检索结果-内蒙古大学图书馆

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

作者： Libo Qin Fuxuan Wei Qiguang Chen Jingxuan Zhou Shijue Huang Jiasheng Si Wenpeng Lu Wanxiang Che School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences)

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU.

关键词： Large language models Signal processing Benchmark testing Multitasking Filling Acoustics Speech processing Information exchange Standards

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Head-Mounted Display based Brain-Computer Interface for Virtual Robotic Arm Operation

Performance Evaluation of Head-Mounted Display based Brain-C...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Yang, Yuzhe Xie, Jun Xiao, Yi Ren, Zhiyuan Zhang, Huanqing Xiao, Xianzi Dong, Yuanzhe Tang, Xi Li, Guanglin Fang, Peng Xi'An Jiaotong University School of Mechanical Engineering Xi'an710049 China China Astronauts Research and Training Center National Key Laboratory of Human Factors Engineering Beijing100094 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems The Shenzhen Engineering Laboratory of Neural Rehabilitation Technology Shenzhen Institute of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9781665481090

The steady-state visual evoked potential based brain-computer interface (SSVEP BCI) mostly uses desktop display to present the visual stimulation, and it cannot meet the needs of immersive brain-computer interaction. This study proposed the head-mounted display (HMD) implementation of the SSVEP BCI. And based on the head-mounted virtual reality (VR) glasses device, this study established the BCI system in the VR environment for the operation of the virtual robotic arm. In offline experiments, the system accuracy was 86.66% and the information transfer rate (ITR) was 18.33 bits/min. And in the online experiment, the recognition accuracy was 88.08% and the ITR was 19.26 bits/min. Experimental results verified the effectiveness of the proposed HMD based BCI system in the operation of the virtual robotic arm. © 2022 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Enriching Multimodal Sentiment Analysis through Textual Emotional Descriptions of Visual-Audio Content

arXiv

引用

arXiv 2024年

作者： Wu, Sheng Wang, Xiaobao Wang, Longbiao He, Dongxiao Dang, Jianwu School of New Media and Communication Tianjin University Tianjin China China Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

Multimodal Sentiment Analysis (MSA) stands as a critical research frontier, seeking to comprehensively unravel human emotions by amalgamating text, audio, and visual data. Yet, discerning subtle emotional nuances within audio and video expressions poses a formidable challenge, particularly when emotional polarities across various segments appear similar. In this paper, our objective is to spotlight emotion-relevant attributes of audio and visual modalities to facilitate multimodal fusion in the context of nuanced emotional shifts in visual-audio scenarios. To this end, we introduce DEVA, a progressive fusion framework founded on textual sentiment descriptions aimed at accentuating emotional features of visual-audio content. DEVA employs an Emotional Description Generator (EDG) to transmute raw audio and visual data into textualized sentiment descriptions, thereby amplifying their emotional characteristics. These descriptions are then integrated with the source data to yield richer, enhanced features. Furthermore, DEVA incorporates the Text-guided Progressive Fusion Module (TPF), leveraging varying levels of text as a core modality guide. This module progressively fuses visual-audio minor modalities to alleviate disparities between text and visual-audio modalities. Experimental results on widely used sentiment analysis benchmark datasets, including MOSI, MOSEI, and CH-SIMS, underscore significant enhancements compared to state-of-the-art models. Moreover, fine-grained emotion experiments corroborate the robust sensitivity of DEVA to subtle emotional variations. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Prosthetic Hand System with Human-Like Grasping by Combining EMG and Visual Information

A Prosthetic Hand System with Human-Like Grasping by Combini...

引用

International Conference on Mechatronics and machine Vision in Practice (M2VIP)

作者： Yue Zheng Xinxing Chen Lan Tian Xiangxin Li Haoshi Zhang Xugang Jiang Guanglin Li Chenglong Fu Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Shenzhen China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences (CAS) China

ISBN: (数字)9798350391916

ISBN: (纸本)9798350391923

This paper proposed a novel prosthetic hand system integrated with a designed hybrid control method for achieving human-like grasping. The system design has been elaborated, including the mechanism design of a humanoid prosthetic hand equipped with multimodal sensing capabilities, a multi-channel EMG collector, a sensory feedback device, and a real-time central processing unit. A hybrid control method that combines electromyogram (EMG) and visual information was proposed to recognize the control intention of the system user. Preliminary verification of grasping experiments had been conducted, which proved the effectiveness of the prosthetic hand system and the hybrid control method. The development of this system aims to enhance the control performance and perceptual interaction capabilities of prosthetic hands while addressing limitations encountered in traditional myoelectric prosthetic hands. Besides, it could serve as a validation platform for assessing the control performance of diverse algorithms applied in practical applications.

关键词： Visualization Mechatronics Multimodal sensors machine vision Mechanism design Grasping Electromyography Real-time systems Prosthetic hand System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Expert with Outlier Exposure for Continual Learning of New Diseases

Expert with Outlier Exposure for Continual Learning of New D...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhengjing Xu Kanghao Chen Wei-Shi Zheng Zhijun Tan Xiaobo Yang Ruixuan Wang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE China State Key Laboratory of Dampness Syndrome of Chinese Medicine Guangzhou China Department of Network Intelligence Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Current intelligent diagnosis systems struggle to continually learn to diagnose more and more diseases due to catastrophic forgetting of old knowledge when learning new knowledge. Although storing small old data for subsequent continual learning can effectively help alleviate the forgetting issue, the heavy data imbalance between old classes and to-be-learned new classes in classifier training often causes biased prediction towards the new classes just learned by the updated classifier. In this study, an outlier detection technique is novelly applied to train an additional expert classifier for new classes to help alleviate the class imbalance issue and discriminate the learned new classes from old classes during inference (instead of the training phase). Specially, the stored small data of old classes are considered as outliers during training the expert classifier, such that the output probability distributions from the expert classifier are expected to be obviously different between test data of the old classes and those of the new classes. Such difference between old classes and new classes can be used to fine-tune the original output from the updated classifier which is responsible for prediction of all learned (old and new) classes. During inference, a novel ensemble strategy is proposed to combine the predictions from the updated classifier, the expert classifier, and the previously learned old classifier. The proposed learning and inference framework can be easily combined with existing continual learning strategies. Empirical evaluations on three medical image datasets and one natural image dataset show that the proposed framework can effectively improve continual learning performance.

关键词： Training Biological system modeling Probability distribution Bioinformatics Anomaly detection Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Halftone Image Steganalysis by Reconstructing Grayscale Image 7th

Halftone Image Steganalysis by Reconstructing Grayscale Imag...

引用

7th International Conference on Artificial intelligence and Security, ICAIS 2021

作者： Luo, Junwei Lin, Cong Zeng, Lingwen Liang, Jifan Lu, Wei School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China School of Statistics and Mathematics Guangdong University of Finance and Economics Guangzhou510320 China

ISBN: (纸本)9783030786113

Utilizing some special pixels patterns constructing the steganalytic features is popular in binary image steganalysis, which could be also used in halftone image. There is almost no specific image steganalysis for halftone image. In this paper, a halftone image steganalysis scheme is proposed and achieves a satisfactory performance, which is totally different from the previous works focussing on some special pixels patterns. Inspired by the fact that halftoning techniques based on the low-pass characteristic of human visual system model (HVS model), the grayscale image is considered reconstructing with a Gaussian filter. And the distortions caused by embedding secret messages will still exist. After that, some common grayscale image steganalysis can be used for extracting the steganalytic features. Furthermore, a series of experiments are conducted and the experimental results show that the proposed scheme is effective on halftone image steganalysis. © 2021, Springer Nature Switzerland AG.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

Visual Class Incremental Learning with Textual Priors Guidance based on an Adapted Vision-Language Model

引用

IEEE Transactions on Multimedia 2025年

作者： Zhang, Wentao Yu, Tong Wang, Ruixuan Xie, Jianhui Trucco, Emanuele Zheng, Wei-Shi Yang, Xiaobo Sun Yat-sen Univerisity School of Computer Science and Engineering Guangzhou510275 China Peng Cheng Laboratory Shenzhen518066 China MOE Key Laboratory of Machine Intelligence and Advanced Computing Guangzhou510275 China Second Affiliated Hospital Guangzhou University of Chinese Medicine State Key Laboratory of Dampness Syndrome of Chinese Medicine Guangzhou510260 China Guangdong Provincial Key Laboratory of Clinical Research on Traditional Chinese Medicine Syndrome Guangzhou510120 China University of Dundee School of Science and Engineering DundeeDD1 4HN United Kingdom

An ideal artificial intelligence (AI) system should have the capability to continually learn like humans. However, when learning new knowledge, AI systems often suffer from catastrophic forgetting of old knowledge. Although many continual learning methods have been proposed, they often ignore the issue of misclassifying similar classes and make insufficient use of textual priors of visual classes to improve continual learning performance. In this study, we propose a continual learning framework based on a pre-trained vision-language model (VLM) that does not require storing old class data. This framework utilizes parameter-efficient fine-tuning of the VLM's text encoder for constructing a shared and consistent semantic textual space throughout the continual learning process. The textual priors of visual classes are encoded by the adapted VLM's text encoder to generate discriminative semantic representations, which are then used to guide the learning of visual classes. Additionally, fake out-of-distribution (OOD) images constructed from each training image further assist in the learning of visual classes. Extensive empirical evaluations on three natural datasets and one medical dataset demonstrate the superiority of the proposed framework. The source code is available at https://***/OpenMedIA/CIL_Adapterd_VLM. © 1999-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

QDL: Quantitative Dynamic Latency Model in Permissioned Blockchain System 22

QDL: Quantitative Dynamic Latency Model in Permissioned Bloc...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Wei, Jiacheng Wang, Qingmei Wang, Zheng Beihang University School of Artificial Intelligence Beijing China Beihang University Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing China University of Science and Technology Beijing National Center for Materials Service Safety Beijing China Shanghai Jiao Tong University Institute of Cyber Science and Technology China Shanghai Key Laboratory of Integrated Administration Technologies for Information Security China

ISBN: (纸本)9798331509712

Latency, as a critical attribute influencing scalability and consistency in blockchain systems, has attracted significant research attention. This paper addresses the issue of latency evaluation by presenting a novel framework. We thoroughly analyze the factors affecting latency in blockchain system, including concurrency, consistency, and contention. To accurately model the correlation between latency and the quantity of nodes in permissioned blockchain setup, we introduce the Latency Regression Loss (LRL) function. By utilizing Newton's interpolation and least squares methods, we determine the hyperparameters. Subsequently, we devise the framework for the Quantitative Dynamic Latency (QDL) evaluation model, which accounts for both the growth rate and magnitude of latency. Utilizing the parameters derived from the LRL function facilitated the calculation of latency growth rate, allowing for a comprehensive evaluation of latency. Finally, we validated the accuracy of the LRL function through extensive experiments and simulated the adaptability of the QDL model in latency assessment. © 2024 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Augmenting Short Enrollment Speech via Synthesis for Target Speaker Extraction

Augmenting Short Enrollment Speech via Synthesis for Target ...

引用

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

作者： Zikang Huang Jingru Lin Meng Ge Yu Jiang Xiaobao Wang Longbiao Wang Jianwu Dang Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China Department of Electrical and Computer and Engineering National University of Singapore Huiyan Technology (Tianjin) Co. Ltd. Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

A high-quality enrollment speech is crucial to target speaker extraction (TSE), since it provides essential cues for identifying the target speaker in the mixture. However, real applications usually only permit a short enrollment speech, e.g. a wakeup word for a mobile device, that provides limited cues. To address this issue, we propose an enrollment augmentation strategy that allows us to enrich the limited enrollment speech with massive text data through speech synthesis. By doing so, the extended enrollment speech contains enhanced speaker timbre and phonetic content which leads to better extraction quality. Furthermore, we propose a training data augmentation strategy to improve the model’s robustness and generalization in short enrollment speech scenarios. Experiments on Libri2Mix demonstrate that our proposed strategies bring a significant improvement in extreme scenarios where only 0.5s and 1-word enrollment speech is provided. We also release our code at https://***/HuangZikang-TJU/Aug4TSE.

关键词： Training data Speech enhancement Phonetics Signal processing Speech Robustness Mobile handsets Data models Timbre Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

OR-Gate Mixup Multiscale Spectral Graph Neural Network for Node Anomaly Detection

引用

IEEE Transactions on Neural Networks and Learning Systems 2025年 PP卷 PP页

作者： Li, Zekang Liu, Ruonan Chen, Dongyue Hu, Qinghua Tianjin University College of Intelligence and Computing Tianjin Key Laboratory of Machine Learning Tianjin 300350 China Shanghai Jiao Tong University Department of Automation Shanghai 200240 China National Key Laboratory of Marine Engine Science and Technology Shanghai 201108 China

Graph node anomaly detection has important applications in practical scenarios. Although many graph neural networks (GNNs) have been proposed, how to design tailored spectral filters for node anomaly detection to fully mine high-frequency signals in the graph is still a challenge. Most GNNs are equivalent to low-pass filters and mine multiorder signals through a series structure. The computational cost increases as the number of layers increases and further leads to an over-smoothing problem. They mainly focus on low-frequency signals and suppress high-frequency signals, thus smoothing the differences between abnormal and normal nodes, making them indistinguishable. Due to the difficulty in mining high-frequency signals, the poorly distinguishable feature representations learned by low-pass GNNs can even harm the performance of data augmentation. To solve the above challenges, in this article, we propose a or-gate mixup multiscale spectral GNN (MMGNN) from the spectral domain. Specifically, we design multiorder multiscale bandpass filters through the superposition of polynomial spectral filters and then decompose them into preprocessing parts and training parts to form a double-parallel structure, which can effectively mine high-frequency signals in the graph and reduce computational cost. Finally, we propose or-gate mixup to perform data augmentation in the spectral space to improve model generalization. Experimental results on four real-world datasets demonstrate the effectiveness of the proposed MMGNN against the state-of-the-art methods. © 2012 IEEE.

关键词： Graph data augmentation graph neural networks (GNNs) graph pattern mining graph representation learning node anomaly detection

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：