检索结果-内蒙古大学图书馆

International Conference on Technologies and Applications of Artificial Intelligence (TAAI)

作者： Yu-Lun Hsieh Shih-Hung Liu Yung-Chun Chang Wen-Lian Hsu Department of Computer Science National Chengchi University Taiwan Social Networks and Human-Centered Computing Program Academia Sinica Taiwan Institute of Information Science Academia Sinica Taiwan Graduate Institute of Electrical Engineering National Taiwan University Taiwan Departmem of Information Management National Taiwan University Taiwan

ISBN: (纸本)9781467396073

In the age of information explosion, efficiently categorizing the topic of a document can assist our organization and comprehension of the vast amount of text. In this paper, we propose a novel approach, named DKV, for document categorization using distributed real-valued vector representation of keywords learned from neural networks. Such a representation can project rich context information (or embedding) into the vector space, and subsequently be used to infer similarity measures among words, sentences, and even documents. Using a Chinese news corpus containing over 100,000 articles and five topics, we provide a comprehensive performance evaluation to demonstrate that by exploiting the keyword embeddings, DKV paired with support vector machines can effectively categorize a document into the predefined topics. Results demonstrate that our method can achieve the best performances compared to several other approaches.

关键词： Computational modeling Manuals

来源：评论

学校读者我要写书评

暂无评论

Medical image denoising using sparse representations

Medical image denoising using sparse representations

引用

International Conference on Awareness Science and Technology (iCAST)

作者： Fatma S. Abousaleh Neng-Hao Yu Kai-Lung Hua Wen-Huang Cheng Social Networks and Human Centered Computing Program Institute of Information Science Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan Department of Computer Science National Chengchi University Taipei Taiwan Department of Computer Science and Information Engineering Taiwan University of Science and Technology Taipei Taiwan

Image noise reduction, or denoising, became an attractive research domain in the recent years. There are several published approaches in the image denoising field and each one has its presumptions, advantages, and limitations. In this paper, we address the problem of eliminating or even decreasing the noise from medical images. Some schemes for image noise reduction are proposed. The schemes include DCT_OMP, DCT_BOMP, Log Gabor_BOMP, DCT_OCMP and Wavelet_OMP. In these schemes, the image content is represented as a sparse linear combination of a set of atoms that can be obtained from some trained dictionaries. In literature, several algorithms are proposed to build up these kinds of dictionaries. In our study, the K-SVD algorithm is utilized to obtain a dictionary that can effectively describe the image. Also, some greedy algorithms are used to perform the sparse-coding of the signal. The proposed schemes have been tested on two different medical images with different levels of an additive noise. The Log Gabor_BOMP scheme showed a significant outperformance, in both the de-noising results and computational time, on all the other schemes.

关键词： Matching pursuit algorithms Dictionaries Approximation algorithms Image denoising Noise reduction Discrete cosine transforms Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Linguistic Patterns for Code Word Resilient Hate Speech Identification

引用

SENSORS 2021年第23期21卷 7859-7859页

作者： Calderon, Fernando H. Balani, Namrita Taylor, Jherez Peignon, Melvyn Huang, Yen-Hao Chen, Yi-Shin Natl Tsing Hua Univ Inst Informat Syst & Applicat Guang Fu Rd Sec 2 Hsinchu 300 Taiwan Taiwan Int Grad Program Acad Sinica Inst Informat Sci Social Networks & Human Centered Comp 128 Acad RdSec 2 Taipei 115 Taiwan

The permanent transition to online activity has brought with it a surge in hate speech discourse. This has prompted increased calls for automatic detection methods, most of which currently rely on a dictionary of hate speech words, and supervised classification. This approach often falls short when dealing with newer words and phrases produced by online extremist communities. These code words are used with the aim of evading automatic detection by systems. Code words are frequently used and have benign meanings in regular discourse, for instance, "skypes, googles, bing, yahoos" are all examples of words that have a hidden hate speech meaning. Such overlap presents a challenge to the traditional keyword approach of collecting data that is specific to hate speech. In this work, we first introduced a word embedding model that learns the hidden hate speech meaning of words. With this insight on code words, we developed a classifier that leverages linguistic patterns to reduce the impact of individual words. The proposed method was evaluated across three different datasets to test its generalizability. The empirical results show that the linguistic patterns approach outperforms the baselines and enables further analysis on hate speech expressions.

关键词： hate speech social media linguistic patterns

来源：评论

学校读者我要写书评

暂无评论

TEAM: Task-Clustering and Enhanced Adaptability for Meta-Reinforcement Learning on Robotics Through Multi-Task Diffusion and Optimization

TEAM: Task-Clustering and Enhanced Adaptability for Meta-Rei...

引用

IEEE International Conference on Robotic computing (IRC)

作者： Joshua Ho Chien-Min Wang Chung-Ta King Chi-Wei Feng Shih-Yun Sunkuan Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu Taiwan Department of Computer Science National Tsing Hua University Hsinchu Taiwan Department of Electrical Engineering National Taiwan University Taipei Taiwan

ISBN: (数字)9798331521554

ISBN: (纸本)9798331521561

The ability of robots to imitate human learning strategies-rapidly adapting to new tasks without large datasets-has garnered significant attention in meta-learning. Meta-reinforcement learning seeks to enhance robotic agent flexibility across diverse tasks and contexts, offering promise where single-task learning often fails. Despite advancements like multi-task diffusion models and task-weighted optimization mechanisms, effectively training tasks with varying complexities simultaneously remains a major challenge. This paper introduces a novel meta-reinforcement learning method that addresses this issue by clustering the training tasks of robotic arms based on semantic and trajectory similarities, while leveraging adaptive learning rates and task-specific weights proposed by the multitask optimization techniques. Our approach, TEAM, emphasizes performance-driven semantic clustering, optimizing based on robotic task similarity, complexity, and convergence objectives. We also integrate fast adaptive and multi-task optimization of the diffusion model to enhance computational efficiency and adaptability. More specifically, we introduce a cluster-specific optimization technique, using specialized parameters for each group to allow more refined task handling. The experimental validation demonstrates the effectiveness of this scalable method in improving performance, adaptability, and efficiency in real-world, heterogeneous robotic tasks, further advancing robotic computing in meta-reinforcement learning.

关键词： Training Metalearning program processors Semantics Multitasking Diffusion models Complexity theory Trajectory Robots Optimization

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Masking and Mapping Based on Hierarchical Extreme Learning Machine for Speech Enhancement

Comparative Study of Masking and Mapping Based on Hierarchic...

引用

IEEE International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)

作者： Ryandhimas E. Zezario Join W. C. Sigalingging Tassadaq Hussain Jia-Ching Wang Yu Tsao Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan National Central University Taoyuan Taiwan Taiwan International Graduate Program in Social Network and Human-Centered Computing Institute of Information Science Academia Sinica Taipei Taiwan

In this study, we compare the speech enhancement performance based on hierarchical extreme learning machine (HELM) with two distinct strategies: masking and mapping. Experimental results of the perceptual evaluation of speech quality (PESQ) show that for both of limited and sufficient amounts of training data, mapping-based HELM tends to be more effective to improve the performance of speech enhancement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How Good is ChatGPT at Audiovisual Deepfake Detection: A Comparative Study of ChatGPT, AI Models and human Perception

arXiv

引用

arXiv 2024年

作者： Shahzad, Sahibzada Adil Hashmi, Ammarah Peng, Yan-Tsung Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei Taiwan The Department of Computer Science National Chengchi University Taipei Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan The Institute of Information Science Academia Sinica Taiwan

Multimodal deepfakes involving audiovisual manipulations are a growing threat because they are difficult to detect with the naked eye or using unimodal deep learning-based forgery detection methods. Audiovisual forensic models, while more capable than unimodal models, require large training datasets and are computationally expensive for training and inference. Furthermore, these models lack interpretability and often do not generalize well to unseen manipulations. In this study, we examine the detection capabilities of a large language model (LLM) (i.e., ChatGPT) to identify and account for any possible visual and auditory artifacts and manipulations in audiovisual deepfake content. Extensive experiments are conducted on videos from a benchmark multimodal deepfake dataset to evaluate the detection performance of ChatGPT and compare it with the detection capabilities of state-of-the-art multimodal forensic models and humans. Experimental results demonstrate the importance of domain knowledge and prompt engineering for video forgery detection tasks using LLMs. Unlike approaches based on end-to-end learning, ChatGPT can account for spatial and spatiotemporal artifacts and inconsistencies that may exist within or across modalities. Additionally, we discuss the limitations of ChatGPT for multimedia forensic tasks. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

Towards Adversarial Robustness for Multi-Mode Data through Metric Learning

引用

Sensors 2023年第13期23卷 6173页

作者： Khan, Sarwar Chen, Jun-Cheng Liao, Wen-Hung Chen, Chu-Song Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan Social Networks Human-Centered Computing Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan Department of Computer Science National Chengchi University Taipei11605 Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei106319 Taiwan

Adversarial attacks have become one of the most serious security issues in widely used deep neural networks. Even though real-world datasets usually have large intra-variations or multiple modes, most adversarial defense methods, such as adversarial training, which is currently one of the most effective defense methods, mainly focus on the single-mode setting and thus fail to capture the full data representation to defend against adversarial attacks. To confront this challenge, we propose a novel multi-prototype metric learning regularization for adversarial training which can effectively enhance the defense capability of adversarial training by preventing the latent representation of the adversarial example changing a lot from its clean one. With extensive experiments on CIFAR10, CIFAR100, MNIST, and Tiny ImageNet, the evaluation results show the proposed method improves the performance of different state-of-the-art adversarial training methods without additional computational cost. Furthermore, besides Tiny ImageNet, in the multi-prototype CIFAR10 and CIFAR100 where we reorganize the whole datasets of CIFAR10 and CIFAR100 into two and ten classes, respectively, the proposed method outperforms the state-of-the-art approach by 2.22% and 1.65%, respectively. Furthermore, the proposed multi-prototype method also outperforms its single-prototype version and other commonly used deep metric learning approaches as regularization for adversarial training and thus further demonstrates its effectiveness. © 2023 by the authors.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Investigation of a Single-Channel Frequency-Domain Speech Enhancement Network to Improve End-to-End Bengali Automatic Speech Recognition Under Unseen Noisy Conditions

Investigation of a Single-Channel Frequency-Domain Speech En...

引用

Oriental COCOSDA International Conference on Speech Database and Assessments

作者： Md Mahbub E Noor Yen-Ju Lu Syu-Siang Wang Supratip Ghose Chia-Yu Chang Ryandhimas E. Zezario Shafique Ahmed Wei-Ho Chung Yu Tsao Hsin-Min Wang Taiwan International Graduate Program in Social Network and Human-Centered Computing Institute of Information Science Academia Sinica Taiwan National Tsing Hua University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan University of Information Technology & Sciences Bangladesh

ISBN: (纸本)9781665408714

Due to the presence of distortion, most of the single-channel frequency-domain speech enhancement (SE) approaches are still challenging for downstream automatic speech recognition (ASR) tasks, even with satisfactory improvements in enhancing speech quality and intelligibility. Recently, transformer-based models have shown better performance in speech processing tasks. Therefore, we intend to explore a transformer-based SE model, which is fine-tuned through a two-stage training scheme. Pre-training is performed using a feature-level optimization criterion through SE loss, and then a pre-trained end-to-end ASR model is used to fine-tune the SE model using an ASR-oriented optimization criterion through SE and ASR losses. We evaluate the proposed approach on low-resourced Bengali language, which has not received as much attention as resource-rich English or Mandarin languages in both SE and ASR fields. Experimental results show that it can improve the performance of SE and ASR under severe unseen noisy conditions and its performance is reasonably good compared with other state-of-the-art SE methods.

关键词： Training Frequency-domain analysis Training data Speech enhancement Transformers Robustness Noise measurement

来源：评论

学校读者我要写书评

暂无评论

CapST: An Enhanced and Lightweight Method for Deepfake Video Classification

arXiv

引用

arXiv 2023年

作者： Ahmad, Wasim Peng, Yan-Tsung Chang, Yuan-Hao Ganfure, Gaddisa Olani Khan, Sarwar Shahzad, Sahibzada Adil Institute of Information Science Academia Sinica Taipei11529 Taiwan Department of Computer Science National Chengchi University Taipei116 Taiwan Social Networks Human-Centered Computing Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan Dire Dawa University Ethiopia Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan

The proliferation of deepfake videos, synthetic media produced through advanced Artificial Intelligence techniques, has raised significant concerns across various sectors, encompassing realms such as politics, entertainment, and security. In response, this research introduces an innovative and streamlined model designed to classify deepfake videos generated by five distinct encoders adeptly. Our approach not only achieves state-of-the-art performance but also optimizes computational resources. At its core, our solution employs part of a VGG19_bn as a backbone to efficiently extract features, a strategy proven effective in image-related tasks. We integrate a Capsule Network coupled with a Spatial-Temporal attention mechanism to bolster the model’s classification capabilities while conserving resources. This combination captures intricate hierarchies among features, facilitating robust identification of deepfake attributes. Delving into the intricacies of our innovation, we introduce an existing video-level fusion technique that artfully capitalizes on temporal attention mechanisms. This mechanism serves to handle concatenated feature vectors, capitalizing on the intrinsic temporal dependencies embedded within deepfake videos. By aggregating insights across frames, our model gains a holistic comprehension of video content, resulting in more precise predictions. Experimental results on an extensive benchmark dataset of deepfake videos (DFDM) showcase the efficacy of our proposed method. Notably, our approach achieves up to a 4% improvement in accurately categorizing deepfake videos compared to baseline models, all while demanding fewer computational resources. Copyright © 2023, The Authors. All rights reserved.

关键词： Routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning Adaptation and Generalization from human-Inspired Meta-Reinforcement Learning Using Bayesian Knowledge and Analysis

Learning Adaptation and Generalization from Human-Inspired M...

引用

Artificial Intelligence and Knowledge Engineering (AIKE)

作者： Joshua Ho Chien-Min Wang Chung-Ta King Yi-Hsin You Chi-Wei Feng Yen-Min Chen Bo-Yi Kuo Academia Sinica Institute of Information Science Taipei Taiwan Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Systems and Applications National Tsing Hua University Hsinchu Taiwan Center of Intelligent Healthcare National Taiwan University Hospital Taipei Taiwan Department of Computer Science National Tsing Hua University Hsinchu Taiwan Department of Computer Science National Taiwan University Taipei Taiwan

Over the last decades, there has been growing interest in research in multiple and interdisciplinary fields of human-AI computing. In particular, approaches integrating the intersecting design with reinforcement learning (RL) have received more attention. However, the current research on RL may need to consider its enhancement from a human-inspired approach further. In the present work, we focus on enabling a meta-reinforcement learning (meta-RL) agent to achieve adaptation and generalization according to modeling Markov decision processes using Bayesian knowledge and analysis. By introducing a novel framework called human-inspired meta-RL (HMRL), we incorporate the agent performing resilient actions to leverage the dynamic dense reward based on the knowledge and prediction of a Bayesian analysis. The proposed framework can make the agent learn generalization and prevent the agent from failing catastrophically. The experimental results show that our approach helps the agent reduce computational costs with learning adaptation. Finally, we conclude and anticipate that integrating human-inspired meta-RL can enable learning more formulations relating to robustness and scalability, leading to promising directions and more complex AI goals in the future.

关键词：

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：