检索结果-内蒙古大学图书馆

Object search by a concept-conditioned object detector

Neural Computing and Applications 2024年第26期36卷 16001-16021页

作者： Rigoni, Davide Serafini, Luciano Sperduti, Alessandro Department of Mathematics "Tullio Levi-Civita" University of Padova Via Trieste 63 PD Padua35131 Italy Human Inspired Technology Research Centre University of Padova Via Luzzatti 4 PD Padua35121 Italy Augmented Intelligence Center Bruno Kessler Foundation Via Sommarive 18 TN Povo38123 Italy Department of Pharmaceutical and Pharmacological Sciences University of Padova Via Marzolo 5 PD Padua35131 Italy Department of Information Engineering and Computer Science University of Trento Via Sommarive 9 TN Povo38123 Italy

Object detectors are used for searching all objects belonging to a pre-defined set of categories contained in a given picture. However, users are often not interested in finding all objects, but only those that pertain to a small set of categories or concepts. Nowadays, the standard approach to solve this task involves initially employing an object detector to identify all objects within the image, followed by refining the outcomes to retain only the ones of interest. Nevertheless, the object detector does not take advantage of the user’s prior intent that, when used, can potentially improve the detection performance of the model. This work presents a method to condition an existing object detector with the user’s intent, encoded as one or more concepts from the WordNet graph, to find just those objects of interest. The proposed approach takes advantage of existing datasets for object detection without the need for new annotations, and it allows to adapt the already existing object detector models with minor changes. The evaluation, performed on the COCO and the Visual Genome datasets considering several object detector architectures, shows that conditioning the search on concepts is actually beneficial. The code and the pre-trained model weights are released at: https://***/drigoni/Concept-Conditioned-Object-Detector. © The Author(s) 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

What Makes Im Users (Un)Responsive: An Empirical Investigation for Understanding Im Responsiveness

SSRN

引用

SSRN 2022年

作者： Lee, Hao-Ping Chiang, Yi-Shyuan Chou, Yu-Ling Lin, Kung-Pai Chang, Yung-Ju Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Department of Computer Science University of Illinois Urbana-Champaign UrbanaIL United States

Instant messaging (IM) communication has been widely studied due to its prevalence in our everyday communication. Numerous factors that contribute to (un)responsiveness have been identified. Yet an integrated view of the factors that influence IM responsiveness remains absent. This paper reports qualitative findings from interviews with 46 IM users, and identifies five main elements underlying IM users’ response decisions: response habits, need fulfillment, perceived obligation, perceived readiness/suitability, and pace/rhythm coordination. To the best of our knowledge, this is the first integrated view of the key elements underlying IM responsiveness. Among these elements, we particularly highlight that regarding the influence of contextual factors on IM responsiveness, what may matters more is IM users’ perceptions of their readiness and suitability of the contexts, rather than the contexts’ objective properties. We also uncovered pace/rhythm coordination as a crucial factor behind IM responsiveness, which has been little discussed in the literature. Responsiveness, as our findings show, was often not a consequence, but a manifestation, of users’ pursuit of specific responsiveness-related aims such as ongoing shaping and sustaining of a dyad’s pace and rhythm. © 2022, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Co-Speech Gesture for Multimodal Aphasia Type Detection

arXiv

引用

arXiv 2023年

作者： Lee, Daeun Son, Sejung Jeon, Hyolim Kim, Seungbae Han, Jinyoung Department of Applied Artificial Intelligence Sungkyunkwan University Seoul Korea Republic of Department of Human-AI Interaction Sungkyunkwan University Seoul Korea Republic of Department of Computer Science & Engineering University of South Florida TampaFL United States

Aphasia, a language disorder resulting from brain damage, requires accurate identification of specific aphasia types, such as Broca’s and Wernicke’s aphasia, for effective treatment. However, little attention has been paid to developing methods to detect different types of aphasia. Recognizing the importance of analyzing co-speech gestures for distinguish aphasia types, we propose a multimodal graph neural network for aphasia type detection using speech and corresponding gesture patterns. By learning the correlation between the speech and gesture modalities for each aphasia type, our model can generate textual representations sensitive to gesture information, leading to accurate aphasia type detection. Extensive experiments demonstrate the superiority of our approach over existing methods, achieving state-of-the-art results (F1 84.2%). We also show that gesture features outperform acoustic features, highlighting the significance of gesture expression in detecting aphasia types. We provide the codes for reproducibility purposes1 Copyright © 2023, The Authors. All rights reserved.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

User-Driven Value Alignment: Understanding Users’ Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions

arXiv

引用

arXiv 2024年

作者： Fan, Xianzhe Xiao, Qing Zhou, Xuhui Pei, Jiaxin Sap, Maarten Lu, Zhicong Shen, Hong Tsinghua University Beijing China Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Language Technologies Institute Carnegie Mellon University PittsburghPA United States Stanford University StanfordCA United States Department of Computer Science George Mason University FairfaxVA United States

Large language model-based AI companions are increasingly viewed by users as friends or romantic partners, leading to deep emotional bonds. However, they can generate biased, discriminatory, and harmful outputs. Recently, users are taking the initiative to address these harms and re-align AI companions. We introduce the concept of user-driven value alignment, where users actively identify, challenge, and attempt to correct AI outputs they perceive as harmful, aiming to guide the AI to better align with their values. We analyzed 77 social media posts about discriminatory AI statements and conducted semi-structured interviews with 20 experienced users. Our analysis revealed six common types of discriminatory statements perceived by users, how users make sense of those AI behaviors, and seven user-driven alignment strategies, such as gentle persuasion and anger expression. We discuss implications for supporting user-driven value alignment in future AI systems, where users and their communities have greater agency. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synthesizing world models for bilevel planning

arXiv

引用

arXiv 2025年

作者： Ahmed, Zergham Tenenbaum, Joshua B. Bates, Christopher J. Gershman, Samuel J. Department of Computer Science Harvard University United States Department of Brain and Cognitive Sciences MIT United States Institute for Human and Machine Cognition Harvard University United States Department of Psychology Center for Brain Science Harvard University United States

Modern reinforcement learning (RL) systems have demonstrated remarkable capabilities in complex environments, such as video games. However, they still fall short of achieving human-like sample efficiency and adaptability when learning new domains. Theory-based reinforcement learning (TBRL) is an algorithmic framework specifically designed to address this gap. Modeled on cognitive theories, TBRL leverages structured, causal world models—"theories"—as forward simulators for use in planning, generalization and exploration. Although current TBRL systems provide compelling explanations of how humans learn to play video games, they face several technical limitations: their theory languages are restrictive, and their planning algorithms are not scalable. To address these challenges, we introduce TheoryCoder, an instantiation of TBRL that exploits hierarchical representations of theories and efficient program synthesis methods for more powerful learning and planning. TheoryCoder equips agents with general-purpose abstractions (e.g., "move to"), which are then grounded in a particular environment by learning a low-level transition model (a Python program synthesized from observations by a large language model). A bilevel planning algorithm can exploit this hierarchical structure to solve large domains. We demonstrate that this approach can be successfully applied to diverse and challenging grid-world games, where approaches based on directly synthesizing a policy perform poorly. Ablation studies demonstrate the benefits of using hierarchical abstractions. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Passive Variable Impedance Control Strategy with Viscoelastic Parameters Estimation of Soft Tissues for Safe Ultrasonography

arXiv

引用

arXiv 2023年

作者： Beber, Luca Lamon, Edoardo Nardi, Davide Fontanelli, Daniele Saveriano, Matteo Palopoli, Luigi Department of Industrial Engineering Università di Trento Trento Italy Department of Information Engineering and Computer Science Università di Trento Trento Italy Human-Robot Interfaces and Interaction Istituto Italiano di Tecnologia Genoa Italy

In the context of telehealth, robotic approaches have proven a valuable solution to in-person visits in remote areas, with decreased costs for patients and infection risks. In particular, in ultrasonography, robots have the potential to reproduce the skills required to acquire high-quality images while reducing the sonographer’s physical efforts. In this paper, we address the control of the interaction of the probe with the patient’s body, a critical aspect of ensuring safe and effective ultrasonography. We introduce a novel approach based on variable impedance control, allowing the real-time optimisation of compliant controller parameters during ultrasound procedures. This optimisation is formulated as a quadratic programming problem and incorporates physical constraints derived from viscoelastic parameter estimations. Safety and passivity constraints, including an energy tank, are also integrated to minimise potential risks during human-robot interaction. The proposed method’s efficacy is demonstrated through experiments on a patient’s dummy torso, highlighting its potential for achieving safe behaviour and accurate force control during ultrasound procedures, even in cases of contact loss. Copyright © 2023, The Authors. All rights reserved.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Congenital hydrocephalus:a review of recent advances in genetic etiology and molecular mechanisms

引用

Military Medical Research 2024年第6期11卷 942-958页

作者： Xiu-Yun Liu Xin Song Marek Czosnyka Chiara Robba Zofia Czosnyka Jennifer Lee Summers Hui-Jie Yu Guo-Yi Gao Peter Smielewski Fang Guo Mei-Jun Pang Dong Ming Medical School Tianjin UniversityTianjin 300072China State Key Laboratory of Advanced Medical Materials and Devices Tianjin UniversityTianjin 300072China Haihe Laboratory of Brain-Computer Interaction and Human-Machine Integration Tianjin 300380China School of Pharmaceutical Science and Technology Tianjin University300072 TianjinChina Department of Clinical Neurosciences Addenbrooke’s HospitalUniversity of CambridgeCambridge CB20QQUK San Martino Policlinico Hospital IRCCS for Oncology and Neuroscience16132 GenoaItaly Department of Anesthesiology and Critical Care Medicine Johns Hopkins UniversityBaltimoreMD 21287USA Department of Neurosurgery Tianjin Medical University General HospitalTianjin 300052China Department of Neurosurgery Beijing Tiantan HospitalCapital Medical UniversityBeijing 100070China Department of Neurosurgery Tianjin Huanhu HospitalTianjin 300350China

The global prevalence rate for congenital hydrocephalus(CH)is approximately one out of every five hundred births with multifaceted predisposing factors at *** influences stand as a major contributor to CH pathogenesis,and epidemiological evidence suggests their involvement in up to 40%of all cases observed *** about an individual’s genetic susceptibility can significantly improve prognostic precision while aiding clinical decision-making ***,the precise genetic etiology has only been pinpointed in fewer than 5%of human *** occurrences of CH cases are required for comprehensive gene sequencing aimed at uncovering additional potential genetic loci.A deeper comprehension of its underlying genetics may offer invaluable insights into the molecular and cellular basis of this brain *** review provides a summary of pertinent genes identified through gene sequencing technologies in humans,in addition to the 4 genes currently associated with CH(2 X-linked genes L1CAM and AP1S2,2 autosomal recessive MPDZ and CCDC88C).Others predominantly participate in aqueduct abnormalities,ciliary movement,and nervous system *** prospective CH-related genes revealed through animal model gene-editing techniques are further outlined,focusing mainly on 4 pathways,namely cilia synthesis and movement,ion channels and transportation,Reissner’s fiber(RF)synthesis,cell apoptosis,and ***,the proper functioning of motile cilia provides significant impulsion for cerebrospinal fluid(CSF)circulation within the brain ventricles while mutations in cilia-related genes constitute a primary cause underlying this *** far,only a limited number of CH-associated genes have been identified in *** integration of genotype and phenotype for disease diagnosis represents a new trend in the medical *** models provide insights into the pathogenesis of CH and contribute to our understanding of its association w

关键词： Congenital hydrocephalus Genetic disease Central system Cilia Ventricle

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Method to Survey with Protecting Privacy yet Maintaining Accuracy 18th

A Lightweight Method to Survey with Protecting Privacy yet...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Wang, Yuxuan Di, Xinyu Liu, Ningbo Zhang, Xianchao Ren, Wei School of Computer Science China University of Geosciences Wuhan China Department of Computer Science University of Toronto TorontoONM5S 1A1 Canada International College Chongqing University of Technology Chongqing China Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province Jiaxing University Jiaxing China Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing University Jiaxing China Ministry of Education Chengdu China State Key Laboratory of Geo-Information Engineering and Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of MNR CASM Beijing China

ISBN: (纸本)9783031714665

In a survey, a lot of questions and answers are listed and participators will select one of the answers for each question. Sometimes, participators may not be willing to select the preferred one item in the answers because the item may damage the privacy of themselves. If this question is not answered, then it reveals that the question or the answers are sensitive, which also damages the privacy. Besides, each participator may have distinct privacy concerns even for the same questions and answers, thus the privacy-aware questions and answers cannot be determined and be removed in advance. Thus, the dilemma is how to select the answers for privacy-aware questions yet maintain the utility of the answering results in the survey. In this paper, we propose a general method to protect the various privacy in the investigation without the knowledge of privacy to be protected in advance. The main idea is that participators can randomly select answers if the privacy is the concern for themselves in the answers for this question. Our method is lightweight so as to be convenient in practices. We extensively analyze the accuracy of survey results to justify that our method can protect the privacy yet maintain the utility of the investigation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Variable Selection for the Prediction of TSS, pH and TA of Intact Berries of Thompson Seedless Grapes from their NIS Reflection 30

Variable Selection for the Prediction of TSS, pH and TA of I...

引用

30th International Conference on Software, Telecommunications and computer Networks, SoftCOM 2022

作者： Chariskou, Chrysanthi Bazinas, Christos Daniels, Andries J. Opara, Umezuruike L. Nieuwoudt, Helene H. Kaburlasos, Vassilis G. Human-Machines Interaction Lab International Hellenic University Department of Computer Science Kavala Greece University of Stellenbosch Department of Viticulture and Oenology Stellenbosch South Africa University of Stellenbosch Faculty of AgriSciences Department of Horticultural Sciences Postharvest Technology Research Stellenbosch South Africa Institute for Wine Biotechnology University of Stellenbosch Department of Viticulture and Oenology Stellenbosch South Africa

ISBN: (数字)9789532901177

ISBN: (纸本)9789532901177

Wavenumbers of high absolute value of correlation coefficient to Total Soluble Solids (TSS), pH, or Titratable Acidity (TA) were selected from reflection Fourier transform near infrared (FT -NIR) spectra of intact grape berries of the white variety Thompson Seedless. Multiple linear regression (MLR) and partial least squares (PLS) regression were applied to the spectra to construct trained regression models able to predict TSS, pH, and TA. Square Pearson's correlation coefficient (R2) and the Mean Square Error (MSE) were used to evaluate the precision of prediction. TSS content was predicted with R2 score of 0.972 and MSE 0.094 using MLR and with R2 0.926 and MSE 0.223 using PLS regression. The pH prediction scores were R2 0.812 and MSE 0.002 with MLR. With PLS regression the values were R2 0.485 and MSE 0.004. TA can be predicted only from the second derivatives of the spectra. MLR produced R2 for prediction 0.745 and MSE 0.076, while the scores using PLS regression were R2 0.648 and MSE 0.114. It was concluded that variable selection could greatly improve the prediction accuracy. The appropriateness of the two regression methods depends on the structure of the spectra dataset and on the characteristics whose prediction is sought. © 2022 University of Split, FESB.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

SpeechMirror: A Multimodal Visual Analytics System for Personalized Reflection of Online Public Speaking Effectiveness

arXiv

引用

arXiv 2023年

作者： Huang, Zeyuan He, Qiang Maher, Kevin Deng, Xiaoming Lai, Yu-Kun Ma, Cuixia Qin, Sheng-Feng Liu, Yong-Jin Wang, Hongan The Beijing Key Laboratory of Human-Computer Interaction Institute of Software Chinese Academy of Sciences and also with the School of Computer Science and Technology University of Chinese Academy of Sciences China Diatom Design Limited Liability Company United States The School of Computer Science and Informatics Cardiff University United Kingdom The School of Design Northumbria University United Kingdom The Department of Computer Science and Technology MOE-Key Laboratory of Pervasive Computing Tsinghua University China

As communications are increasingly taking place virtually, the ability to present well online is becoming an indispensable skill. Online speakers are facing unique challenges in engaging with remote audiences. However, there has been a lack of evidence-based analytical systems for people to comprehensively evaluate online speeches and further discover possibilities for improvement. This paper introduces SpeechMirror, a visual analytics system facilitating reflection on a speech based on insights from a collection of online speeches. The system estimates the impact of different speech techniques on effectiveness and applies them to a speech to give users awareness of the performance of speech techniques. A similarity recommendation approach based on speech factors or script content supports guided exploration to expand knowledge of presentation evidence and accelerate the discovery of speech delivery possibilities. SpeechMirror provides intuitive visualizations and interactions for users to understand speech factors. Among them, SpeechTwin, a novel multimodal visual summary of speech, supports rapid understanding of critical speech factors and comparison of different speech samples, and SpeechPlayer augments the speech video by integrating visualization of the speaker's body language with interaction, for focused analysis. The system utilizes visualizations suited to the distinct nature of different speech factors for user comprehension. The proposed system and visualization techniques were evaluated with domain experts and amateurs, demonstrating usability for users with low visualization literacy and its efficacy in assisting users to develop insights for potential improvement. Copyright © 2023, The Authors. All rights reserved.

关键词： Modal analysis

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：