检索结果-内蒙古大学图书馆

Bridging The Gap: Entailment Fused-T5 for Open-retrieval Conversational Machine Reading Comprehension

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Xiao Huang, Heyan Chi, Zewen Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center High Volume Language Information Processing and Cloud Computing Applications China Southeast Academy of Information Technology Beijing Institute of Technology China

Open-retrieval conversational machine reading comprehension (OCMRC) simulates real-life conversational interaction scenes. Machines are required to make a decision of Yes/No/Inquire or generate a follow-up question when the decision is Inquire based on retrieved rule texts, user scenario, user question, and dialogue history. Recent studies explored the methods to reduce the information gap between decision-making and question generation and thus improve the performance of generation. However, the information gap still exists because these pipeline structures are still limited in decision-making, span extraction, and question rephrasing three stages. Decision-making and generation are reasoning separately, and the entailment reasoning utilized in decision-making is hard to share through all stages. To tackle the above problem, we proposed a novel one-stage end-to-end framework, called Entailment Fused-T5 (EFT), to bridge the information gap between decision-making and generation in a global understanding manner. The extensive experimental results demonstrate that our proposed framework achieves new state-of-the-art performance on the OR-ShARC benchmark. Copyright © 2022, The Authors. All rights reserved.

关键词： Decision making

Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan Department of Computer Science National Chengchi University Taipei11529 Taiwan Department of Electrical Engineering Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan Institute of Information Science Academia Sinica Taipei11529 Taiwan

The emergence of contemporary deepfakes has attracted significant attention in machine learning research, as artificial intelligence (AI) generated synthetic media increases the incidence of misinterpretation and is difficult to distinguish from genuine content. Currently, machine learning techniques have been extensively studied for automatically detecting deepfakes. However, human perception has been less explored. Malicious deepfakes could ultimately cause public and social problems. Can we humans correctly perceive the authenticity of the content of the videos we watch? The answer is obviously uncertain;therefore, this paper aims to evaluate the human ability to discern deepfake videos through a subjective study. We present our findings by comparing human observers to five state-of-the-art deepfake detection models. To this end, we used gamification concepts to provide 110 participants (55 native English speakers and 55 non-native English speakers) with a web-based platform where they could access a series of 40 videos (20 real and 20 fake) to determine their authenticity. Each participant performed the experiment twice with the same 40 videos in different random orders. The videos are manually selected from the FakeAVCeleb dataset. We found that all AI models performed significantly better than humans when evaluated on the same 40 videos. The study also reveals that while deception is not impossible, humans tend to overestimate their detection capabilities. Our experimental results may help benchmark human versus machine performance, advance forensics analysis, and enable adaptive countermeasures. © 2024, CC BY.

关键词： Audiovisual

Understanding Audiovisual Deepfake Detection: Techniques, Challenges, Human Factors and Perceptual Insights

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan The Department of Computer Science National Chengchi University Taipei11529 Taiwan The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Deep Learning has been successfully applied in diverse fields, and its impact on deepfake detection is no exception. Deepfakes are fake yet realistic synthetic content that can be used deceitfully for political impersonation, phishing, slandering, or spreading misinformation. Despite extensive research on unimodal deepfake detection, identifying complex deepfakes through joint analysis of audio and visual streams remains relatively unexplored. To fill this gap, this survey first provides an overview of audiovisual deepfake generation techniques, applications, and their consequences, and then provides a comprehensive review of state-of-the-art methods that combine audio and visual modalities to enhance detection accuracy, summarizing and critically analyzing their strengths and limitations. Furthermore, we discuss existing open source datasets for a deeper understanding, which can contribute to the research community and provide necessary information to beginners who want to analyze deep learning-based audiovisual methods for video forensics. By bridging the gap between unimodal and multimodal approaches, this paper aims to improve the effectiveness of deepfake detection strategies and guide future research in cybersecurity and media integrity. © 2024, CC BY.

关键词： Audiovisual

Transfer Learning for Keypoint Detection in Low-Resolution Thermal TUG Test Images

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Wei-Lun Hsieh, Chia-Yeh Kao, Yu-Hsiang Liu, Kai-Chun Peng, Sheng-Yu Tsao, Yu Research Center for Information Technology Innovation Academic Sinica Taiwan Graduate Institute of Electrical Engineering National Taiwan University Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan Department of Electrical Engineering National Taiwan University Taiwan College of Information and Computer Sciences University of Massachusetts AmherstMA01003 United States Department of Electrical Engineering National Taiwan University of Science of Technology Taiwan

This study presents a novel approach to human keypoint detection in low-resolution thermal images using transfer learning techniques. We introduce the first application of the Timed Up and Go (TUG) test in thermal image computer vision, establishing a new paradigm for mobility assessment. Our method leverages a MobileNetV3-Small encoder and a ViTPose decoder, trained using a composite loss function that balances latent representation alignment and heatmap accuracy. The model was evaluated using the Object Keypoint Similarity (OKS) metric from the COCO Keypoint Detection Challenge. The proposed model achieves better performance with AP, AP50, and AP75 scores of 0.861, 0.942, and 0.887 respectively, outperforming traditional supervised learning approaches like Mask R-CNN and ViTPose-Base. Moreover, our model demonstrates superior computational efficiency in terms of parameter count and FLOPS. This research lays a solid foundation for future clinical applications of thermal imaging in mobility assessment and rehabilitation monitoring. Copyright © 2025, The Authors. All rights reserved.

关键词： Thermography (imaging)

Photonic Frequency Space Simulation of Tight-Binding Lattices Using Integrated LNOI Ring Resonators

学校读者我要写书评

暂无评论

Photonic Frequency Space Simulation of Tight-Binding Lattice...

Pacific Rim Conference on Lasers and Electro-Optics (CLEO/Pacific Rim)

作者： Armandas Balčytis Hiep Dinh Tomoki Ozawa Yasutomo Ota Toshihiko Baba Satoshi Iwamoto Arnan Mitchell Thach G. Nguyen Integrated Photonics and Applications Centre RMIT University Melbourne VIC Australia Advanced Institute for Materials Research Tohoku University Sendai Japan Department of Applied Physics and Physico-Informatics Keio University Yokohama Japan Department of Electrical and Computer Engineering Yokohama National University Hodogaya-ku Yokohama Japan Research Center for Advanced Science and Technology The University of Tokyo Meguro-ku Tokyo Japan

We use electro-optically modulated ring cavities, integrated on thin-film lithium niobate, to model frequency dimension tight-binding lattices with versatile connectivity. Inter-mode coupling range, strength, and hopp... 详细信息

ISBN: (数字)9798350372076

ISBN: (纸本)9798350372083

关键词： Frequency modulation Lithium niobate Resonant frequency Lattices Electro-optic modulators Ring lasers Laser modes

InfoFlowNet: A Multi-head Attention-based Self-supervised Learning Model with Surrogate Approach for Uncovering Brain Effective Connectivity

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chuang, Chun-Hsiang Fang, Shao-Xun Huang, Chih-Sheng Ding, Weiping Research Center for Education and Mind Sciences College of Education National Tsing Hua University Hsinchu Taiwan Institute of Information Systems and Applications College of Electrical Engineering and Computer Science National Tsing Hua University Hsinchu Taiwan Department of Education and Learning Technology National Tsing Hua University Hsinchu Taiwan Department of Computer Science and Engineering National Taiwan Ocean University Keelung Taiwan Department of Artificial Intelligence Research and Development Elan Microelectronics Corporation Hsinchu Taiwan College of Artificial Intelligence and Green Energy National Yang Ming Chiao Tung University Hsinchu Taiwan College of Electrical Engineering and Computer Science National Taipei University of Technology Hsinchu Taiwan School of Information Science and Technology Nantong University Nantong China Institute of Information Systems and Applications College of Electrical Engineering and Computer Science NTHU Treasure Taipei Chapter of IEEE Computational Intelligence Society Taiwan

Deciphering brain network topology can enhance the depth of neuroscientific knowledge and facilitate the development of neural engineering methods. Effective connectivity, a measure of brain network dynamics, is particularly useful for investigating the directional influences among different brain regions. In this study, we introduce a novel brain causal inference model named InfoFlowNet, which leverages the self-attention mechanism to capture associations among electroencephalogram (EEG) time series. The proposed method estimates the magnitude of directional information flow (dIF) among EEG processes by measuring the loss of model inference resulting from the shuffling of the time order of the original time series. To evaluate the feasibility of InfoFlowNet, we conducted experiments using a synthetic time series and two EEG datasets. The results demonstrate that InfoFlowNet can extract time-varying causal relationships among processes, reflected in the fluctuation of dIF values. Compared with the Granger causality model and temporal causal discovery framework, InfoFlowNet can identify more significant causal edges underlying EEG processes while maintaining an acceptable computation time. Our work demonstrates the potential of InfoFlowNet for analyzing effective connectivity in EEG data. The findings highlight the importance of effective connectivity in understanding the complex dynamics of the brain network. Copyright © 2023, The Authors. All rights reserved.

关键词： Electroencephalography

Generative Models in Computational Pathology: A Comprehensive Survey on Methods, applications, and Challenges

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Yuan Zhang, Xinfeng Qi, Xiaoming Wu, Xinyu Chen, Feng Yang, Guanyu Fu, Huazhu Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications [Southeast University Ministry of Education Nanjing China School of Biomedical Engineering Tsinghua University Beijing China Department of Biomedical Engineering Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore School of Information Science and Engineering Southeast University Nanjing China Department of Biostatistics Center for Global Health School of Public Health Nanjing Medical University Nanjing China Institute of High-Performance Computing Agency for Science Technology and Research Singapore

Generative modeling has emerged as a promising direction in computational pathology, offering capabilities such as data-efficient learning, synthetic data augmentation, and multimodal representation across diverse diagnostic tasks. This review provides a comprehensive synthesis of recent progress in the field, organized into four key domains: image generation, text generation, multimodal image–text generation, and other generative applications, including spatial simulation and molecular inference. By analyzing over 150 representative studies, we trace the evolution of generative architectures—from early generative adversarial networks to recent advances in diffusion models and foundation models with generative capabilities. We further examine the datasets and evaluation protocols commonly used in this domain and highlight ongoing limitations, including challenges in generating high-fidelity whole slide images, clinical interpretability, and concerns related to the ethical and legal implications of synthetic data. The review concludes with a discussion of open challenges and prospective research directions, with an emphasis on developing unified, multimodal, and clinically deployable generative systems. This work aims to provide a foundational reference for researchers and practitioners developing and applying generative models in computational pathology. © 2025, CC BY-NC-ND.

关键词： Generative adversarial networks

Fine-Tuning Optimization of Small Language Models: A Novel Graph-Theoretical Approach for Efficient Prompt engineering

学校读者我要写书评

暂无评论

Fine-Tuning Optimization of Small Language Models: A Novel G...

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Venkata Gadiraju Hao-Yu Tsai Hsiao-Chun Wu Manali Singha C.-H. Scott Huang Guannan Liu Shih Yu Chang Yiyan Wu School of Electrical Engineering and Computer Science Louisiana State University Baton Rouge USA Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan Innovation Center for AI Applications Yuan Ze University Chungli Taiwan Institute for Genomic Medicine (IGM) Nationwide Children’s Hospital Columbus USA Department of Applied Data Science San Jose State University San Jose USA Communications Research Centre Ottawa Canada

ISBN: (数字)9798350364262

ISBN: (纸本)9798350364279

In the realm of fine-tuning pre-trained language models in modern prompt engineering, we introduce a novel graph-theoretical approach to address the resource-intensive challenges to the conventional data fine-tuning methods for prompt engineering. Leveraging semantic and contextual prompt relationships, we propose to form a novel prompt graph, which facilitates a new comprehensive representation of prompt similarities. Building upon this new graph structure, our proposed approach can minimize the training time during the fine-tuning process for small language models by identifying and utilizing cliques corresponding to condensed subsets of highly similar prompts. This new strategic reduction in training data can greatly reduce the training time, particularly for resource-constrained applications in practice. Our proposed new approach leads to a significant reduction in the original prompt-graph order and a more focused and streamlined fine-tuning process. This data-reduction strategy demonstrates the potential to enable finetuning language models for prompt engineering with smaller datasets subject to less computational resource. The real run-time analysis for the training process of a small language model GPT2 have been undertaken to show the advantage of our proposed new approach.

关键词： Training Computational modeling Simulation Semantics Training data Data models Prompt engineering

Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Nie, Yuxiang Huang, Heyan Wei, Wei Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Beijing Institute of Technology Southeast Academy of Information Technology China Huazhong University of Science and Technology China

Long document question answering is a challenging task due to its demands for complex reasoning over long text. Previous works usually take long documents as non-structured flat texts or only consider the local structure in long documents. However, these methods usually ignore the global structure of the long document, which is essential for long-range understanding. To tackle this problem, we propose Compressive Graph Selector Network (CGSN) to capture the global structure in a compressive and iterative manner. Specifically, the proposed model consists of three modules: local graph network, global graph network and evidence memory network. Firstly, the local graph network builds the graph structure of the chunked segment in token, sentence, paragraph and segment levels to capture the short-term dependency of the text. Secondly, the global graph network selectively receives the information of each level from the local graph, compresses them into the global graph nodes and applies graph attention into the global graph nodes to build the long-range reasoning over the entire text in an iterative way. Thirdly, the evidence memory network is designed to alleviate the redundancy problem in the evidence selection via saving the selected result in the previous steps. Extensive experiments show that the proposed model outperforms previous methods on two datasets.1 Copyright © 2022, The Authors. All rights reserved.

关键词： Iterative methods