检索结果-内蒙古大学图书馆

2025 CHI Conference on human Factors in Computing Systems, CHI EA 2025

作者： Muller, Michael Chilton, Lydia B. Maher, Mary Lou Martin, Charles Patrick Choi, Minsik Walsh, Greg Kantosalo, Anna Human AI Collaboration IBM Research Cambridge MA United States Computer Science Department Columbia University New York NY United States University of North Carolina at Charlotte Charlotte NC United States School of Computing Australian National University Canberra Australia Digital Whimsy Lab. University of Baltimore Baltimore MD United States Siili Solutions Helsinki Finland University of Helsinki Helsinki Finland

ISBN: (纸本)9798400713958

This workshop applies human centered themes to a new and powerful technology, generative artificial intelligence (AI), and - among other approaches - particularly to Large Language Models (LLMs) and Foundation Models (FMs). Unlike AI systems that produce decisions or descriptions, generative AI systems can produce new and creative content that can include images, texts, music, video, code, and other forms of design. The results are often similar to results produced by humans. However, it is not yet clear how humans make sense of generative AI algorithms or their outcomes. It is also not yet clear how humans can control and more generally, interact with, these powerful capabilities in ethical ways. Finally, it is not clear what kinds of collaboration patterns will emerge when creative humans and creative technologies work together. Following successful workshops in 2022–2024, we convene the interdisciplinary research domain of generative AI and HCI. Participation is open to seasoned scholars and early career researchers. We solicit descriptions of completed projects, works-in-progress, and provocations. Together we will develop theories and practices in this intriguing new domain. © 2025 Copyright held by the owner/author(s).

关键词： Bias Design Ethics Generative AI HCAI HCI Large language models Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Multi-tasking Dialogue Comprehension with Discourse Parsing 35

Multi-tasking Dialogue Comprehension with Discourse Parsing

引用

35th Pacific Asia Conference on Language, Information and Computation, PACLIC 2021

作者： He, Yuchen Zhang, Zhuosheng 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 MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Multi-party dialogue machine reading comprehension (MRC) raises an even more challenging understanding goal on dialogue with more than two involved speakers, compared with the traditional plain passage style MRC. To accurately perform the question-answering (QA) task according to such multi-party dialogue, models have to handle fundamentally different discourse relationships from common non-dialogue plain text, where discourse relations are supposed to connect two far apart utterances in a linguistics-motivated way. To further explore the role of such unusual discourse structure on the correlated QA task in terms of MRC, we propose the first multi-task model for jointly performing QA and discourse parsing (DP) on the multi-party dialogue MRC task. Our proposed model is evaluated on the latest benchmark Molweni, whose results indicate that training with complementary tasks indeed benefits not only QA task, but also DP task itself. We further find that the joint model is distinctly stronger when handling longer dialogues which again verifies the necessity of DP in the related MRC. © Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation, PACLIC 2021.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GenAICHI 2023: Generative AI and HCI at CHI 2023

GenAICHI 2023: Generative AI and HCI at CHI 2023

引用

Extended Abstracts of the 2023 CHI Conference on human Factors in Computing Systems, CHI EA 2023

作者： Muller, Michael Chilton, Lydia B. Kantosalo, Anna Liao, Q. Vera Maher, Mary Lou Martin, Charles Patrick Walsh, Greg Human Ai Collaboration Ibm Research CambridgeMA United States Computer Science Department Columbia University New YorkNY United States University of Helsinki Siili Solutions Helsinki Finland Microsoft Research MontrealQC Canada University of North Carolina at Charlotte CharlotteNC United States School of Computing The Australian National University Canberra Australia Digital Whimsy Lab University of Baltimore BaltimoreMD United States

ISBN: (纸本)9781450394222

This workshop applies human centered themes to a new and powerful technology, generative artificial intelligence (AI). Unlike AI systems that produce decisions or descriptions, generative AI systems can produce new and creative content that can include images, texts, music, video, code, and other forms of design. The results are often similar to results produced by humans. However, it is not yet clear how humans make sense of generative AI algorithms or their outcomes. It is also not yet clear how humans can control and more generally, interact with, these powerful capabilities in ethical ways. Finally, it is not clear what kinds of collaboration patterns will emerge when creative humans and creative technologies work together. Following a successful workshop in 2022, we convene the interdisciplinary research domain of generative AI and HCI. Participation in this invitational workshop is open to seasoned scholars and early career researchers. We solicit descriptions of completed projects, works-in-progress, and provocations. Together we will develop theories and practices in this intriguing new domain. © 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

StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

arXiv

引用

arXiv 2023年

作者： Ma, Yifeng Wang, Suzhen Hu, Zhipeng Fan, Changjie Lv, Tangjie Ding, Yu Deng, Zhidong Yu, Xin Department of Computer Science and Technology BNRist THUAI State Key Laboratory of Intelligent Technology and Systems Tsinghua University China Virtual Human Group Netease Fuxi AI Lab China Zhejiang University China University of Technology Sydney Australia

Different people speak with diverse personalized speaking styles. Although existing one-shot talking head methods have made significant progress in lip sync, natural facial expressions, and stable head motions, they still cannot generate diverse speaking styles in the final talking head videos. To tackle this problem, we propose a one-shot style-controllable talking face generation framework. In a nutshell, we aim to attain a speaking style from an arbitrary reference speaking video and then drive the one-shot portrait to speak with the reference speaking style and another piece of audio. Specifically, we first develop a style encoder to extract dynamic facial motion patterns of a style reference video and then encode them into a style code. Afterward, we introduce a style-controllable decoder to synthesize stylized facial animations from the speech content and style code. In order to integrate the reference speaking style into generated videos, we design a style-aware adaptive transformer, which enables the encoded style code to adjust the weights of the feed-forward layers accordingly. Thanks to the style-aware adaptation mechanism, the reference speaking style can be better embedded into synthesized videos during decoding. Extensive experiments demonstrate that our method is capable of generating talking head videos with diverse speaking styles from only one portrait image and an audio clip while achieving authentic visual effects. Project Page: https://***/FuxiVirtualhuman/styletalk. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Hierarchical generative modelling for autonomous robots

arXiv

引用

arXiv 2023年

作者： Yuan, Kai Sajid, Noor Friston, Karl Li, Zhibin Embodied AI Lab Intel Labs Germany Wellcome Centre for Human Neuroimaging Queen Square Institute of Neurology University College London United Kingdom Department of Computer Science UCL Robotics Institute University College London United Kingdom

humans can produce complex whole-body motions when interacting with their surroundings, by planning, executing and combining individual limb movements. We investigated this fundamental aspect of motor control in the setting of autonomous robotic operations. We approach this problem by hierarchical generative modelling equipped with multi-level planning—for autonomous task completion—that mimics the deep temporal architecture of human motor control. Here, temporal depth refers to the nested time scales at which successive levels of a forward or generative model unfold, for example, delivering an object requires a global plan to contextualise the fast coordination of multiple local movements of limbs. This separation of temporal scales also motivates robotics and control. Specifically, to achieve versatile sensorimotor control, it is advantageous to hierarchically structure the planning and low-level motor control of individual limbs. We use numerical and physical simulation to conduct experiments and to establish the efficacy of this formulation. Using a hierarchical generative model, we show how a humanoid robot can autonomously complete a complex task that necessitates a holistic use of locomotion, manipulation, and grasping. Specifically, we demonstrate the ability of a humanoid robot that can retrieve and transport a box, open and walk through a door to reach the destination, approach and kick a football, while showing robust performance in presence of body damage and ground irregularities. Our findings demonstrated the effectiveness of using human-inspired motor control algorithms, and our method provides a viable hierarchical architecture for the autonomous completion of challenging goal-directed tasks. © 2023, CC BY.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Exploiting aliasing for manga restoration

arXiv

引用

arXiv 2021年

作者： Xie, Minshan Xia, Menghan Wong, Tien-Tsin Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology SIAT CAS

As a popular entertainment art form, manga enriches the line drawings details with bitonal screentones. However, manga resources over the Internet usually show screentone artifacts because of inappropriate scanning/rescaling resolution. In this paper, we propose an innovative twostage method to restore quality bitonal manga from degraded ones. Our key observation is that the aliasing induced by downsampling bitonal screentones can be utilized as informative clues to infer the original resolution and screentones. First, we predict the target resolution from the degraded manga via the Scale Estimation Network (SENet) with spatial voting scheme. Then, at the target resolution, we restore the region-wise bitonal screentones via the Manga Restoration Network (MR-Net) discriminatively, depending on the degradation degree. Specifically, the original screentones are directly restored in pattern-identifiable regions, and visually plausible screentones are synthesized in pattern-agnostic regions. Quantitative evaluation on synthetic data and visual assessment on real-world cases illustrate the effectiveness of our method. Copyright © 2021, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Augmented reality and robotics in education: A systematic literature review

Computers in Human Behavior: Artificial Humans

引用

computers in human Behavior: Artificial humans 2025年 4卷

作者： Christina Pasalidou Chris Lytridis Avgoustos Tsinakos Nikolaos Fachantidis Laboratory of Informatics & Robotic Applications in Education and Society Department of Educational and Social Policy University of Macedonia Thessaloniki Greece Human-Machines Interaction (HUMAIN) Lab Department of Computer Science Democritus University of Thrace Kavala Greece Advanced Educational Technologies and Mobile Applications (AETMA) Lab Department of Computer Science Democritus University of Thrace Kavala Greece

Integrating cutting-edge technologies into education has been a continuous goal to enhance teaching and learning experiences. Augmented Reality (AR) and robotics are two emerging technologies that have shown promise in transforming educational environments. This paper presents a systematic review of the literature on the combination of AR and robotics for educational purposes, identifying key applications, benefits, and trends. Using the PRISMA methodology, 69 relevant studies from five major databases were analysed and categorised into three themes: (a) AR and Socially Assistive Robots (SAR), (b) AR-assisted educational robotics, and (c) AR in robotics/engineering education. The review provides insights into how different AR-enhanced robotics applications across primary, secondary, and higher education, provide visualizations, multimodal feedback, and immersive experiences. Key findings suggest that while interactive features of AR and the embodiment of robots show promising results for learning, fostering motivation, excitement, positive attitudes, and enriched educational experiences, challenges such as technological complexity and cost remain barriers to widespread adoption. Future research should focus on pedagogical frameworks and large-scale implementations to optimize AR-robotics integration in diverse educational settings.

关键词： Robotics Augmented reality HRI Education

来源：评论

学校读者我要写书评

暂无评论

Video Face Clustering with Self-Supervised Representation Learning

IEEE Transactions on Biometrics, Behavior, and Identity Scie...

引用

IEEE Transactions on Biometrics, Behavior, and Identity science 2020年第2期2卷 145-157页

作者： Sharma, Vivek Tapaswi, Makarand Saquib Sarfraz, M. Stiefelhagen, Rainer Department of Informatics Institute for Anthropomatics and Robotics Computer Vision for Human-Computer Interaction Lab Karlsruhe Institute of Technology Karlsruhe76131 Germany University of Toronto TorontoONM5S 3G4 Canada Massachusetts Institute of Technology CambridgeMA02139 United States Vector Institute TorontoON Canada Inria Paris75012 France

Characters are a key component of understanding the story conveyed in TV series and movies. With the rise of advanced deep face models, identifying face images may seem like a solved problem. However, as face detectors get better, clustering and identification need to be revisited to address increasing diversity in facial appearance. In this paper, we propose unsupervised methods for feature refinement with application to video face clustering. Our emphasis is on distilling the essential information, identity, from the representations obtained using deep pre-trained face networks. We propose a self-supervised Siamese network that can be trained without the need for video/track based supervision, that can also be applied to image collections. We evaluate our methods on three video face clustering datasets. Thorough experiments including generalization studies show that our methods outperform current state-of-the-art methods on all datasets. The datasets and code are available at https://***/vivoutlaw/SSIAM. © 2019 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Sq-Swin: Siamese Quadratic Swin Transformer for Lettuce Browning Prediction

SSRN

引用

SSRN 2023年

作者： Wang, Dayang Zhang, Boce Xu, Yongshun Luo, Yaguang Yu, Hengyong Department of Electrical and Computer Engineering University of Massachusetts LowellMA United States Department of Food Science and Human Nutrition University of Florida GainesvilleFL United States Food Quality Lab Environmental Microbial and Food Safety Lab Agricultural Research Service United States Department of Agriculture Beltsville MD20705 United States

Enzymatic browning is a major quality defect of packaged "ready-to-eat" fresh-cut lettuce salads. While there have been many research and breeding efforts to counter this problem, progress is hindered by the lack of a technology to identify and quantify browning rapidly, objectively, and reliably. Here, we report a deep learning model for lettuce browning prediction. To the best of our knowledge, it is the first-of-its-kind on deep learning for lettuce browning prediction using a pretrained Siamese Quadratic Swin (SQ-Swin) transformer with several highlights. First, our model includes quadratic features in the transformer model which is more powerful to incorporate real world representations than the linear transformer. Second, a multi-scale training strategy is proposed to augment the data and explore more of the inherent self-similarity of the lettuce images. Third, the proposed model uses a siamese architecture which learns the inter-relations among the limited training samples. Fourth, the model is pretrained on the ImageNet and then trained with the reptile meta-learning algorithm to learn higher-order gradients than a regular one. Experiment results on the fresh-cut lettuce datasets show that the proposed SQ-Swin outperforms the traditional methods and other deep learning-based backbones. © 2023, The Authors. All rights reserved.

关键词： Lettuce

来源：评论

学校读者我要写书评

暂无评论

Advances and challenges in unsupervised neural machine translation 16

Advances and challenges in unsupervised neural machine trans...

引用

16th Conference of the European Chapter of the Associationfor Computational Linguistics: Tutorials, EACL 2021

作者： Wang, Rui Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781954085039

Unsupervised cross-lingual language representation initialization methods, together with mechanisms such as denoising and back-translation, have advanced unsupervised neural machine translation (UNMT), which has achieved impressive results. Meanwhile, there are still several challenges for UNMT. This tutorial first introduces the background and the latest progress of UNMT. We then examine a number of challenges to UNMT and give empirical results on how well the technology currently holds up1 © 2020 Association for Computational Linguistics.

关键词： Neural machine translation

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：