检索结果-内蒙古大学图书馆

A novel comparative deep learning framework for facial age estimation

EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING 2016年第1期2016卷 1页

作者： Abousaleh, Fatma S. Lim, Tekoing Cheng, Wen-Huang Yu, Neng-Hao Hossain, M. Anwar Alhamid, Mohammed F. Acad Sinica IIS Taiwan Int Grad Program Social Networks & Human Centered Comp Program Acad Rd Taipei 11529 Taiwan Acad Sinica Res Ctr Informat Technol Innovat CITI Acad Rd Taipei 11529 Taiwan Natl Chengchi Univ Dept Comp Sci ZhiNan Rd Taipei 11605 Taiwan King Saud Univ Dept Software Engn Coll Comp & Informat Sci Riyadh 11362 Saudi Arabia

Developing automatic facial age estimation algorithms that are comparable or even superior to the human ability in age estimation becomes an attractive yet challenging topic emerging in recent years. The conventional methods estimate one person's age directly from the given facial image. In contrast, motivated by human cognitive processes, we proposed a comparative deep learning framework, called Comparative Region Convolutional Neural Network (CRCNN), by first comparing the input face with reference faces of known age to generate a set of hints (comparative relations, i.e., the input face is younger or older than each reference). Then, an estimation stage aggregates all the hints to estimate the person's age. Our approach has several advantages: first, the age estimation task is split into several comparative stages, which is simpler than directly computing the person's age;secondly, in addition to the input face itself, side information (comparative relations) can be explicitly involved to benefit the estimation task;finally, few incorrect comparisons will not influence much the accuracy of the result, making this approach more robust than the conventional approach. To the best of our knowledge, the proposed approach is the first comparative deep learning framework for facial age estimation. Furthermore, we proposed to incorporate the Method of Auxiliary Coordinates (MAC) for training, which reduces the ill-conditioning problem of the deep network and affords an efficient and distributed optimization. In comparison to the best results from the state-of-the-art methods, the CRCNN showed a significant outperformance on all the benchmarks, with a relative improvement of 13.24% (on FG-NET), 23.20% (on MORPH), and 4.74% (IoG).

关键词： Deep learning Facial age estimation Region convolutional neural network Comparative framework

来源：评论

学校读者我要写书评

暂无评论

Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learning 30th

Adversarially Robust Deepfake Detection via Adversarial Fea...

引用

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Khan, Sarwar Chen, Jun-Cheng Liao, Wen-Hung Chen, Chu-Song Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan Social Networks Human-Centered Computing TIGP Academia Sinica Taipei Taiwan Computer Science National Chengchi University Taipei Taiwan Computer Science and Information Engineering National Taiwan University Taipei Taiwan

ISBN: (纸本)9783031533105

Deepfake technology has raised concerns about the authenticity of digital content, necessitating the development of effective detection methods. However, the widespread availability of deepfakes has given rise to a new challenge in the form of adversarial attacks. Adversaries can manipulate deepfake videos with small, imperceptible perturbations that can deceive the detection models into producing incorrect outputs. To tackle this critical issue, we introduce Adversarial Feature Similarity Learning (AFSL), which integrates three fundamental deep feature learning paradigms. By optimizing the similarity between samples and weight vectors, our approach aims to distinguish between real and fake instances. Additionally, we aim to maximize the similarity between both adversarially perturbed examples and unperturbed examples, regardless of their real or fake nature. Moreover, we introduce a regularization technique that maximizes the dissimilarity between real and fake samples, ensuring a clear separation between these two categories. With extensive experiments on popular deepfake datasets, including FaceForensics++, FaceShifter, and DeeperForensics, the proposed method outperforms other standard adversarial training-based defense methods significantly. This further demonstrates the effectiveness of our approach to protecting deepfake detectors from adversarial attacks. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Lip Sync Matters: A Novel Multimodal Forgery Detector

Lip Sync Matters: A Novel Multimodal Forgery Detector

引用

14th Annual Summit and Conference of the Asia-Pacific-Signal-and-Information-Processing-Association (APSIPA ASC)

作者： Shahzad, Sahibzada Adil Hashmi, Ammarah Khan, Sarwar Peng, Yan-Tsung Tsao, Yu Wang, Hsin-Min Acad Sinica Inst Informat Sci Social Networks & Human Centered Comp Program Taiwan Int Grad Program New Taipei Taiwan Natl Chengchi Univ Dept Comp Sci Taipei Taiwan Natl Tsing Hua Univ Inst Informat Syst & Applicat Taipei Taiwan Acad Sinica Res Ctr Informat Technol Innovat Taipei Taiwan

ISBN: (数字)9786165904773

ISBN: (纸本)9786165904773

Deepfake technology has advanced a lot, but it is a double-sided sword for the community. One can use it for beneficial purposes, such as restoring vintage content in old movies, or for nefarious purposes, such as creating fake footage to manipulate the public and distribute non-consensual pornography. A lot of work has been done to combat its improper use by detecting fake footage with good performance thanks to the availability of numerous public datasets and unimodal deep learning-based models. However, these methods are insufficient to detect multimodal manipulations, such as both visual and acoustic. This work proposes a novel lip-reading-based multimodal Deepfake detection method called "Lip Sync Matters." It targets high-level semantic features to exploit the mismatch between the lip sequence extracted from the video and the synthetic lip sequence generated from the audio by the Wav2lip model to detect forged videos. Experimental results show that the proposed method outperforms several existing unimodal, ensemble, and multimodal methods on the publicly available multimodal FakeAVCeleb dataset.

关键词： Deepfakes Visualization Lips Semantics Detectors Feature extraction Motion pictures

来源：评论

学校读者我要写书评

暂无评论

Explainable and Adaptable Augmentation in Knowledge Attention Network for Multi-Agent Deep Reinforcement Learning Systems

Explainable and Adaptable Augmentation in Knowledge Attentio...

引用

Artificial Intelligence and Knowledge Engineering (AIKE)

作者： Joshua Ho Chien-Min Wang 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

ISBN: (数字)9781728187082

ISBN: (纸本)9781728187099

The scale of modem Artificial Intelligence systems has been growing and entering more research territories by incorporating Deep Learning (DL) and Deep Reinforcement Learning (DRL) methods. More specifically, multi-agent DRL methods have been widely applied to address the problems of high-dimensional computation, which interpret the conditions that real-world systems mainly encounter and the issues that require resolving. However, the current approaches of DL and DRL are often challenged for their untransparent and time-consuming modeling processes in their attempt to achieve a practical and applicable inference based on human-level perspective and acceptance. This paper presents an explainable and adaptable augmented knowledge attention network for multi-agent DRL systems, which uses game theory simulation to tackle the problem of non-stationarity at the beginning, while improving the learning exploration built upon the strategic ontology to achieve the learning convergence more efficiently for autonomous agents. We anticipate that our approach will facilitate future research studies and potential research inspections of emerging multi-agent DRL systems for increasingly complex and autonomous environments.

关键词： Knowledge engineering Adaptation models Reinforcement learning Ontologies Inspection Modems Game theory

来源：评论

学校读者我要写书评

暂无评论

Audio-Driven Facial Landmark Generation in Violin Performance using 3DCNN Network with Self Attention Model

Audio-Driven Facial Landmark Generation in Violin Performanc...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ting-Wei Lin Chao-Lin Liu Li Su 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

In a music scenario, both auditory and visual elements are essential to achieve an outstanding performance. Recent research has focused on the generation of body movements or fingering from audio in music performance. The audio-driven face generation technique in music performance is still deficient. In this paper, we compile a violin soundtrack and facial expression dataset (VSFE) for modeling facial expressions in violin performance. To our knowledge, this is the first dataset mapping the relationship between violin performance audio and musicians’ facial expressions. We then propose a 3DCNN network with self-attention and residual blocks for audio-driven facial expression generation. In the experiments, we compare our methods with three baselines on talking face generation. The codes and dataset are available on the Github (https://***/kevinlin91/icassp_music2face).

关键词： Visualization Codes Avatars Signal processing Acoustics Multiple signal classification Speech processing

来源：评论

学校读者我要写书评

暂无评论

Reactive supervision: A new method for collecting sarcasm data

arXiv

引用

arXiv 2020年

作者： Shmueli, Boaz Ku, Lun-Wei Ray, Soumya Social Networks and Human-Centered Computing Taiwan International Graduate Program Taiwan Institute of Information Science Academia Sinica Taiwan Institute of Service Science National Tsing Hua University Taiwan

Sarcasm detection is an important task in affective computing, requiring large amounts of labeled data. We introduce reactive supervision, a novel data collection method that utilizes the dynamics of online conversations to overcome the limitations of existing data collection techniques. We use the new method to create and release a first-of-its-kind large dataset of tweets with sarcasm perspective labels and new contextual features. The dataset is expected to advance sarcasm detection research. Our method can be adapted to other affective computing domains, thus opening up new research opportunities. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

socialNLP EmotionGIF 2020 challenge overview: Predicting reaction GIF categories on social media

arXiv

引用

arXiv 2021年

We present an overview of the EmotionGIF 2020 Challenge, held at the 8th International Workshop on Natural Language Processing for social Media (socialNLP), in conjunction with ACL 2020. The challenge required predicting affective reactions to online texts, and includes the EmotionGIF dataset, with tweets labeled for the reaction categories. The novel dataset included 40K tweets with their reaction GIFs. Due to the special circumstances of year 2020, two rounds of the competition were conducted. A total of 84 teams registered for the task. Of these, 25 teams successfully submitted entries to the evaluation phase in the first round, while 13 teams participated successfully in the second round. Of the top participants, five teams presented a technical report and shared their code. The top score of the winning team using the Recall@K metric was 62.47%. Copyright © 2021, The Authors. All rights reserved.

关键词： social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Happy Dance, Slow Clap: Using Reaction GIFs to Predict Induced Affect on Twitter

arXiv

引用

arXiv 2021年

作者： Shmueli, Boaz Ra, Soumya Ku, Lun-Wei Social Networks and Human-Centered Computing TIGP Academia Sinica Institute of Service Science National Tsing Hua University Institute of Information Science Academia Sinica

Datasets with induced emotion labels are scarce but of utmost importance for many NLP tasks. We present a new, automated method for collecting texts along with their induced reaction labels. The method exploits the online use of reaction GIFs, which capture complex affective states. We show how to augment the data with induced emotions and induced sentiment labels. We use our method to create and publish ReactionGIF, a first-of-its-kind affective dataset of 30K tweets. We provide baselines for three new tasks, including induced sentiment prediction and multilabel classification of induced emotions. Our method and dataset open new research opportunities in emotion detection and affective computing. Copyright © 2021, The Authors. All rights reserved.

关键词：

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 6

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

引用

6th IEEE International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023

作者： Ho, Joshua Wang, Chien-Min King, Chung-Ta You, Yi-Hsin Feng, Chi-Wei Chen, Yen-Min Kuo, Bo-Yi Institute of Information Science Academia Sinica Taipei11529 Taiwan Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan Department of Computer Science National Tsing Hua University Hsinchu30013 Taiwan Department of Computer Science National Taiwan University Taipei10631 Taiwan Center of Intelligent Healthcare National Taiwan University Hospital Taipei10022 Taiwan

ISBN: (纸本)9798350331288

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 humaninspired 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. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multilayer CPW-Fed Patch Antenna on New AMC Ground Plane for 60 GHz Millimeter-Wave Communications

Multilayer CPW-Fed Patch Antenna on New AMC Ground Plane for...

引用

IEEE Vehicular Technology Conference

作者： Imad Ali Ronald Y. Chang Jenny Yi-Chun Liu Taiwan International Graduate Program in Social Networks and Human-Centered Computing Institute of Information Science Academia Sinica Research Center for Information Technology Innovation Academia Sinica Department of Electrical Engineering National Tsing Hua University

ISBN: (纸本)9781509016990

This paper presents a 60 GHz CPW-fed patch antenna on multilayer LTCC- and LCP-based materials with new and compact AMC. The proposed antenna structure consists of top three layers of antenna and bottom three layers of AMC ground plane. First, a new and compact three-layer AMC is designed on both LTCC- and LCP-based substrates. The designed AMC is more compact and provides 37.5% higher in-phase bandwidth as compared to a state-of-the-art design. Then, a three-layer CPW-fed patch antenna is designed and optimized on LTCC- and LCP-based substrates on top of the three-layer AMC ground plane of the same material. We perform a gain-bandwidth comparative study of antennas on multilayer LTCC- and LCP-based substrates with AMC/PEC ground planes for 60 GHz. We observe that antennas on LCP-based substrate outperform those on LTCC-based substrate in terms of input impedance, bandwidth, and gains on both AMC and PEC ground planes, while antennas on LTCC-based substrate have smaller antenna and AMC dimensions.

关键词： AMCN gene antecedent moisture condition (amc) Patch antennas ANTENNA Ground plane Planing antennae impedance Substrates plane

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：