检索结果-内蒙古大学图书馆

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

作者： Yi Qiao Yang Liu Qing He Xiang Ao Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciencs Beijing China Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Graph Neural Networks (GNNs) have demonstrated impressive success across diverse fields when data satisfies in-distribution (ID) assumption. Nevertheless, GNN performance significantly declines in cases of distribution shifts between training and testing graph data. This degradation primarily stems from spurious correlations between irrelevant domain information and target labels in out-of-distribution (OOD) scenarios. Thus, maximizing the utilization of domain information becomes imperative. In light of this, we propose a novel approach named Domain-aware Node Representation Learning (DNRL), comprehensively incorporates domain information to bolster generalization capability. Specifically, DNRL selectively interpolates nodes with the same label but different domains, extending training data into unseen domains and alleviating the effects caused by domain-related spurious correlations. Futhermore, by introducing a domain-aware contrastive learning strategy, our method implicitly decouples domain information from node information to learn domain-independent node representations. Extensive experiments on graph out-of-distribution benchmarks demonstrate that DNRL can achieve effective OOD generalization performance across diverse domains.

关键词： Representation learning Training Degradation Interpolation Correlation Training data Signal processing Graph neural networks Data models Speech processing

来源：评论

学校读者我要写书评

暂无评论

Movie preference prediction based on EEG signal under high brain correlation 4

Movie preference prediction based on EEG signal under high b...

引用

4th International Conference on Signal processing and Computer Science, SPCS 2023

作者： Yue, Yuanhao Zhao, Xingcong Zhou, Wei Liu, Guangyuan School of Electronic and Information Engineering Southwest University Tiansheng Road Beibei Chongqing400715 China Institute of Affective Computing and Information Processing Southwest University Tiansheng Road Beibei Chongqing400715 China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Southwest University Tiansheng Road Beibei Chongqing400715 China

ISBN: (纸本)9781510672505

In this study, we recorded the electroencephalography (EEG) of human subjects when they watched a movie trailer. Based on the willingness preference from the subjects after finished the movie trailer watching, the EEG signals were analyzed to build regression models to predict the subjects' movie preferences. We proposed a new approach to rise the prediction accuracy. Specifically, the correlated component analysis (CCA) algorithm was used to calculate the inter-subject correlation (ISC) of each time segment in the movie trailer and the ISC of each channel in the EEG. These two states were selected to locate the moment when a specific area of the brain responds most strongly to the video stimulation, as an effective indicator for predicting individual movie preferences. The experimental results show that the method of selecting effective EEG signals at the level of ISC has achieved a better prediction effect on the GBDT regression model (R2 = 0.733, RMSE = 0.681). We also found that low-frequency EEG signals in the θ and δ bands of the parietal and occipital sites are more effective in predicting movie preferences than high-frequency EEG signals. © 2023 SPIE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Category Agnostic Model for Visual Rearrangment

A Category Agnostic Model for Visual Rearrangment

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuyi Liu Xinhang Song Weijie Li Xiaohan Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

This paper presents a novel category agnostic model for visual rearrangement task, which can help an embodied agent to physically recover the shuffled scene configuration without any category concepts to the goal configuration. Previous methods usually follow a similar architecture, completing the rearrangement task by aligning the scene changes of the goal and shuffled configuration, according to the semantic scene graphs. However, constructing scene graphs requires the inference of category labels, which not only causes the accuracy drop of the entire task but also limits the application in real world scenario. In this paper, we delve deep into the essence of visual re-arrangement task and focus on the two most essential issues, scene change detection and scene change matching. We utilize the movement and the protrusion of point cloud to accurately identify the scene changes and match these changes depending on the similarity of category agnostic appearance feature. Moreover, to assist the agent to explore the environment more efficiently and comprehensively, we propose a closer-aligned-retrace exploration policy, aiming to observe more details of the scene at a closer distance. We conduct extensive experiments onAI2THOR Rearrangement Challenge based on RoomR dataset and a new multi-room multi-instance dataset MrMiR collected by us. The experimental results demonstrate the effectiveness of our proposed method.

关键词： Point cloud compression Visualization Computer vision Accuracy Semantics Feature extraction Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Enhanced Discriminant Analysis Based Fault Diagnosis Scheme for Marine Diesel Engines 11

Enhanced Discriminant Analysis Based Fault Diagnosis Scheme ...

引用

11th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2022

作者： Zhong, Kai Wang, Jiayi Pan, Donghui Institutes of Physical Science and Information Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education Anhui Hefei230601 China School of Mathematical Science Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui Hefei230601 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

Since the marine diesel engine is one of the most popular power equipments for modern shipping, accurate and timely diagnose the faults occurred in diesel engine is extraordinary important for long service life and high reliability. Note that Fisher discriminant analysis (FDA) has been widely applied in fault diagnosis field. However, it is quite susceptible to the small sample size (SSS) problem, which is very common in the running process of diesel engine. In response to the problem, this study pro-poses a new fault classification criterion based exponential discriminant analysis (EDA) scheme for diesel engine fault diagnosis, in which the exponential transformation is carried out first to enlarge the margin between different classes, thus the different fault classes are further separated and the diagnosis capability is enhanced. In addition, the theorems of matrix exponential guarantee that the matrix exp (Sw) is always full-rank, even though the Sw is singular. That means, the novel methodology is still appli-cable when confronts with the SSS problem. Finally, based on the more reasonable fault classification criterion, the simulation results on a real-world two-stroke six-cylinder low-speed marine diesel engine indicate that the EDA based diagnosis scheme achieves higher fault diagnosis accuracy with good robustness and practicability in real-world engineering applications. © 2022 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Dual-Band HRRP Recognition via Wavelet Packet Decomposition and Redundancy Reduction Model 2

Dual-Band HRRP Recognition via Wavelet Packet Decomposition ...

引用

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

作者： Yang, Wei Qi, Zhuchang Wu, Heke Li, Yang Zhang, Liang Wang, Yanhua Radar Technology Research Institute Beijing Institute of Technology Beijing100081 China Zhengzhou Academy of Intelligent Technology Beijing Institute of Technology Zhengzhou450000 China Xi'an Institute of Modern Control Technology Xi'an710065 China Beijing Key Laboratory of Embedded Real-time Information: Processing Technology Beijing100081 China Chongqing Innovation Center Beijing Institute of Technology Chongqing401120 China

ISBN: (纸本)9798331515669

High resolution range profiles (HRRP) is widely used in radar automatic target recognition. Due to aspect sensitivity, HRRP of different targets can be similar under certain aspects, making it difficult for recognition via traditional methods. One way to mitigate it is to increase the frequency dimension, utilizing the differences of target frequency response to extract inter-class discriminative information. Therefore, we propose a HRRP recognition model based on redundancy reduction criterion and wavelet packet decomposition. Specifically, we use deep wavelet packet decomposition to perform multi-level decomposition of dual-band HRRP and adaptively extract discriminative features of sub-wavelets;we use redundancy reduction layer to cluster intra-class features and expand inter-class features, thereby reducing feature heterogeneity. Furthermore, we propose a deep discriminative correlation analysis for joint analysis and transformation of dual-band features to fuse complementary information. Experimental results show that proposed method has excellent recognition performance. Additionally, analysis study also verify the effectiveness of each submodule. © 2024 IEEE.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

αSetup-PCTL:An Adaptive Setup-Based Two-Level Preconditioner for Sequence of Linear Systems of Three-Temperature Energy Equations

引用

Communications in Computational Physics 2022年第10期32卷 1287-1309页

作者： Silu Huang Xiaoqiang Yue Xiaowen Xu Laboratory of Computational Physics Institute of Applied Physics and ComputationalMathematicsBeijing 100088China National Center for Applied Mathematics in Hunan Key Laboratory of Intelligent Computing and Information Processing of Ministry of EducationHunan Key Laboratory for Computation and Simulation in Science and EngineeringXiangtan UniversityXiangtan 411105China

The iterative solution of the sequence of linear systems arising from threetemperature(3-T)energy equations is an essential component in the numerical simulation of radiative hydrodynamic(RHD)***,due to the complicated application features of the RHD problems,solving 3-T linear systems with classical preconditioned iterative techniques is *** address this difficulty,a physicalvariable based coarsening two-level(PCTL)preconditioner has been proposed by dividing the fully coupled system into four individual easier-to-solve *** its nearly optimal complexity and robustness,the PCTL algorithm suffers from poor efficiency because of the overhead associatedwith the construction of setup phase and the solution of ***,the PCTL algorithm employs a fixed strategy for solving the sequence of 3-T linear systems,which completely ignores the dynamically and slowly changing features of these linear *** address these problems and to efficiently solve the sequence of 3-T linear systems,we propose an adaptive two-level preconditioner based on the PCTL algorithm,referred to as α*** adaptive strategies of the αSetup-PCTL algorithm are inspired by those of αSetup-AMG algorithm,which is an adaptive-setup-based AMG solver for sequence of sparse linear *** proposed αSetup-PCTL algorithm could adaptively employ the appropriate strategies for each linear system,and thus increase the overall *** results demonstrate that,for 36 linear systems,the αSetup-PCTL algorithm achieves an average speedup of 2.2,and a maximum speedup of 4.2 when compared to the PCTL algorithm.

关键词： Sequence of linear systems sparse linear solver preconditioning methods radiation hydrodynamics simulation

来源：评论

学校读者我要写书评

暂无评论

A Dual Prompt Learning Framework for Few-Shot Dialogue State Tracking 23

A Dual Prompt Learning Framework for Few-Shot Dialogue State...

引用

2023 World Wide Web Conference, WWW 2023

作者： Yang, Yuting Lei, Wenqiang Huang, Pei Cao, Juan Li, Jintao Chua, Tat-Seng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China Sichuan University Sichuan China Stanford University CA United States National University of Singapore Singapore Singapore

ISBN: (纸本)9781450394161

Dialogue State Tracking (DST) module is an essential component of task-oriented dialog systems to understand users' goals and needs. Collecting dialogue state labels including slots and values can be costly, requiring experts to annotate all (slot, value) information for each turn in dialogues. It is also difficult to define all possible slots and values in advance, especially with the wide application of dialogue systems in more and more new-rising applications. In this paper, we focus on improving DST module to generate dialogue states in circumstances with limited annotations and knowledge about slot ontology. To this end, we design a dual prompt learning framework for few-shot DST. The dual framework aims to explore how to utilize the language understanding and generation capabilities of pre-trained language models for DST efficiently. Specifically, we consider the learning of slot generation and value generation as dual tasks, and two kinds of prompts are designed based on this dual structure to incorporate task-related knowledge of these two tasks respectively. In this way, the DST task can be formulated as a language modeling task efficiently under few-shot settings. To evaluate the proposed framework, we conduct experiments on two task-oriented dialogue datasets. The results demonstrate that the proposed method not only outperforms existing state-of-the-art few-shot methods, but also can generate unseen slots. It indicates that DST-related knowledge can be probed from pre-trained language models and utilized to address low-resource DST efficiently with the help of prompt learning. © 2023 Owner/Author.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

DD-Net: Dynamic Network Architecture for Optimized Curve Segmentation and Reduce Computational Redundancy 27th

DD-Net: Dynamic Network Architecture for Optimized Curve Seg...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Cao, Yunxiang Chen, Li Wang, Yubo Feng, Zhida Tian, Jing School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China Institute of Systems Science National University of Singapore Singapore Singapore

ISBN: (纸本)9783031783821

Curvilinear Structure segmentation has numerous applications in various fields, including providing a better understanding of defects such as cracks on roads or walls, thereby assessing the structural safety of buildings. Numerous curve segmentation methods based on Convolutional Neural Networks(CNN) have been developed in recent years. However, preserving feature integrity remains a challenge. To address this issue, this paper introduces a double dynamic network, called DD-Net, which consists of a dynamic structure for training and dynamic masking for inference. Firstly, to enhance the nonlinearity of the model, a paradigm to auto-adjust the CNN structure via a trainable module is formed for better fine-grained feature extraction. This dynamic structure (DS) paradigm enables a trade-off to extract or discard the feature data in the model training. Due to the data heterogeneity between the training and inference data, models may contain some useless nodes that are less effective during inference. The dynamic masking (DM) is proposed to omit the useless nodes based on the score difference between the train and inference feature statistics, thereby reducing redundant computations. To further improve the model’s performance on thin-curve segmentation and to preserve feature integrity, we introduce a non-curve suppression (NCS) module. This module focuses on background information while considering foreground prediction to address noisy conditions. The experimental results show that our DD-Net achieves promising results on three benchmark datasets and outperforms state-of-the-art curve segmentation models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Glancing Future for Simultaneous Machine Translation

Glancing Future for Simultaneous Machine Translation

引用

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

作者： Shoutao Guo Shaolei Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) University of Chinese Academy of Sciences Beijing China

Simultaneous machine translation (SiMT) outputs translation while reading the source sentence. Unlike conventional sequence-to-sequence (seq2seq) training, existing SiMT methods adopt the prefix-to-prefix (prefix2prefix) training, where the model predicts target tokens based on partial source tokens. However, the prefix2prefix training diminishes the ability of the model to capture global information and introduces forced predictions due to the absence of essential source information. Consequently, it is crucial to bridge the gap between the prefix2prefix training and seq2seq training to enhance the translation capability of the SiMT model. In this paper, we propose a novel method that glances future in curriculum learning to achieve the transition from the seq2seq training to prefix2prefix training. Specifically, we gradually reduce the available source information from the whole sentence to the prefix corresponding to that latency. Our method is applicable to a wide range of SiMT methods and experiments demonstrate that our method outperforms strong baselines 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Not all diffusion model activations have been evaluated as discriminative features 24

Not all diffusion model activations have been evaluated as d...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Benyuan Meng Qianqian Xu Zitai Wang Xiaochun Cao Qingming Huang Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at https://***/Darkbblue/generic-diffusion-feature.

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：