检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Yiyang Huang, Xinting Bi, Wei Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China NLP Center Tencent AI-Lab Hong Kong

Multi-party dialogues are more difficult for models to understand than one-to-one two-party dialogues, since they involve multiple interlocutors, resulting in interweaving reply-to relations and information flows. To step over these obstacles, an effective way is to pre-train a model that understands the discourse structure of multi-party dialogues, namely, to whom each utterance is replying. However, due to the lack of explicitly annotated discourse labels in multi-party dialogue corpora, previous works fail to scale up the pre-training process by putting aside the unlabeled multi-party conversational data for nothing. To fully utilize the unlabeled data, we propose to treat the discourse structures as latent variables, then jointly infer them and pre-train the discourse-aware model by unsupervised latent variable inference methods. Experiments on multiple downstream tasks show that our pre-trained model outperforms strong baselines by large margins and achieves state-of-the-art (SOTA) results, justifying the effectiveness of our method. The official implementation of this paper is available at https://***/EricLee8/MPD_EMVI. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HCILab at Memotion 2.0 2022: Analysis of Sentiment, Emotion and Intensity of Emotion Classes from Meme Images using Single and Multi Modalities 1

HCILab at Memotion 2.0 2022: Analysis of Sentiment, Emotion ...

引用

1st Workshop on Multimodal Fact-Checking and Hate Speech Detection, DE-FACTIFY 2022

作者： Nguyen, Thanh Tin Pham, Nhat Truong Nguyen, Ngoc Duy Nguyen, Hai Nguyen, Long H. Kim, Yong-Guk Human Computer Interaction Lab Department of Computer Engineering Sejong University Seoul Korea Republic of Division of Computational Mechatronics Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam Institute for Intelligent Systems Research and Innovation Deakin University Victoria Australia Khoury College of Computer Sciences Northeastern University Boston United States Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam

Nowadays, memes found on internet are overwhelming. Although they are innocuous and sometimes entertaining, there exist memes that contain sarcasm, offensive, or motivational feelings. In this study, several approaches are proposed to solve the multiple modality problem in analysing the given meme dataset. The imbalance issue has been addressed by using a new Auto Augmentation method and the uncorrelation issue has been mitigated by adopting deep Canonical Correlation Analysis to find the most correlated projections of visual and textual feature embedding. In addition, both stacked attention and multi-hop attention network are employed to efficiently generate aggregated features. As a result, our team, i.e. HCILab, achieved a weighted F1 score of 0.4995 for sentiment analysis, 0.7414 for emotion classification, and 0.5301 for scale/intensity of emotion classes on the leaderboard. This results are obtained by using concatenation between image and text model and our code can be found at https://***/JMRa8. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (***)

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Case Study of human-AI interactions Using Transparent AI-Driven Autonomous Systems for Improved human-AI Trust Factors 3

A Case Study of Human-AI Interactions Using Transparent AI-D...

引用

3rd IEEE International Conference on human-Machine Systems, ICHMS 2022

作者： Pham, Daniel Menon, Vineetha Tenhundfeld, Nathan Weger, Kristin Mesmer, Bryan Gholston, Sampson Davis, Thomas The University of Alabama in Huntsville Department of Computer Science HuntsvilleAL United States The University of Alabama in Huntsville Department of Psychology HuntsvilleAL United States The University of Alabama in Huntsville Department of Iseem HuntsvilleAL United States Human Systems Integration Division Devcom Data and Analysis Center HuntsvilleAL United States

ISBN: (数字)9781665452380

ISBN: (纸本)9781665452380

human interactions with Artificial Intelligence (AI) have become a ubiquitous phenomenon in our society. It plays a major role in defense and espionage in the context of AI-based autonomous systems such as drones and ground robots that are sent to the front lines to navigate terrains, map the surroundings, and identify adversaries in the environment. In these types of scenarios, hostages may be spread out over a larger geographical area. Reliance on ground vision alone may not only be obscured and insufficient but also can expose soldiers or human rescuers to danger. Since time is of great essence, such an intense situation calls for decisions to be made swiftly and efficiently as the lives of hostages are at stake. This makes such a scenario ideal to evaluate the effectiveness of an AI-driven drone autonomous system for combat search and rescue (CSAR) missions. Here the focus is to gather information about the operational environment (detect hostages and other targets-of-interest) in a short amount of time that spans a varying geographic terrain. This allows for targeted rescue operations with AI-informed decision-making outcomes to ensure that the rescuers at ground level can be directed along the most optimal path, and casualties will be either minimized or entirely averted. In this work, we study the feasibility of our drone-based AI target detection autonomous system to evaluate the classification accuracy of multi-view targets-of-interest in the CSAR environment. The overarching goal of this study is to understand the role of AI-driven autonomous systems as an assistive support tool for efficient, swift and accurate decision making, navigating a complex and ever-changing environment, and identification of targets. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Benefits of the Immersive Space to Think

Evaluating the Benefits of the Immersive Space to Think

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Lee Lisle Xiaoyu Chen J.K. Edward Gitre Chris North Doug A. Bowman Department of Computer Science Center for Human-Computer Interaction Grado Department of Industrial and Systems Engineering Virginia Tech Department of History Virginia Tech Center for Human-Computer Interaction

ISBN: (数字)9781728165325

ISBN: (纸本)9781728165332

Sensemaking with large multimedia dataset is a cognitively intensive task that requires analysts to understand the underlying stories that the dataset tells. Often, analysts use tools in order to offload cognition as well as convey their new understanding of the dataset; however, existing tools are limited by their underlying technologies. We have proposed a novel virtual reality tool to support sensemaking called the Immersive Space to Think (IST). IST can aid the process of analyzing multimedia data, but it remains unproven whether IST improves sensemaking performance over a traditional desktop setting. In a study performed over six weeks, one participant used both IST and traditional methods of sensemaking with a dataset of 100 text documents of transcribed survey responses from World War 2 soldiers to perform historical analysis. The participant was asked guided questions that produced three essays with their understanding of the data. After conducting a blind evaluation of the participant’s interpretation of the data, a team of three experts in historical analysis concluded that the essays written with IST displayed a better understanding of the dataset. Furthermore, the participant gave positive feedback on IST, and also suggested possible improvements.

关键词： Tools Visualization Task analysis human computer interaction Virtual reality Three-dimensional displays Information analysis

来源：评论

学校读者我要写书评

暂无评论

Event-Guided Attention Network for Low Light Image Enhancement

Event-Guided Attention Network for Low Light Image Enhanceme...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Qiaobin Wang Haiyan Jin Haonan Su Zhaolin Xiao Department of Computer Science and Engineering Engineering Research Center Shaanxi Key Laboratory for Network Computing and Security Technology Human-Machine Integration Intelligent Robot Shaanxi University Xi'an University of Technology

In the low-light conditions, images are corrupted by low contrast and severe noise, but event cameras can capture event streams with clear edge structures. Therefore, we propose an Event-Guided Attention Network for Low-light Image Enhancement (EGAN) using a dual branch Network and recover clear structure with the guide of events. To overcome the lack of paired training datasets, we first synthesize the dataset containing low-light event streams, low-light images, and the ground truth (GT) normal-light images. Then, we develop an end-to-end dual branch network consisting of a Image Enhancement Branch (IEB) and a Gradient Reconstruction Branch (GRB). The GRB branch reconstructs image gradients using events, and the IEB enhances low-light images using reconstructed gradients. Moreover, we develops the Attention based Event-Image Feature Fusion Module (AEIFFM) which selectively fuses the event and low-light image features using the spatial and channel attention mechanism, and the fused features are concatenated into the IEB and GRB, which respectively generate the enhanced images with clear structure and more accurate gradient images. Extensive experiments on synthetic and real datasets demonstrate that the proposed EGAN produces visually more appealing enhancement images, and achieves a good performance in structure preservation and denoising over state-of-the-arts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fractal scaling and the aesthetics of trees

arXiv

引用

arXiv 2024年

作者： Gao, Jingyi Newberry, Mitchell University of Wisconsin Madison Department of Computer Science United States University of New Mexico Department of Biology United States University of Michigan Center for the Study of Complex Systems United States Max Planck Institute for Evolutionary Anthropology Department of Human Behaviour Ecology and Culture Germany

Trees in works of art have stirred emotions in viewers for millennia. Leonardo da Vinci described geometric proportions in trees to provide both guidelines for painting and insights into tree form and function. Da Vinci’s Rule of trees further implies fractal branching with a particular scaling exponent α = 2 governing both proportions between the diameters of adjoining boughs and the number of boughs of a given diameter. Contemporary biology increasingly supports an analogous rule with α = 3 known as Murray’s Law. Here we relate trees in art to a theory of proportion inspired by both da Vinci and modern tree physiology. We measure α in 16th century Islamic architecture, Edo period Japanese painting and 20th century European art, finding α in the range 1.5 to 2.5. We find that both conformity and deviations from ideal branching create stylistic effect and accommodate constraints on design and implementation. Finally, we analyze an abstract tree by Piet Mondrian which forgoes explicit branching but accurately captures the modern scaling exponent α = 3, anticipating Murray’s Law by 15 years. This perspective extends classical mathematical, biological and artistic ways to understand, recreate and appreciate the beauty of trees. © 2024, CC BY-SA.

关键词： Fractals

来源：评论

学校读者我要写书评

暂无评论

Redundancy-aware unsupervised ranking based on game theory - application to gene enrichment analysis

arXiv

引用

arXiv 2022年

作者： Balestra, Chiara Maj, Carlo Müller, Emmanuel Mayr, Andreas Department of Computer Science TU Dortmund Germany University Hospital of Bonn Germany Center for Human Genetics University Hospital of Marburg Germany

Gene set collections are a common ground to study the enrichment of genes for specific phenotypic traits. Gene set enrichment analysis aims to identify genes that are over-represented in gene sets collections and might be associated with a specific phenotypic trait. However, as this involves a massive number of hypothesis testing, it is often questionable whether a pre-processing step to reduce gene sets collections' sizes is helpful. Moreover, the often highly overlapping gene sets and the consequent low interpretability of gene sets' collections demand for a reduction of the included gene sets. Inspired by this bioinformatics context, we propose a method to rank sets within a family of sets based on the distribution of the singletons and their size. We obtain sets' importance scores by computing Shapley values without incurring into the usual exponential number of evaluations of the value function. Moreover, we address the challenge of including a redundancy awareness in the rankings obtained where, in our case, sets are redundant if they show prominent intersections. We finally evaluate our approach for gene sets collections;the rankings obtained show low redundancy and high coverage of the genes. The unsupervised nature of the proposed ranking does not allow for an evident increase in the number of significant gene sets for specific phenotypic traits when reducing the size of the collections. However, we believe that the rankings proposed are of use in bioinformatics to increase interpretability of the gene sets collections and a step forward to include redundancy into Shapley values computations. Copyright © 2022, The Authors. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Left inferior parietal lobe and auditory cortex jointly contribute to sound knowledge retrieval

引用

Brain Stimulation 2025年第4期18卷 1037-1047页

作者： Kuhnke, Philipp Numssen, Ole Voeller, Johannah Cheung, Vincent K.M. Weise, Konstantin Kiefer, Markus Hartwigsen, Gesa Wilhelm Wundt Institute for Psychology Leipzig University Germany Research Group Cognition and Plasticity Max Planck Institute for Human Cognitive and Brain Sciences (MPI CBS) Leipzig Germany Methods and Development Group Brain Networks MPI CBS Leipzig Germany TMS Group Department of Neuroscience and Biomedical Engineering Aalto University Finland TMS Lab Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital Boston United States Department of Experimental Psychology University of Granada Spain Mind Brain and Behavior Research Center (CIMCYC) University of Granada Spain Sony Computer Science Laboratories Tokyo Japan Leipzig University of Applied Sciences HTWK Leipzig Germany Department of Psychiatry Ulm University Germany

Background: Conceptual knowledge is central to human cognition. Neuroimaging studies suggest that conceptual processing relies on the joint contribution of modality-specific perceptual-motor and multimodal brain regions. In particular, the multimodal left inferior parietal lobe (IPL) couples with auditory association cortex during sound knowledge retrieval and with somatomotor cortex during action feature retrieval. However, it remains unknown whether the interaction between modality-specific and multimodal cortices is causally relevant for conceptually-guided behavior. Methods: To tackle this issue, we applied offline transcranial magnetic stimulation (TMS) over modality-specific cortex (somatomotor, auditory, or sham), before 24 healthy participants received online TMS over multimodal cortex (IPL, or sham) during action and sound knowledge tasks on written words. For the first time in a TMS study on higher cognition, TMS targeting and dosing were optimized using individual a priori computational electric field simulations. Results: We found that combined stimulation of auditory association cortex and multimodal IPL selectively impaired sound judgments, but not action judgments, on low sound–low action words (BF₁₀ = 5.316). Unifocal TMS over auditory cortex or IPL alone did not disrupt behavior, suggesting adaptive compensatory plasticity. Conclusions: These results indicate that the joint contribution of multimodal IPL and auditory cortex is causally relevant for sound knowledge retrieval: The functional relevance of left IPL depends on the integrity of the auditory cortex, and vice versa, as single perturbation of either region did not disrupt performance. Our findings support “hybrid theories” of conceptual processing, which propose that task-dependent functional interactions between modality-specific and multimodal regions are crucial. © 2025 The Authors

关键词： Compensation Computational modeling Concepts Plasticity Semantics TMS

来源：评论

学校读者我要写书评

暂无评论

Developing a Research center for Artificial Intelligence in Medicine

Mayo Clinic Proceedings: Digital Health

引用

Mayo Clinic Proceedings: Digital Health 2024年第4期2卷 677-686页

作者： Langlotz, Curtis P. Kim, Johanna Shah, Nigam Lungren, Matthew P. Larson, David B. Datta, Somalee Li, Fei Fei Montine, Thomas J. Harrington, Robert A. Gold, Garry E. Departments of Radiology Medicine and Biomedical Data Science Center for Artificial Intelligence in Medicine and Imaging Stanford University Stanford CA United States Center for Artificial Intelligence in Medicine and Imaging Stanford University Stanford CA United States Departments of Medicine and Biomedical Data Science Center for Artificial Intelligence in Medicine and Imaging Stanford Health Care Stanford University Stanford CA United States Department of Radiology Stanford University Stanford CA United States Department of Computer Science Institute for Human Centered Artificial Intelligence Stanford University Stanford CA United States Department of Pathology Stanford University Stanford CA United States Office of the Dean Weill Cornell Medicine New York NY United States Microsoft Redmond WA United States Research Information Technology Stanford University School of Medicine Stanford CA United States Department of Psychiatry and Behavioral Sciences Stanford University School of Medicine Stanford CA United States

Artificial intelligence (AI) and machine learning (ML) are driving innovation in biosciences and are already affecting key elements of medical scholarship and clinical care. Many schools of medicine are capitalizing on the promise of these new technologies by establishing academic units to catalyze and grow research and innovation in AI/ML. At Stanford University, we have developed a successful model for an AI/ML research center with support from academic leaders, clinical departments, extramural grants, and industry partners. The center for Artificial Intelligence in Medicine and Imaging uses the following 4 key tactics to support AI/ML research: project-based learning opportunities that build interdisciplinary collaboration;internal grant programs that catalyze extramural funding;infrastructure that facilitates the rapid creation of large multimodal AI-ready clinical data sets;and educational and open data programs that engage the broader research community. The center is based on the premise that foundational and applied research are not in tension but instead are complementary. Solving important biomedical problems with AI/ML requires high-quality foundational team science that incorporates the knowledge and expertise of clinicians, clinician scientists, computer scientists, and data scientists. As AI/ML becomes an essential component of research and clinical care, multidisciplinary centers of excellence in AI/ML will become a key part of the scholarly portfolio of academic medical centers and will provide a foundation for the responsible, ethical, and fair implementation of AI/ML systems. © 2024 The Authors

关键词： AI artificial intelligence AIMI center Stanford center for Artificial Intelligence in Medicine and Imaging CT computed tomography EHR electronic health record FDA Food and Drug Administration HAI Stanford Institute for human centered Artificial Intelligence ML machine learning STARR Stanford Research Repository

来源：评论

学校读者我要写书评

暂无评论

FerroVibe: Towards a Modular Tactile Device

FerroVibe: Towards a Modular Tactile Device

引用

Telepresence, IEEE Conference on

作者： Harsimran Singh Luis Perez Marcilla Premankur Banerjee Michael Rothammer Thomas Hulin The Institute of Robotics and Mechatronics German Aerospace Center (DLR) Munich Germany Centre for Tactile Internet with Human-in-the-Loop (CeTI) Cluster of Excellence at TU Dresden Dresden Germany Department of Computer Science University of Southern California USA Hapticlabs Germany

ISBN: (数字)9798331528249

ISBN: (纸本)9798331528256

This paper presents the proof of concept of the modular nature of ferrofluid based tactile device, FerroVibe. The modularity of FerroVibe allows for customization in degrees of freedom, force feedback, and vibrational cues by strategically positioning magnetic actuators around the central assembly containing a neodymium magnet and ferrofluid. Three distinct configurations of FerroVibe are introduced, each offering unique actuation mechanisms and physical characteristics that could be tailored to different application requirements. The paper showcases the proof of concept and details the working principle of each configuration, highlighting the strengths and limitations of each design. Initial comparative analysis is conducted to evaluate the trade-offs in terms of power consumption, speed, size, weight, and feedback fidelity. The results demonstrate that FerroVibe’s potential modular architecture provides a flexible and effective solution for a wide range of tactile feedback applications, making it a promising candidate for future advancements in haptic technology.

关键词： Ferrofluid Actuators Telepresence Power demand Neodymium Force feedback Tactile sensors Magnetosphere Assembly

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：