chennai India Dhanalakshmi College of Engineering Department of Electrical and Electronics Engineering Chennai India Chennai India Panimalar Engineering College Department of Information Technology Chennai600123 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350377972

Industrial Internet of Things can improve critical infrastructure in energy, transportation, and manufacturing. However, IIoT device and system integration opened security weaknesses that bad actors may exploit, causing huge disruptions and financial losses. IoT network security and privacy must be prioritized to protect key infrastructure. IIoT security issues and solutions are examined in this research. First, we take a look at the state of security and the unique risks that industrial IoT devices are up against, including hacking, illegal access, and cyber-physical assaults. Then, to lessen the impact of these dangers, we investigate cutting-edge security solutions, such as authentication, encryption, and access control systems. Building a robust security architecture specifically for IIoT applications is one of the main goals of the project. To improve safety and anonymity, this system uses cutting-edge innovation like blockchain, AI, and edge computing. We also talk about how privacy-preserving methods like differential privacy and anonymization are important for keeping sensitive information safe while allowing data sharing for analysis and operations. We assess the efficacy of the suggested security protocols and procedures using a battery of case studies and simulations. Reducing the attack surface and improving the resilience of IIoT systems can be achieved by a multi-layered security approach that includes effective privacy protections. We conclude by outlining our research's larger implications, which include the importance of standardization, regulatory compliance, and stakeholder collaboration in ensuring the safe and privacy-protecting deployment of IIoT technologies in vital infrastructure. Protecting vital infrastructure from cyber threats is our ultimate goal, and our work helps build IIoT systems that are more secure and dependable. © 2024 IEEE.

关键词： Industrial internet of things (IIoT)

来源：评论

学校读者我要写书评

暂无评论

Transparency, Trust, and Security Needs for the Design of Digital News Authentication Tools

引用

Proceedings of the ACM on Human-Computer Interaction 2023年第1 CSCW期7卷 1-44页

作者： Francis, Errol Monroe, Ayana Sidnam-Mauch, Emily Ivancsics, Bernat Washington, Eve Mcgregor, Susan E. Bonneau, Joseph Caine, Kelly Clemson University School of Computing ClemsonSC29631 United States University of North Carolina at Chapel Hill 201 S Columbia St Chapel HillNC27515 United States Columbia University Columbia Journalism School New YorkNY10027 United States Columbia University Department of Computer Science New YorkNY10027 United States Columbia University Data Science Institute New YorkNY10027 United States New York University Courant Institute of Mathematical Sciences New YorkNY10012 United States

Americans' trust in news is declining, and authenticity and transparency challenges in digital publishing contexts pose unique challenges to the ability to effectively gratify their information-seeking needs via online media. Cryptographic technologies and web-based provenance indicators have the potential to enhance the trustworthiness and transparency of digital communication, but better understandings of news consumers practices and needs are required to develop practical tools. Through a representative online survey of 400 digital news consumers and 19 follow-up interviews, we investigate how users authenticate and assign trust to news content, and identify specific needs pertaining to news transparency and authentication that could be met by digital news authentication tools. While many users currently rely on political ideology to assess news trustworthiness, we find that users of all political orientations see value in independent provenance and authentication tools for digital news. © 2023 ACM.

关键词： Transparency

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：