检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wu, Shuchen Alaniz, Stephan Schulz, Eric Akata, Zeynep Explainable Machine Learning Lab Helmholtz Munich Germany Max Planck Institute for Biological Cybernetics Germany Munich Center for Machine Learning Germany Department of Computer Science Technical University of Munich Germany Institute for Human-Centered AI Helmholtz Munich Germany

Understanding neural networks is challenging due to their high-dimensional, interacting components. Inspired by human cognition, which processes complex sensory data by chunking it into recurring entities, we propose leveraging this principle to interpret artificial neural population activities. Biological and artificial intelligence share the challenge of learning from structured, naturalistic data, and we hypothesize that the cognitive mechanism of chunking can provide insights into artificial systems. We first demonstrate this concept in recurrent neural networks (RNNs) trained on artificial sequences with imposed regularities, observing that their hidden states reflect these patterns, which can be extracted as a dictionary of chunks that influence network responses. Extending this to large language models (LLMs) like LLaMA, we identify similar recurring embedding states corresponding to concepts in the input, with perturbations to these states activating or inhibiting the associated concepts. By exploring methods to extract dictionaries of identifiable chunks across neural embeddings of varying complexity, our findings introduce a new framework for interpreting neural networks, framing their population activity as structured reflections of the data they process. © 2025, CC BY.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

Theory of Mind Abilities Predict Robot's Gaze Effects on Object Preference

引用

IEEE Transactions on Affective Computing 2025年

作者： Manzi, Federico Ishikawa, Mitsuhiko Dio, Cinzia Di Itakura, Shoji Kanda, Takayuki Ishiguro, Hiroshi Massaro, Davide Marchetti, Antonella Università Cattolica del Sacro Cuore Research Unit on Theory of Mind Department of Psychology Milan Italy Università Cattolica del Sacro Cuore Research Unit in Psychology and Robotics in the Lifespan Department of Psychology Milan Italy IRCCS Fondazione Don Carlo Gnocchi Milan Italy Hitotsubashi University Hitotsubashi Institute for Advanced Study Japan Ritsumeikan University Kyoto Japan Kyoto University Department of Computer Science Human-Robot Interaction Laboratory Kyoto Japan IRC'HIL Keihana Science City Advanced Telecommunications Research Institute International Kyoto Japan Osaka University Department of Intelligent Systems Toyonaka Japan

This study investigated the differences between human and robot gaze in influencing preference formation, and examined the role of Theory of Mind (ToM) abilities in this process. human eye gaze is one of the most important sources of information for social interaction and research has demonstrated its effectiveness in influencing people's preference. With increasing technological development, we will interact with robots that can exhibit gaze behavior and influence people's preference. It is unclear whether there are any differences between humans and robots in this process. The present study aimed to analyze the role of the gaze of a robot and a human in influencing the ascription of a preference to the gazer and the participants' preference. Furthermore, we examined the role of ToM abilities in preference formation. The results showed that the gaze has a greater effect on the gazer preference compared to participants' preference regardless of the agent (human or robot). In addition, ToM abilities predict both gazer and individual preferences in the robot's condition only even though different socio-cognitive mechanisms are involved. The study suggests that adults are cognitively able to process the gaze of a robot similar to a human, recognizing the underlying mental state. However, only for the robot, different cognitive mechanisms are involved in the gazer (i.e., perspective taking) and participants' preference formation (i.e., advanced ToM). © 2010-2012 IEEE.

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

Automated Facial Expression Recognition and Age Estimation Using Deep Learning

引用

computers, Materials & Continua 2022年第6期71卷 5235-5252页

作者： Syeda Amna Rizwan Yazeed Yasin Ghadi Ahmad Jalal Kibum Kim Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Computer Science and Software Engineering Al Ain UniversityAbu Dhabi122612UAE Department of Human-Computer Interaction Hanyang UniversityAnsan15588Korea

With the advancement of computer vision techniques in surveillance systems,the need for more proficient,intelligent,and sustainable facial expressions and age recognition is *** main purpose of this study is to develop accurate facial expressions and an age recognition system that is capable of error-free recognition of human expression and age in both indoor and outdoor *** proposed system first takes an input image pre-process it and then detects faces in the entire *** that landmarks localization helps in the formation of synthetic face mask prediction.A novel set of features are extracted and passed to a classifier for the accurate classification of expressions and age *** proposed system is tested over two benchmark datasets,namely,the Gallagher collection person dataset and the Images of Groups *** system achieved remarkable results over these benchmark datasets about recognition accuracy and computational *** proposed system would also be applicable in different consumer application domains such as online business negotiations,consumer behavior analysis,E-learning environments,and emotion robotics.

关键词： Feature extraction face expression model local transform features and recurrent neural network(RNN)

来源：评论

学校读者我要写书评

暂无评论

Evaluating the effectiveness of spatial memory in 2D and 3D physical and virtual environments 02

Evaluating the effectiveness of spatial memory in 2D and 3D ...

引用

SIGCHI Conference on human Factors in Computing Systems: Changing our World, Changing Ourselves, CHI '02

作者： Cockburn, Andy McKenzie, Bruce Department of Computer Science Human-Computer Interaction Lab University of Canterbury Christchurch New Zealand

ISBN: (纸本)1581134533

User interfaces can improve task performance by exploiting the powerful human capabilities for spatial cognition. This opportunity has been demonstrated by many prior experiments. It is tempting to believe that providing greater spatial flexibility-by moving from flat 2D to 3D user interfaces-will further enhance user performance. This paper describes an experiment that investigates the effectiveness of spatial memory in real-world physical models and in equivalent computer-based virtual systems. The different models vary the user's freedom to use depth and perspective in spatial arrangements of images representing web pages. Results show that the subjects' performance deteriorated in both the physical and virtual systems as their freedom to locate items in the third dimension increased. Subjective measures reinforce the performance measures, indicating that users found interfaces with higher dimensions more 'cluttered' and less efficient.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Markerless Sagittal Gait Analysis of Cerebral Palsy in Children Using Pose Estimation Techniques

Markerless Sagittal Gait Analysis of Cerebral Palsy in Child...

引用

Innovation in Computing and Engineering (ICE), International Conference on

作者： Vinay Kumar Vats Chandra Prakash Amandeep Kaur Rajesh Kumar Computer Science and Engineering National Institute of Technology Delhi India Computational Intelligence and Smart Motion Research (CISMR) Lab SVNIT Surat India Malaviya National Institute of Technology Jaipur India Department of Human Anatomy and Physiology Faculty of Health Sciences University of Johannesburg Johannesburg South Africa

ISBN: (数字)9798350380460

ISBN: (纸本)9798350380477

Cerebral Palsy (CP) is a neurological disorder affecting children’s motor function and posture. Early detection and monitoring of Cerebral palsy is crucial for effective intervention and improved quality of life. Gait analysis is a critical tool for assessing motor function in children with cerebral palsy, often requiring controlled environments and markers for accuracy. Markerless gait analysis has emerged as a promising tool for objectively evaluating gait abnormalities in children with CP. In this study, we propose a markerless methodology utilising pose estimation to analyse gait patterns from sagittal video recordings captured in unconstrained environments. The dataset consists of 49 children, including 10 typically developing children and 39 with cerebral palsy, focusing on side-view videos for the analysis. Given the motor disabilities of these children, conducting gait analysis in a constrained environment can alter their natural walking patterns, making our approach particularly advantageous. Then we identify the key gait events, heel strike and toe-off, to distinguish gait between cycles by tracing knee joint movements. This technique demonstrates the potential for practical, non-invasive gait assessment in natural settings, offering insights into the distinct gait characteristics of children with cerebral palsy compared to their typically developing peers.

关键词： Legged locomotion Neurological diseases Cerebral palsy Technological innovation Pose estimation Motors Motion control Gait recognition Video recording Monitoring

来源：评论

学校读者我要写书评

暂无评论

Threefolded motion perception during immersive walkthroughs 14

Threefolded motion perception during immersive walkthroughs

引用

20th ACM Symposium on Virtual Reality Software and Technology, VRST 2014

作者： Bruder, Gerd Steinicke, Frank Human-Computer Interaction Department of Computer Science University of Hamburg Germany

ISBN: (纸本)9781450332538

Locomotion is one of the most fundamental processes in the real world, and its consideration in immersive virtual environments (IVEs) is of major importance for many application domains requiring immersive walkthroughs. From a simple physics perspective, such self-motion can be defined by the three components speed, distance, and time. Determining motions in the frame of reference of a human observer imposes a significant challenge to the perceptual processes in the human brain, and the resulting speed, distance, and time percepts are not always veridical. In previous work in the area of IVEs, these components were evaluated in separate experiments, i. e., using largely different hardware, software and protocols. In this paper we analyze the perception of the three components of locomotion during immersive walkthroughs using the same setup and similar protocols. We conducted experiments in an Oculus Rift head-mounted display (HMD) environment which showed that subjects largely underestimated virtual distances, slightly underestimated virtual speed, and we observed that subjects slightly overestimated elapsed time. Copyright © 2014 by the Association for Computing Machinery, Inc (ACM).

关键词： Helmet mounted displays

来源：评论

学校读者我要写书评

暂无评论

TOUCHSCREEN FIELD SPECIFICATION FOR PUBLIC-ACCESS DATABASE QUERIES - LET YOUR FINGERS DO THE WALKING 90

引用

18TH ANNUAL CONF OF THE ASSOC FOR COMPUTING MACHINERY ON computer science : COOPERATION ( CSC 90 )

作者： SEARS, A KOCHAVY, Y SHNEIDERMAN, B Human-Computer Interaction Laboratory Department of Computer Science University of Maryland College Park Maryland

ISBN: (纸本)0897913485

Database query is becoming a common task in public access systems; touchscreens can provide an appealing interface for such a system. This paper explores three interfaces for constructing queries on alphabetic field values with a touchscreen interface; including a QWERTY keyboard, an Alphabetic keyboard, and a Reduced Input Data Entry (RIDE) interface. The RIDE interface allows field values to be entered with fewer “keystrokes” (touches) than either keyboard while eliminating certain errors. In one test database, the RIDE interface required 69% fewer keystrokes than either keyboard interface.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Efficacy of Immersive Virtual Reality Combined With Multisensor Biofeedback on Chronic Pain in Fibromyalgia: A Pilot Randomized Controlled Trial

ACR Open Rheumatology

引用

ACR Open Rheumatology 2025年第5期7卷 e70048页

作者： Chittaro, Luca Longhino, Simone Serafini, Marta Cacioppo, Sofia Quartuccio, Luca Human-Computer Interaction Lab Department of Mathematics Computer Science and Physics University of Udine Udine Italy Rheumatology Division Department of Medicine University of Udine Udine Italy Rheumatology Division Department of Medicine University of Udine and Azienda Sanitaria Universitaria Friuli Centrale Udine Italy

Objective: Fibromyalgia (FM) is a syndrome marked by chronic pain, fatigue, and mood disorders. Nonpharmacologic strategies are recommended to avoid overuse of opioids or nonsteroidal anti-inflammatory drugs, but current approaches often provide limited relief. This study aimed to preliminarily assess the efficacy and feasibility of a new combined intervention of immersive virtual reality with multisensor biofeedback (IVR-BF) in FM management. Methods: In this single-center, pilot, open-label, randomized controlled trial, adult patients with FM were randomly assigned 1:1 to either the treatment (TR) group, receiving IVR-BF immediately, or a waitlist control (WL) group, receiving IVR-BF after the TR group completed treatment. The primary outcome was reduction in visual analog scale (VAS) pain scores in the TR group, after five IVR-BF sessions, compared to the WL group, after the waiting period. Secondary outcomes included improvements in FM impact (FM Impact Questionnaire [FIQ] score) and qualitative aspect of pain (Short-form McGill Pain Questionnaire [SF-MPQ] score). A longitudinal analysis was conducted across all patients to examine the trends in VAS pain, SF-MPQ, and FIQ score during the trial. Results: Fifty patients were screened, and 20 female patients (10 TR and 10 WL) completed the trial and were analyzed. Those in the TR group showed significantly lower VAS pain scores compared to those in the WL group (P = 0.011), along with significant improvement in the FIQ score (P = 0.018). The longitudinal analysis revealed progressive improvements in VAS pain, SF-MPQ, and FIQ score, supported by physiologic improvements (heart rate variability, respiratory rate, skin conductance). No significant safety concerns were reported. Patients expressed a high level of satisfaction with the IVR experience. Conclusion: IVR-BF is a feasible treatment that shows potential in reducing pain and improving quality of life in patients with FM, supporting the need for larger trials t

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysing mouse and pen flick gestures 02

Analysing mouse and pen flick gestures

引用

3rd ACM SIGCHI NZ Symposium on computer-human interaction, CHINZ 2002

作者： Moyle, Michael Cockburn, Andy Human-Computer Interaction Lab. Department of Computer Science University of Canterbury Christchurch New Zealand

ISBN: (纸本)0473085003

Gesture based interfaces promise to increase the efficiency of user input, particularly in mobile computing where standard input devices such as the mouse and keyboard are impractical. This paper describes an investigation into the low-level physical properties of linear 'flick' gestures that users create using mouse and pen input devices. The study was motivated by our need to determine sensible constraints on values such as the magnitude, timing, and angular accuracy of gestures for a marking-menu implementation. The results show that pen gestures are substantially larger than mouse gestures, that angular errors are larger in the left and right directions with the pen, that vertical gestures are 'awkward' with the mouse, and that downwards gestures are approximately 11% slower than other directions. © 2002 ACM.

关键词： Knobs

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Mirror: Designing an Interactive Tool to Promote Self-Reflection for YouTube Recommendations

arXiv

引用

arXiv 2025年

作者： Kondo, Yui Dunnell, Kevin Xiao, Qing Zhao, Jun Rocher, Luc Oxford Internet Institute University of Oxford United Kingdom MIT Media Lab Massachusetts Institute of Technology United States Human-Computer Interaction Institute Carnegie Mellon University United States Department of Computer Science University of Oxford United Kingdom

Big Data analytics and Artificial Intelligence systems derive non-intuitive and often unverifiable inferences about individuals’ behaviors, preferences, and private lives. Drawing on diverse, feature-rich datasets of unpredictable value, these systems erode the intuitive connection between our actions and how we are perceived, diminishing control over our digital identities. While Explainable Artificial Intelligence scholars have attempted to explain the inner workings of algorithms, their visualizations frequently overwhelm end-users with complexity. This research introduces ‘hypothetical inference’—a novel approach that uses language models to simulate how algorithms might interpret users’ digital footprints and infer personal characteristics without requiring access to proprietary platform algorithms. Through empirical studies with fourteen adult participants, we identified three key design opportunities to foster critical algorithmic literacy: (1) reassembling scattered digital footprints into a unified map, (2) simulating algorithmic inference through LLM-generated interpretations, and (3) incorporating temporal dimensions to visualize evolving patterns. This research lays the groundwork for tools that can help users recognize the influence of data on platforms and develop greater autonomy in increasingly algorithm-mediated digital environments. Copyright © 2025, The Authors. All rights reserved.

关键词： Video 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：