检索结果-内蒙古大学图书馆

Unsupervised Dialogue State Tracking for End-to-End Task-Oriented Dialogue with a Multi-Span Prediction Network

Journal of Computer Science & Technology 2023年第4期38卷 834-852页

作者：刘庆斌何世柱刘操刘康赵军 National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Beijing Sankuai Online Technology Company Limited Beijing 100102China

This paper focuses on end-to-end task-oriented dialogue systems,which jointly handle dialogue state tracking(DST)and response *** methods usually adopt a supervised paradigm to learn DST from a manually labeled ***,the annotation of the corpus is costly,time-consuming,and cannot cover a wide range of domains in the real *** solve this problem,we propose a multi-span prediction network(MSPN)that performs unsupervised DST for end-to-end task-oriented ***,MSPN contains a novel split-merge copy mechanism that captures long-term dependencies in dialogues to automatically extract multiple text spans as *** on these keywords,MSPN uses a semantic distance based clustering approach to obtain the values of each *** addition,we propose an ontology-based reinforcement learning approach,which employs the values of each slot to train MSPN to generate relevant *** results on single-domain and multi-domain task-oriented dialogue datasets show that MSPN achieves state-of-the-art performance with significant ***,we construct a new Chinese dialogue dataset MeDial in the low-resource medical domain,which further demonstrates the adaptability of MSPN.

关键词： end-to-end task-oriented dialogue dialogue state tracking(DST) unsupervised learning reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Federated Local Compact Representation Communication:Framework and Application

引用

Machine intelligence Research 2024年第6期21卷 1103-1120页

作者： Zhengquan Luo Yunlong Wang Zilei Wang University of Science and Technology of China(USTC) Hefei230026China New Laboratory of Pattern Recognition(NLPR) Institute of AutomationChinese Academy of SciencesBeijing100190China State Key Laboratory of Multimodal Artificial Intelligence Systems(MAIS) Institute of AutomationChinese Academy of SciencesBeijing100190China

The core of federated learning(FL)is to transfer data diversity and distribution knowledge of cross-client ***-though adopted by most FL methods,model-sharing-based communication has limitations such as unstable optimization and lack of reasonable *** this paper,we propose an innovative approach that exploits a highly abstract local compact representation(LCR)as a communication carrier,paving a new feasible path for *** is not only more intuitive for multiclient joint training but also insensitive to local privacy,particularly in computer vision *** proposed LCR communication-based FL framework aims to improve performance,mitigate negative transfer,and enhance optimization ***,based on the domain adaptation theorem,in-depth theoretical proofs guarantee the contribution of representation communication from other domains,which may lead to a tight-er generalization error bound of the local ***,inspired by metric learning,a federated version of the triplet(FedTriplet)loss and distribution similarity reweighting aggregation are proposed to fully digest LCR from other clients and realize the LCRC-based FL framework with better ***-client FedTriplet transferring redresses the category boundaries in local latent space,resist-ing *** modified Wasserstein distance is employed for reweighting aggregation to overcome the negative transfer problem caused by ***,extensive experiments on MNIST/EMNIST and successful iris recognition applications demon-strate that the proposed LCRC framework is superior in terms of accuracy compared to mainstream model-sharing-based FL *** visualization results also show significant improvements in the distinguishability of the representation distribution.

关键词： Federated learning representation learning domain adaptation biometrics iris recognition

来源：评论

学校读者我要写书评

暂无评论

DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model 38

DrivingDojo Dataset: Advancing Interactive and Knowledge-Enr...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Yuqi Cheng, Ke He, Jiawei Wang, Qitai Dai, Hengchen Chen, Yuntao Xia, Fei Zhang, Zhaoxiang New Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Meituan Inc. China Centre for Artificial Intelligence and Robotics HKISI CAS China

Driving world models have gained increasing attention due to their ability to model complex physical dynamics. However, their superb modeling capability is yet to be fully unleashed due to the limited video diversity in current driving datasets. We introduce DrivingDojo, the first dataset tailor-made for training interactive world models with complex driving dynamics. Our dataset features video clips with a complete set of driving maneuvers, diverse multi-agent interplay, and rich open-world driving knowledge, laying a stepping stone for future world model development. We further define an action instruction following (AIF) benchmark for world models and demonstrate the superiority of the proposed dataset for generating action-controlled future predictions. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of CNN-and Transformer-Based Visual Style Transfer

引用

Journal of Computer Science & Technology 2022年第3期37卷 601-614页

作者： Hua-Peng Wei Ying-Ying Deng Fan Tang Xing-Jia Pan Wei-Ming Dong School of Artificial Intelligence Jilin UniversityChangchun 130012China National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China Youtu Laboratory Tencent IncorporatedShanghai 200233China

Vision Transformer has shown impressive performance on the image classification *** that most existing visual style transfer(VST)algorithms are based on the texture-biased convolution neural network(CNN),here raises the question of whether the shape-biased Vision Transformer can perform style transfer as *** this work,we focus on comparing and analyzing the shape bias between CNN-and transformer-based models from the view of VST *** comprehensive comparisons,we propose three kinds of transformer-based visual style transfer(Tr-VST)methods(Tr-NST for optimization-based VST,Tr-WCT for reconstruction-based VST and Tr-AdaIN for perceptual-based VST).By engaging three mainstream VST methods in the transformer pipeline,we show that transformer-based models pre-trained on ImageNet are not proper for style transfer *** to the strong shape bias of the transformer-based models,these Tr-VST methods cannot render style *** further analyze the shape bias by considering the influence of the learned parameters and the structure *** prove that with proper style supervision,the transformer can learn similar texture-biased features as CNN *** the reduced shape bias in the transformer encoder,Tr-VST methods can generate higher-quality results compared with state-of-the-art VST methods.

关键词： transformer convolution neural network visual style transfer comparative study

来源：评论

学校读者我要写书评

暂无评论

Streaming Stroke Classification of Online Handwriting 48

Streaming Stroke Classification of Online Handwriting

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Liu, Jing-Yu Zhang, Yan-Ming Yin, Fei Liu, Cheng-Lin Institute of Automation of Chinese Academy of Sciences Nation Laboratory of Pattern Recognition China University of Chinese Academy of Sciences School of Artificial Intelligence China

ISBN: (纸本)9781728163277

Stroke classification for online handwriting aims at providing each stroke with a semantic label so as to fulfill handwriting segmentation. This task has attracted considerable attention due to its significance in online handwriting analysis. Existing methods are designed for the static situation, where stroke classification is conducted on the completion of handwriting. With the popularity of pad devices and electronic whiteboards, streaming stroke classification becomes increasingly important for instant handwriting processing and feedback. However, streaming classification is much more challenging due to the lack of contextual information and is underexplored in the past. In this paper, we propose Multiple Stroke State Transformer (MSST), a novel framework to enable simultaneous real-time classification and modifiability of previous predictions. Particularly, we set multiple states with duration for each stroke and then divide all states into chunks to perform message passing by Transformer. Experiments on handwritten documents and diagrams demonstrate the superiority of our method. © 2023 IEEE.

关键词： Multiple Stroke State Transformer online handwriting analysis streaming stroke classification

来源：评论

学校读者我要写书评

暂无评论

EmoFake: An Initial Dataset for Emotion Fake Audio Detection 23

引用

23rd Chinese National Conference on Computational Linguistics, CCL 2024

作者： Zhao, Yan Yi, Jiangyan Tao, Jianhua Wang, Chenglong Dong, Yongfeng School of Artificial Intelligence Hebei University of Technology China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China Department of Automation Tsinghua University China

ISBN: (纸本)9780000000002

To enhance the effectiveness of fake audio detection techniques, researchers have developed multiple datasets such as those for the ASVspoof and ADD challenges. These datasets typically focus on capturing non-emotional characteristics in speech, such as the identity of the speaker and the authenticity of the content. However, they often overlook changes in the emotional state of the audio, which is another crucial dimension affecting the authenticity of speech. Therefore, this study reports our progress in developing such an emotion fake audio detection dataset involving changing emotion state of the origin audio named EmoFake. The audio samples in EmoFake are generated using open-source emotional voice conversion models, intended to simulate potential emotional tampering scenarios in real-world settings. We conducted a series of benchmark experiments on this dataset, and the results show that even advanced fake audio detection models trained on the ASVspoof 2019 LA dataset and the ADD 2022 track 3.2 dataset face challenges with EmoFake. The EmoFake is publicly available1 now. © 2024 China National Conference on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Research on Fast Steel Surface Deficiency Detection System based on FPGA 3

Research on Fast Steel Surface Deficiency Detection System b...

引用

3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing, CAMMIC 2023

作者： Wang, Yaoyao Liu, Dengfeng School of Artificial Intelligence and Computer Jiangnan University Wuxi214122 China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China

ISBN: (数字)9781510667617

ISBN: (纸本)9781510667600

Convolutional neural network-related applications have now been developed on a variety of platforms, including CPUs, GPUs, and others, but most of them sacrificed energy consumption to achieve good performance. Therefore, in recent years, more and more hot spots have shifted to how to achieve related applications such as low energy consumption research methods. In order to make the steel surface defect detection system meet the requirements of real-time detection, this article proposes that VGG16 is used as the main network to complete the design of the FPGA's rapid detection and identification system for the FPGA. This system conducts software and hard-hard design based on the ZYNQ-7000 platform (1) The design of parallelization of convolution on the PL side The hardware acceleration is achieved by accelerating the data flow design. Each IP core accelerated with the PL end. (2) In the method of quantifying the data, in the case of almost little loss of data accuracy, the use of resources on FPGA films has been greatly reduced to achieve acceleration of algorithms. The final experimental results show that compared with the CPU, this algorithm has increased by 6 times. The power consumption ratio of the CPU platform and the FPGA platform is 12.6, and the power consumption ratio of the GPU platform and the FPGA platform is 38.2, which is more suitable for applications on the embedded platform. © 2023 SPIE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Learning Interpretable and Robust Spatiotemporal Dynamics from fMRI for Precise Identification of Neurological Disorders

Learning Interpretable and Robust Spatiotemporal Dynamics fr...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Youhao Huang, Yongzhi Gao, Qingchen Chen, Pindong Liu, Yong Tu, Liyun Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing100876 China Brainnetome Center and National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9798350386226

Resting-state functional magnetic resonance imaging (rs-fMRI) has significantly advanced the diagnosis of brain diseases. However, existing methods are generally limited to small, disease-specific datasets with less convincing outcomes or lack the interpretability needed to identify reliable disease-associated biomarkers. In this paper, we introduce a novel generative inference model that integrates a Variational Autoencoder (VAE) with Non-negative Matrix Factorization (NMF). Our model comprises three key components: an encoder for learning spatiotemporal dynamic feature embeddings within fMRI data, a decoder to reconstruct the input data from the encoded latent space, and a classifier to distinguish between neurological disorders and normal controls. The three components are simultaneously optimized to perform inference by estimating the posterior distribution of the latent variables from the input fMRI, yielding predictive and interpretable biomarkers for the diagnosis of neurological disorders. We extensively evaluated our method for identifying Autism Spectrum Disorder (ASD) and Alzheimer's Disease (AD) using two public datasets, ABIDE and ADNI. Experimental results show that our method achieves state-of-the-art performance across various metrics. © 2024 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

EmoFake: An Initial Dataset for Emotion Fake Audio Detection 23rd

EmoFake: An Initial Dataset for Emotion Fake Audio Detectio...

引用

23rd China National Conference on Computational Linguistics, CCL 2024

作者： Zhao, Yan Yi, Jiangyan Tao, Jianhua Wang, Chenglong Dong, Yongfeng School of Artificial Intelligence Hebei University of Technology Tianjin China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Department of Automation Tsinghua University Beijing China

ISBN: (纸本)9789819783663

To enhance the effectiveness of fake audio detection techniques, researchers have developed multiple datasets such as those for the ASVspoof and ADD challenges. These datasets typically focus on capturing non-emotional characteristics in speech, such as the identity of the speaker and the authenticity of the content. However, they often overlook changes in the emotional state of the audio, which is another crucial dimension affecting the authenticity of speech. Therefore, this study reports our progress in developing such an emotion fake audio detection dataset involving changing emotion state of the origin audio named EmoFake. The audio samples in EmoFake are generated using open-source emotional voice conversion models, intended to simulate potential emotional tampering scenarios in real-world settings. We conducted a series of benchmark experiments on this dataset, and the results show that even advanced fake audio detection models trained on the ASVspoof 2019 LA dataset and the ADD 2022 track 3.2 dataset face challenges with EmoFake. The EmoFake is publicly available (https://***/records/10443769) now. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： emotion fake emotion voice conversion fake audio detection dataset

来源：评论

学校读者我要写书评

暂无评论

PIC 4th Challenge: Semantic-Assisted multi-feature encoding and multi-head decoding for dense video captioning 4

PIC 4th Challenge: Semantic-Assisted multi-feature encoding ...

引用

4th Person in Context Workshop, PIC 2022

作者： Lu, Yifan Zhang, Ziqi Chen, Yuxin Yuan, Chunfeng Li, Bing Hu, Weiming National Laboratory of Pattern Recognition CASIA and School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China National Laboratory of Pattern Recognition CASIA Beijing China National Laboratory of Pattern Recognition CASIA and CAS Center for Excellence in Brain Science and Intelligence Technology Beijing China

ISBN: (纸本)9781450394895

The task of Dense Video Captioning (DVC) aims to generate captions with timestamps for multiple events in one video. Semantic information plays an important role for both localization and description of DVC. We present a semantic-Assisted dense video captioning model based on the encoding-decoding framework. In the encoding stage, we design a concept detector to extract semantic information, which is then fused with multi-modal visual features to sufficiently represent the input video. In the decoding stage, we design a classification head, paralleled with the localization and captioning heads, to provide semantic supervision. Our method achieves significant improvements on the YouMakeup dataset \citewang2019youmakeup under DVC evaluation metrics and achieves high performance in the Makeup Dense Video Captioning (MDVC) task of \hrefhttp://***/challenge/task/mdvc/ PIC 4th Challenge. © 2022 ACM.

关键词： Semantics

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：