检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Muth, Markus Peer, Marco Kleber, Florian Sablatnig, Robert Computer Vision Lab Institute of Visual Computing and Human-Centered Technology TU Wien Wien1040 Austria

ISBN: (纸本)9783031784941

In this paper, the usability of synthetic handwritten text to improve machine learning models is examined for the domain of handwritten text detection. We generate synthetic handwritten text by using an existing model based on a style conditioned GAN, and add those texts to scanned documents to mimic handwritten annotations. Object detection models (YOLOv5 and YOLOv8) are trained using synthetic data as a baseline to distinguish handwritten text from remaining content. We study different granularity labels (word-, line- and paragraph-level) and model sizes in our evaluation and show that applying those models to real data results in a mAP@50 of 0.88 and a pixel-level F1@50 of 0.96 for the CVL dataset, and a mAP@50 of 0.72 and F1@50 of 0.89 for SCAN, a custom dataset, created by adding real handwritten annotations to a scientific paper. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

[DC] Conversational Agents for Natural human-Computer Interaction in Virtual Reality

[DC] Conversational Agents for Natural Human-Computer Intera...

引用

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

作者： Matteo Bosco Institute of Visual Computing and Human-Centered Technology TU Wien Austria

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

With the emergence of large language models (LLMs), conversational agents (CAs) have gained significant attention across various domains, including virtual reality (VR). Although LLMs are capable of simulating human dialogue with impressive realism, interactions with LLM-powered CAs still appear unnatural and lack a human-like feel. This is primarily due to several key challenges, including limitations in the accuracy of speech recognition and the quality of speech synthesis. Furthermore, CAs need more autonomy and more natural turn-taking abilities to enable realistic and engaging interactions in VR. This position paper outlines my PhD research by discussing my motivation for improving CAs in VR environments, summarizing my previous work, and presenting my planned research directions.

关键词： human computer interaction Three-dimensional displays Large language models Conferences Natural languages Virtual reality Speech recognition Medical services Companies Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

RoboTeach: How Student Robots' Preexisting Proficiency and Learning Rate Affect human Teachers Demonstrating Object Placement 25

RoboTeach: How Student Robots' Preexisting Proficiency and L...

引用

Proceedings of the 2025 CHI Conference on human Factors in computing Systems

作者： Khaled Kassem Patrick Gietl Florian Michahelles Andrii Matviienko TU Wien Vienna Austria TU Wien Visual Computing & Human-centered Technology Vienna Austria KTH Royal Institute of Technology Stockholm Sweden

来源：评论

学校读者我要写书评

暂无评论

BEHAVE AI: BEst Practices and Guidelines for human-Centric Design and EvAluation of ProactiVE AI Agents 25

BEHAVE AI: BEst Practices and Guidelines for Human-Centric D...

引用

30th International Conference on Intelligent User Interfaces Companion, IUI 2025

作者： Kraus, Matthias Zepf, Sebastian Westhäußer, Rebecca Feustel, Isabel Zargham, Nima Aslan, Ilhan Edwards, Justin Mayer, Sven Kontogiorgos, Dimosthenis Wagner, Nicolas André, Elisabeth Human-Centered Artificial Intelligence Augsburg Germany LMU Munich Munich Germany Mercedes-Benz AG Boeblingen Baden-Wuerttemberg Germany Mercedes-Benz AG Böblingen Germany Institute of Communications Engineering Ulm University Ulm Germany Digital Media Lab University of Bremen Bremen Germany Human-Centered Computing Aalborg University Aalborg Denmark Learning and Educational Technology Lab University of Oulu Oulu Finland Massachusetts Institute of Technology CambridgeMA United States Otto-Friedrich-University Bamberg Bamberg Germany Human-Centered Artificial Intelligence Augsburg University Augsburg Germany

ISBN: (纸本)9798400714092

The last years have seen a significant rise in interest in highly autonomous and proactive agents fueled by the progress of AI. While there is various research on the design, implementation, and evaluation of proactive agents, there remains a critical gap in the methodologies used for both design and evaluation, which are largely informed by reactive system design principles. Our full-day multidisciplinary workshop brings together researchers and practitioners from the IUI community in academia and industry to understand the challenges of designing and evaluating proactive agents in a human-centric manner. We will reflect on existing evaluation methods, identify challenges in designing proactive systems, and discuss potential solutions, best practices, and human-centric guidelines to bridge these gaps. Ultimately, our goal is to map out key focus areas and research challenges, fostering strong interdisciplinary relationships within and across fields related to Artificial Intelligence (AI) and human-Computer Interaction (HCI). © 2025 Copyright held by the owner/author(s).

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

CapST: Leveraging Capsule Networks and Temporal Attention for Accurate Model Attribution in Deep-fake Videos

引用

ACM Transactions on Multimedia computing, Communications and Applications 2025年第4期21卷

作者： Ahmad, Wasim Peng, Yan-Tsung Chang, Yuan-Hao Ganfure, Gaddisa Olani Khan, Sarwar Social Networks and Human-Centered Computing Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei Taiwan Department of Computer Science National Chengchi University Taipei Taiwan Institute of Information Science Academia Sinica Taipei Taiwan Department of Computer Science Dire Dawa University Dire Dawa Ethiopia Social Networks and Human-Centered Computing Taiwan International Graduate Program Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan

Deep-fake videos, generated through AI face-swapping techniques, have garnered considerable attention due to their potential for impactful impersonation attacks. While existing research primarily distinguishes real from fake videos, attributing a deep-fake to its specific generation model or encoder is crucial for forensic investigation, enabling precise source tracing and tailored countermeasures. This approach not only enhances detection accuracy by leveraging unique model-specific artifacts but also provides insights essential for developing proactive defenses against evolving deep-fake techniques. Addressing this gap, this article investigates the model attribution problem for deep-fake videos using two datasets-Deepfakes from Different Models (DFDM) and GANGen-Detection, which comprise deep-fake videos and images generated by GAN models. We select only fake images from the GANGen-Detection dataset to align with the DFDM dataset, which specifies the goal of this study, focusing on model attribution rather than real/fake classification. This study formulates deep-fake model attribution as a multiclass classification task, introducing a novel Capsule-Spatial-Temporal (CapST) model that effectively integrates a modified VGG19 (utilizing only the first 26 out of 52 layers) for feature extraction, combined with Capsule Networks and a Spatio-Temporal attention mechanism. The Capsule module captures intricate feature hierarchies, enabling robust identification of deep-fake attributes, while a video-level fusion technique leverages temporal attention mechanisms to process concatenated feature vectors and capture temporal dependencies in deep-fake videos. By aggregating insights across frames, our model achieves a comprehensive understanding of video content, resulting in more precise predictions. Experimental results on the DFDM and GANGen-Detection datasets demonstrate the efficacy of CapST, achieving substantial improvements in accurately categorizing deep-fake videos

关键词： Computer forensics

来源：评论

学校读者我要写书评

暂无评论

Automatic object annotation in streamed and remotely explored large 3D reconstructions

引用

Computational visual Media 2021年第1期7卷 71-86页

作者： Benjamin Holler Annette Mossel Hannes Kaufmann Institute of Visual Computing and Human-Centered Technology Vienna University of TechnologyFavoritenstraβe 9-11/193/06A-1040 ViennaAustria

We introduce a novel framework for 3 D scene reconstruction with simultaneous object annotation,using a pre-trained 2 D convolutional neural network(CNN),incremental data streaming,and remote exploration,with a virtual reality *** enables versatile integration of any 2 D box detection or segmentation *** integrate new approaches to(i)asynchronously perform dense 3 D-reconstruction and object annotation at interactive frame rates,(ii)efficiently optimize CNN results in terms of object prediction and spatial accuracy,and(iii)generate computationally-efficient colliders in large triangulated3 D-reconstructions at run-time for 3 D scene *** method is novel in combining CNNs with long and varying inference time with live 3 D-reconstruction from RGB-D camera *** further propose a lightweight data structure to store the 3 D-reconstruction data and object annotations to enable fast incremental data transmission for real-time exploration with a remote client,which has not been presented *** framework achieves update rates of 22 fps(SSD Mobile Net)and 19 fps(Mask RCNN)for indoor environments up to 800 m^(3).We evaluated the accuracy of 3 D-object *** work provides a versatile foundation for semantic scene understanding of large streamed3 D-reconstructions,while being independent from the CNN’s processing *** code is available for non-commercial use.

关键词： dense 3D reconstruction object detection CNN distributed virtual reality

来源：评论

学校读者我要写书评

暂无评论

WHEN DISCOURSE STALLS: MOVING PAST FIVE SEMANTIC STOPSIGNS ABOUT GENERATIVE AI IN DESIGN RESEARCH

arXiv

引用

arXiv 2025年

作者： van der Maden, Willem van der Burg, Vera Halperin, Brett A. Jääskeläinen, Petra Lindley, Joseph Lomas, Derek Merritt, Timothy HCI & Design Section ITU Copenhagen Copenhagen Denmark Designing Intelligence Lab Technical University Delft Delft Netherlands Human Centered Design & Engineering University of Washington SeattleWA United States EECS/HCT MID KTH Royal Institute of Technology Stockholm Sweden Lancaster University Lancaster United Kingdom TU Delft Delft Netherlands Dept. of Computer Science Human Centered Computing University Aalborg Denmark

This essay examines how Generative AI (GenAI) is rapidly transforming design practices and how discourse often falls into over-simplified narratives that impede meaningful research and practical progress. We identify and deconstruct five prevalent "semantic stopsigns"—reductive framings about GenAI in design that halt deeper inquiry and limit productive engagement. Reflecting upon two expert workshops at ACM conferences and semi-structured interviews with design practitioners, we analyze how these stopsigns manifest in research and practice. Our analysis develops mid-level knowledge that bridges theoretical discourse and practical implementation, helping designers and researchers interrogate common assumptions about GenAI in their own contexts. By recasting these stopsigns into more nuanced frameworks, we provide the design research community with practical approaches for thinking about and working with these emerging technologies. © 2025, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

HAAQI-Net: A Non-Intrusive Neural Music Audio Quality Assessment Model for Hearing Aids

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1877-1892页

作者： Dyah A. M. G. Wisnu Stefano Rini Ryandhimas E. Zezario Hsin-Min Wang Yu Tsao Taiwan International Graduate Program—Social Network and Human-Centered Computing Institute of Information Science Academia Sinica Taipei Taiwan College of Informatics National Chengchi University Taipei Taiwan Institute of Communications Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan Institute of Information Science Academia Sinica Taipei Taiwan Department of Electrical Engineering Chung Yuan Christian University Taiwan

This paper introduces HAAQI-Net, a non-intrusive music audio quality assessment model for hearing aid users. Unlike traditional methods such as Hearing Aid Audio Quality Index (HAAQI), which requires intrusive reference signal comparisons, HAAQI-Net offers a more accessible and computationally efficient alternative. Leveraging a bidirectional long short-term memory architecture with attention mechanisms and features extracted from a pre-trained BEATs model, it can predict HAAQI scores directly from music audio clips and hearing loss patterns. The experimental results demonstrate that, compared to the traditional HAAQI as the reference, HAAQI-Net achieves a linear correlation coefficient (LCC) of 0.9368, a Spearman's rank correlation coefficient (SRCC) of 0.9486, and a mean squared error (MSE) of 0.0064, while significantly reducing the inference time from 62.52 seconds to 2.54 seconds. Furthermore, a knowledge distillation strategy was applied, reducing the parameters by 75.85% and inference time by 96.46%, while maintaining strong performance (LCC: 0.9071, SRCC: 0.9307, MSE: 0.0091). To expand its capabilities, HAAQI-Net was adapted to predict subjective human scores, mean opinion score (MOS), by fine-tuning. This adaptation significantly improved the prediction accuracy. Furthermore, the robustness of HAAQI-Net was evaluated under varying sound pressure level (SPL) conditions, revealing optimal performance at a reference SPL of 65 dB, with the accuracy gradually decreasing as SPL deviated from this point. The advancements in subjective score prediction, SPL robustness, and computational efficiency position HAAQI-Net as a reliable solution for music audio quality assessment, significantly contributing to the development of efficient and accurate models in audio signal processing and hearing aid technology.

关键词： Hearing aids Quality assessment Training Feature extraction Speech processing Auditory system Computational modeling Adaptation models Transformers Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

visual Analytics Meets Temporal Reasoning: Challenges and Opportunities 29

Visual Analytics Meets Temporal Reasoning: Challenges and Op...

引用

29th International Symposium on Temporal Representation and Reasoning, TIME 2022

作者： Miksch, Silvia Institute of Visual Computing and Human-Centered Technology TU Wien Austria

ISBN: (纸本)9783959772624

visual Analytics as the science of analytical reasoning facilitated by interactive visual interfaces aims to enable the exploration and the understanding of large, heterogeneous, and complex data sets. Time is an important data dimension with distinct characteristics. Intertwining visual Analytics with time and temporal reasoning introduces outstanding challenges and opportunities, which I will illustrate in this talk. © Silvia Miksch.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Video shot analysis for digital curation and preservation of historical films

Video shot analysis for digital curation and preservation of...

引用

2019 Eurographics Workshop on Graphics and Cultural Heritage, GCH 2019

作者： Helm, D. Kampel, M. TU Wien Institute for Visual Computing and Human-Centered Technology Austria

ISBN: (纸本)9783038680826

In automatic video analysis and film preservation, Shot Boundary Detection (SBD) and Shot Type Classification (STC) are fundamental pre-processing steps. While previous research focuses on detecting and classifying shots in different video genres such as sports movies, documentaries or news clips only few studies investigate on SBD and STC in historical footage. In order to promote research on automatic video analysis the project visual History of the Holocaust (VHH) has been started in January 2019. The main aim of this paper is to present first results on the fundamental topics SBD and STC in the context of the project VHH. Therefore, a deep learning-based SBD approach is implemented to detect Abrupt Transitions (ATs). Furthermore, a CNN-based algorithm is analyzed and optimized in order to classify shots into the four categories: Extreme-Long-Shot (ELS), Long-Shot (LS), Medium-Shot (MS) and Close-Up (CU). Finally, both algorithms are evaluated on a self-generated historical dataset related to the National Socialism and the Holocaust. The outcome of this paper demonstrates a first quantitative evaluation of the SBD approach and displays a F1;Score of 0.866 without the need of any re-training or optimization. Moreover, the proposed STC algorithm reaches an accuracy of 0.71 on classifying shots. This paper contributes a significant base for future research on automatic shot analysis related to the project VHH. © 2019 Eurographics Association.

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：