检索结果-内蒙古大学图书馆

26th ACM Conference on computer-Supported Cooperative Work and Social computing, CSCW 2023

作者： Hansson, Karin Bardzell, Shaowen Bhandari, Aparajita Boulicault, Marion Doyle, Dylan Thomas Erete, Sheena Cerratto Pargman, Teresa Lazem, Shaimaa Muller, Michael Normark, Maria Petterson, Adrian Rosén, Anton Poikolainen Taylor, Alex S. Thomas, Jakita O. Watson, Julia Södertörn University The School of Natural Sciences Technology and Environmental Studies Sweden Georgia Institute of Technology The School of Interactive Computing United States Cornell University Department of Communication United States University of Edinburgh Department of Philosophy United States University of Colorado Boulder Department of Information Science United States University of Maryland College of Information United States Stockholm University The Department of Computer and Systems Sciences Sweden City for Scientific Research and Technological Applications The Informatics Research Institute Egypt Ibm Research Human Centered Ai United States Uppsala University Department of Informatics and Media Sweden University of Toronto Faculty of Information Canada Aalto University The School of Arts Design and Architecture Finland City University of London The Centre for Human Computer Interaction Design United Kingdom Auburn University Department of Computer Science and Software Engineering United States University of Toronto Department of Computer Science Canada

ISBN: (纸本)9798400701290

This one-day hybrid workshop builds on previous feminist CSCW workshops to explore feminist theoretical and methodological approaches that have provided us with useful tools to see things differently and make space for change. Since its inception over a decade ago, feminist HCI has progressed from the margins to mainstream HCI, with numerous references in the literature. Feminist HCI has also evolved to incorporate other critical HCI practices such as Queer HCI, participatory design, and speculative design. While feminist approaches have grown in popularity and become mainstream, it is getting more difficult to distinguish the feminist emancipatory core from other attempts of developing and improving society in various ways. In this workshop, we therefore want to revisit our feminist roots, where theory is a liberatory and creative practice, motivated by affect, curiosity, and wonder. From this standpoint, we consider which of our feminist tools can make a significant difference today, in a highly datafied world. The goal of this workshop is to;1) create an inventory of feminist theories and concepts that have had an impact on our work as designers, educators, researchers, and activists;2) develop a feminist toolbox for the CSCW community to strengthen our feminist literacy. © 2023 Owner/Author.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

Embarrassingly Simple Scribble Supervision for 3D Medical Segmentation

arXiv

引用

arXiv 2024年

作者： Gotkowski, Karol Lüth, Carsten Jäger, Paul F. Ziegler, Sebastian Krämer, Lars Denner, Stefan Xiao, Shuhan Disch, Nico Maier-Hein, Klaus H. Isensee, Fabian Division of Medical Image Computing DKFZ Heidelberg Germany Helmholtz Imaging DKFZ Heidelberg Germany Interactive Machine Learning Group DKFZ Heidelberg Germany Medical Faculty Heidelberg University of Heidelberg Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Germany

Traditionally, segmentation algorithms require dense annotations for training, demanding significant annotation efforts, particularly within the 3D medical imaging field. Scribble-supervised learning emerges as a possible solution to this challenge, promising a reduction in annotation efforts when creating large-scale datasets. Recently, a plethora of methods for optimized learning from scribbles have been proposed, but have so far failed to position scribble annotation as a beneficial alternative. We relate this shortcoming to two major issues: 1) the complex nature of many methods which deeply ties them to the underlying segmentation model, thus preventing a migration to more powerful state-of-the-art models as the field progresses and 2) the lack of a systematic evaluation to validate consistent performance across the broader medical domain, resulting in a lack of trust when applying these methods to new segmentation problems. To address these issues, we propose a comprehensive scribble supervision benchmark consisting of seven datasets covering a diverse set of anatomies and pathologies imaged with varying modalities. We furthermore propose the systematic use of partial losses, i.e. losses that are only computed on annotated voxels. Contrary to most existing methods, these losses can be seamlessly integrated into state-of-the-art segmentation methods, enabling them to learn from scribble annotations while preserving their original loss formulations. Our evaluation using nnU-Net reveals that while most existing methods suffer from a lack of generalization, the proposed approach consistently delivers state-of-the-art performance. Thanks to its simplicity, our approach presents an embarrassingly simple yet effective solution to the challenges of scribble supervision. Source code as well as our extensive scribble benchmarking suite will be made publicly available upon publication. © 2024, CC BY.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Translation Effectiveness of Offset Heart Rate Biofeedback as a Mindless Intervention for Alcohol Craving Among Risky Drinkers: Controlled Experiment

引用

JMIR Formative Research 2024年 8卷 e54438页

作者： Zhao, Yiran Arora, Jatin Tao, Yujie Miller, Dave B. Adams, Alexander T. Choudhury, Tanzeem Department of Information Science Cornell University New York NY United States Department of Computer Science Stanford University Stanford CA United States Department of Mechanical Engineering Tufts University Medford MA United States School of Interactive Computing Georgia Institute of Technology Atlanta GA United States

Background: Digital and wearable intervention systems promise to improve how people manage their behavioral health conditions by making interventions available when the user can best benefit from them. However, existing interventions are obtrusive because they require attention and motivation to engage in, limiting the effectiveness of such systems in demanding contexts, such as when the user experiences alcohol craving. Mindless interventions, developed by the human-computer interaction community, offer an opportunity to intervene unobtrusively. Offset heart rate biofeedback is an iconic type of mindless intervention powered by entrainment and can mitigate the physiological and psychological response to stressors. Objective: This work aimed to characterize the translational effectiveness of offset heart rate biofeedback on cue-elicit alcohol craving among risky drinkers. Methods: We conducted an out-of-lab, between-group, controlled experiment with 26 participants who performed harmful or hazardous drinking. The control group served as negative control and received no intervention, while the experimental group received offset heart rate biofeedback during alcohol exposure and recovery. We elicited alcohol cravings through a series of alcohol cues, including performing mental imagery, viewing alcohol images, and sniffing alcohol. We measured the physiological response to alcohol (ie, heart rate variability), self-reported craving, and self-reported anxiety. We constructed linear mixed-effects models to understand the effect of intervention during alcohol exposure and alcohol recovery after exposure. Following the linear mixed effect model, we conducted pair-wise comparisons for measures between the control and experimental groups. Results: We found that offset heart rate biofeedback significantly reduced the increase in heart rate variability (P=.01 and P=.052) and self-reported craving (P=.04 and P=.02) in response to alcohol cues. Participants’ anxiety was not aff

关键词： alcohol craving digital intervention entrainment mindless intervention offset heart rate biofeedback risky drinking wearable device

来源：评论

学校读者我要写书评

暂无评论

Work of the Unemployed: An inquiry into individuals’ experience of data usage in public services and possibilities for their agency 21

Work of the Unemployed: An inquiry into individuals’ experi...

引用

Designing interactive Systems Conference 2021

作者： Naja Holten Holten Møller Trine Rask Rask Nielsen Christopher Le Dantec Department of Computer Science University of Copenhagen Denmark School of Interactive Computing Georgia Institute of Technology United States

ISBN: (纸本)9781450384766

Public services increasingly presume a new and more active role for individuals to play in datafied society. While design efforts increasingly attempt to include stakeholders, such attempts are often limited to professional perspectives. Little is known about how individuals who are subject to these solutions experience the increasing use of data about them. One example of public services is job placement. Taking design fiction as our approach, we invited individuals enrolled in job placement (n=20) to reflect on the ‘work of the unemployed’, a fictive scenario where individuals make themselves eligible for support through sharing data. The fiction addresses power dynamics. The study shows how approaches, such as design fiction, are effective at including marginalized communities through changing the conditions for design. Showcasing the fictional outlook, and how the ‘design experience’ can be disempowering if not qualified through a deeper critique, the paper contributes to agendas on design justice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pre-trained Sentence Embeddings for Implicit Discourse Relation Classification

arXiv

引用

arXiv 2022年

作者： Balusu, Murali Raghu Babu Ji, Yangfeng Eisenstein, Jacob School of Interactive Computing Georgia Institute of Technology AtlantaGA United States Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States

Implicit discourse relations bind smaller linguistic units into coherent texts. Automatic sense prediction for implicit relations is hard, because it requires understanding the semantics of the linked arguments. Furthermore, annotated datasets contain relatively few labeled examples, due to the scale of the phenomenon: on average each discourse relation encompasses several dozen words. In this paper, we explore the utility of pre-trained sentence embeddings as base representations in a neural network for implicit discourse relation sense classification. We present a series of experiments using both supervised end-to-end trained models and pre-trained sentence encoding techniques - SkipThought, Sent2vec and Infersent. The pre-trained embeddings are competitive with the end-to-end model, and the approaches are complementary, with combined models yielding significant performance improvements on two of the three evaluations. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Error-aware policy learning: Zero-shot generalization in partially observable dynamic environments

arXiv

引用

arXiv 2021年

作者： Kumar, Visak Chadalavada Vijay Ha, Sehoon Liu, C. Karen School of Interactive Computing Georgia Institute of Technology United States Computer Science Department Stanford University United States

Simulation provides a safe and efficient way to generate useful data for learning complex robotic tasks. However, matching simulation and real-world dynamics can be quite challenging, especially for systems that have a large number of unobserved or unmeasurable parameters, which may lie in the robot dynamics itself or in the environment with which the robot interacts. We introduce a novel approach to tackle such a sim-to-real problem by developing policies capable of adapting to new environments, in a zero-shot manner. Key to our approach is an error-aware policy (EAP) that is explicitly made aware of the effect of unobservable factors during training. An EAP takes as input the predicted future state error in the target environment, which is provided by an error-prediction function, simultaneously trained with the EAP. We validate our approach on an assistive walking device trained to help the human user recover from external pushes. We show that a trained EAP for a hip-torque assistive device can be transferred to different human agents with unseen biomechanical characteristics. In addition, we show that our method can be applied to other standard RL control tasks. © 2021, CC BY.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

μ-Phone: Accessible Microscope Attachment for Smartphones

μ-Phone: Accessible Microscope Attachment for Smartphones

引用

International Workshop on Wearable and Implantable Body Sensor Networks (BSN)

作者： Kefan Song Sixuan Wu Ruijia Peng Jason Cobb Alexander T Adams Wallace H. Coulter Department of Biomedical Engineering Georgia Institute of Technology Atlanta GA USA School of Interactive Computing Georgia Institute of Technology Atlanta GA USA School of Computer Science Georgia Institute of Technology Atlanta GA USA Renal Medicine Emory University School of Medicine Atlanta GA USA

ISBN: (数字)9798331530143

ISBN: (纸本)9798331530150

Point-of-care (POC) technologies have the potential to greatly improve the clinical lab testing and diagnostics process since they significantly reduce the wait time before getting the results. Microscope, as a very important instrument widely used in clinical testing, is a key component to be adapted to POC scenarios, and there have been various attempts to do so by replacing conventional microscopes with smartphone-attached systems. However, these attempts all utilized components that are either expensive or bulky, which greatly limits the widespread adaptation and utilization of these devices, especially in areas with limited resources. Thus we propose a design and prototype of $\mu$ -Phone, an accessible microscope attachment for smartphones using cheap and easily accessible components to minimize the obstacles to resource availability. The proposed system has a depth of field of 5.25 micrometers, a pixel resolution of 26.3 pixels per micrometer and a spatial resolution of 2.19 micrometers, which makes it powerful enough to capture microscopic images for identification and analysis at a cellular level. With some future developments, this system has great potential to be deployed worldwide for quick and accurate POC analysis of physiological samples.

关键词： Micrometers Optical microscopy Red blood cells Microscopy Ultraviolet sources Prototypes Production Spatial resolution Smart phones Testing

来源：评论

学校读者我要写书评

暂无评论

Residual Physics Learning and System Identification for Sim-to-real Transfer of Policies on Buoyancy Assisted Legged Robots

Residual Physics Learning and System Identification for Sim-...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Nitish Sontakke Hosik Chae Sangjoon Lee Tianle Huang Dennis W. Hong Sehoon Hal School of Interactive Computing Georgia Institute of Technology Atlanta GA USA Department of Mechanical and Aerospace Engineering Los Angeles (UCLA) University of California Los Angeles CA USA Department of Computer Science Los Angeles (UCLA) University of California Los Angeles CA USA

The light and soft characteristics of Buoyancy Assisted Lightweight Legged Unit (BALLU) robots have a great potential to provide intrinsically safe interactions in environments involving humans, unlike many heavy and rigid robots. However, their unique and sensitive dynamics impose challenges to obtaining robust control policies in the real world. In this work, we demonstrate robust sim-to-real transfer of control policies on the BALLU robots via system identification and our novel residual physics learning method, Environment Mimic (EnvMimic). First, we model the nonlinear dynamics of the actuators by collecting hardware data and optimizing the simulation parameters. Rather than relying on standard supervised learning formulations, we utilize deep reinforcement learning to train an external force policy to match real-world trajectories, which enables us to model residual physics with greater fidelity. We analyze the improved simulation fidelity by comparing the simulation trajectories against the real-world ones. We finally demonstrate that the improved simulator allows us to learn better walking and turning policies that can be successfully deployed on the hardware of BALLU.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Overcoming common flaws in the evaluation of selective classification systems 24

Overcoming common flaws in the evaluation of selective class...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jeremias Traub Till J. Bungert Carsten T. Lüth Michael Baumgartner Klaus H. Maier-Hein Lena Maier-Hein Paul F. Jäger German Cancer Research Center (DKFZ) Heidelberg Interactive Machine Learning Group Germany and Helmholtz Imaging DKFZ Heidelberg Germany German Cancer Research Center (DKFZ) Heidelberg Interactive Machine Learning Group Germany and Helmholtz Imaging DKFZ Heidelberg Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany Helmholtz Imaging DKFZ Heidelberg Germany and DKFZ Heidelberg Division of Medical Image Computing (MIC) Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany Helmholtz Imaging DKFZ Heidelberg Germany and DKFZ Heidelberg Division of Medical Image Computing (MIC) Germany and Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany and National Center for Tumor Diseases (NCT) Heidelberg Helmholtz Imaging DKFZ Heidelberg Germany and DKFZ Heidelberg Division of Intelligent Medical Systems (IMSY) Germany and Faculty of Mathematics and Computer Science University of Heidelberg Germany and National Center for Tumor Diseases (NCT) Heidelberg

ISBN: (纸本)9798331314385

Selective Classification, wherein models can reject low-confidence predictions, promises reliable translation of machine-learning based classification systems to real-world scenarios such as clinical diagnostics. While current evaluation of these systems typically assumes fixed working points based on pre-defined rejection thresholds, methodological progress requires benchmarking the general performance of systems akin to the AUROC in standard classification. In this work, we define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, interpretability, and flexibility, and show how current approaches fail to meet them. We propose the Area under the Generalized Risk Coverage curve (AUGRC), which meets all requirements and can be directly interpreted as the average risk of undetected failures. We empirically demonstrate the relevance of AUGRC on a comprehensive benchmark spanning 6 data sets and 13 confidence scoring functions. We find that the proposed metric substantially changes metric rankings on 5 out of the 6 data sets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning

arXiv

引用

arXiv 2021年

作者： Alabdulkarim, Amal Li, Winston Martin, Lara J. Riedl, Mark O. School of Interactive Computing Georgia Institute of Technology United States Computer and Information Science University of Pennsylvania United States

The advent of large pre-trained generative language models has provided a common framework for AI story generation via sampling the model to create sequences that continue the story. However, sampling alone is insufficient for story generation. In particular, it is hard to direct a language model to create stories to reach a specific goal event. We present two automated techniques grounded in deep reinforcement learning and reward shaping to control the plot of computer-generated stories. The first utilizes proximal policy optimization to fine-tune an existing transformer-based language model to generate text continuations but also be goal-seeking. The second extracts a knowledge graph from the unfolding story, which is used by a policy network with graph attention to select a candidate continuation generated by a language model. We report on automated metrics pertaining to how often stories achieve a given goal event as well as human participant rankings of coherence and overall story quality compared to baselines and ablations. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

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：