检索结果-南通市图书馆

Audio-visual keyword transformer for unconstrained sentence-level keyword spotting

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第1期9卷 142-152页

作者： Yidi Li Jiale Ren Yawei Wang Guoquan Wang Xia Li Hong Liu key {1. of machine perception Peking UniversityShenzhen Graduate SchoolShenzhenChina College of Electronics and Information Engineering Sichuan UniversityChengduChina Department of Computer Science ETH ZurichZurichSwitzerland

As one of the most effective methods to improve the accuracy and robustness of speech tasks,the audio-visual fusion approach has recently been introduced into the field of keyword Spotting(KWS).However,existing audio-visual keyword spotting models are limited to detecting isolated words,while keyword spotting for unconstrained speech is still a challenging *** this end,an Audio-Visual keyword Transformer(AVKT)network is proposed to spot keywords in unconstrained video *** authors present a transformer classifier with learnable CLS tokens to extract distinctive keyword features from the variable-length audio and visual *** outputs of audio and visual branches are combined in a decision fusion *** humans can easily notice whether a keyword appears in a sentence or not,our AVKT network can detect whether a video clip with a spoken sentence contains a pre-specified ***,the position of the keyword is localised in the attention map without additional position ***-imental results on the LRS2-KWS dataset and our newly collected PKU-KWS dataset show that the accuracy of AVKT exceeded 99%in clean scenes and 85%in extremely noisy *** code is available at https://***/jialeren/AVKT.

关键词： artificial intelligence multimodal approaches natural language processing neural network speech processing

A Heuristic Radiomics Feature Selection Method Based on Frequency Iteration and Multi-Supervised Training Mode

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 2277-2293页

作者： Zhigao Zeng Aoting Tang Shengqiu Yi Xinpan Yuan Yanhui Zhu School of Computer Hunan University of TechnologyZhuzhou412007China Hunan key {1. of Intelligent Information perception and Processing Technology Zhuzhou412007China

Radiomics is a non-invasive method for extracting quantitative and higher-dimensional features from medical images for *** has received great attention due to its huge application prospects in recent *** can know that the number of features selected by the existing radiomics feature selectionmethods is basically about *** this paper,a heuristic feature selection method based on frequency iteration and multiple supervised training mode is *** on the combination between features,it decomposes all features layer by layer to select the optimal features for each layer,then fuses the optimal features to form a local optimal group layer by layer and iterates to the global optimal combination *** with the currentmethod with the best prediction performance in the three data sets,thismethod proposed in this paper can reduce the number of features fromabout ten to about three without losing classification accuracy and even significantly improving classification *** proposed method has better interpretability and generalization ability,which gives it great potential in the feature selection of radiomics.

关键词： Radiomics feature selection machine learning metaheuristic

Uncertain knowledge graph embedding:an effective method combining multi-relation and multi-path

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第3期18卷 73-89页

作者： Qi LIU Qinghua ZHANG Fan ZHAO Guoyin WANG key {1. of Tourism Multisource Data perception and Decision Ministry of Culture and TourismChongqing University of Posts and TelecommunicationsChongqing 400065China Chongqing key {1. of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Chongqing key {1. of Big Data Intelligent Computing Chongqing University of Posts and TelecommunicationsChongqing 400065China

Uncertain Knowledge Graphs(UKGs)are used to characterize the inherent uncertainty of knowledge and have a richer semantic structure than deterministic knowledge *** research on the embedding of UKG has only recently begun,Uncertain Knowledge Graph Embedding(UKGE)model has a certain effect on solving this ***,there are still unresolved *** the one hand,when reasoning the confidence of unseen relation facts,the introduced probabilistic soft logic cannot be used to combine multi-path and multi-step global information,leading to information *** the other hand,the existing UKG embedding model can only model symmetric relation facts,but the embedding problem of asymmetric relation facts has not be *** address the above issues,a Multiplex Uncertain Knowledge Graph Embedding(MUKGE)model is proposed in this ***,to combine multiple information and achieve more accurate results in confidence reasoning,the Uncertain ResourceRank(URR)reasoning algorithm is ***,the asymmetry in the UKG is *** embed asymmetric relation facts of UKG,a multi-relation embedding model is ***,experiments are carried out on different datasets via 4 tasks to verify the effectiveness of *** results of experiments demonstrate that MUKGE can obtain better overall performance than the baselines,and it helps advance the research on UKG embedding.

关键词： knowledge representation uncertain knowledge graph multi-relation embedding uncertain reasoning

Investigating Optical Transport Network Performance:A Recurrence Plot Approach

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2024年第5期21卷 166-176页

作者： Sun Xiaochuan Cao Difei Wei Biao Li Zhigang Li Yingqi College of Artificial Intelligence North China University of Science and TechnologyTangshan 063210China Hebei key {1. of Industrial Intelligent perception Tangshan 063210China

In future optical transport networks,lightpath performance analysis is of great practical significance for fully automated *** general,the quality of transmission(QoT)of lightpaths,measured by optical quality factor or optical signal-to-noise ratio,has a complex time-varying process,along with the interactions of the other lightpath state parameters(LSPs),such as transmit power,chromatic dispersion,polarization mode *** studies are mostly focused on lightpath QoT estimation,but ignoring lightpath-level data *** this case,our article proposes a novel lightpath performance analysis method considering recurrence plot(RP)and cross recurrence plot(CRP).Firstly,we give a detailed interpretation on the recurrence patterns of LSPs via a qualitative 2-D RP representation and its quantitative *** can potentially enable the accurate and fast lightpath failure detection with a low computational *** the other hand,CRP is devoted to modeling the relationships between lightpath QoT and LSPs,and the correlation degree is determined by a geometric mean of multiple indexes of cross recurrence quantification *** the view of application,such CRP analysis can provide the effective knowledge sharing to guarantee more credible QoT *** experiments on a real-world optical network dataset have clearly demonstrated the effectiveness of our proposal.

关键词： CRP analysis lightpath QoT optical transport networks RP analysis

Causal reasoning in typical computer vision tasks

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第1期67卷 105-120页

作者： ZHANG KeXuan SUN QiYu ZHAO ChaoQiang TANG Yang key {1. of Advanced Control and Optimization for Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China National key {1. of Air based Information perception and Fusion Luoyang 471000China Luoyang Institute of Electro Optical Equipment of Avic Luoyang 471000China

Deep learning has revolutionized the field of artificial *** on the statistical correlations uncovered by deep learning-based methods,computer vision tasks,such as autonomous driving and robotics,are growing *** being the basis of deep learning,such correlation strongly depends on the distribution of the original data and is susceptible to uncontrolled *** the guidance of prior knowledge,statistical correlations alone cannot correctly reflect the essential causal relations and may even introduce spurious *** a result,researchers are now trying to enhance deep learningbased methods with causal *** theory can model the intrinsic causal structure unaffected by data bias and effectively avoids spurious *** paper aims to comprehensively review the existing causal methods in typical vision and visionlanguage tasks such as semantic segmentation,object detection,and image *** advantages of causality and the approaches for building causal paradigms will be *** roadmaps are also proposed,including facilitating the development of causal theory and its application in other complex scenarios and systems.

关键词： causal reasoning computer vision tasks vision-language tasks semantic segmentation object detection

Control of defensive behavior by the nucleus of Darkschewitsch GABAergic neurons

在线全文

学校读者我要写书评

暂无评论

National Science Review 2024年第4期11卷 70-83页

作者： Huiying Zhao Jinrong Liu Yujin Shao Xiang Feng Binhan Zhao Li Sun Yijun Liu Linghui Zeng Xiao-ming Li Hongbin Yang Shumin Duan Yan-qin Yu Department of Neurology of Second Affiliated Hospital and School of Brain Science and Brain Medicine Zhejiang University School of Medicine Nanhu Brain-Computer Interface Institute Liangzhu laboratory MOE Frontier Science Center for Brain Science and Brain-Machine Integration State Key Laboratory of Brain-Machine Intelligence Zhejiang University NHC and CAMS key {1. of Medical Neurobiology Zhejiang University key {1. of Novel Targets and Drug Study for Neural Repair of Zhejiang Province School of Medicine Hangzhou City University

The nucleus of Darkschewitsch(ND), mainly composed of GABAergic neurons, is widely recognized as a component of the eye-movement controlling system. However, the functional contribution of ND GABAergic neurons(NDGABA) in animal behavior is largely unknown. Here, we show that NDGABA neurons were selectively activated by different types of fear stimuli, such as predator odor and foot *** and chemogenetic manipulations revealed that NDGABA neurons mediate freezing ***, using circuit-based optogenetic and neuroanatomical tracing methods, we identified an excitatory pathway from the lateral periaqueductal gray(l PAG) to the ND that induces freezing by exciting ND inhibitory outputs to the motor-related gigantocellular reticular nucleus, ventral part(Gi V). Together,these findings indicate the NDGABA population as a novel hub for controlling defensive response by relaying fearful information from the l PAG to Gi V, a mechanism critical for understanding how the freezing behavior is encoded in the mammalian brain.

关键词： nucleus of Darkschewitsch GABAergic population defensive behavior freezing neural circuitry

A Feature-Aided Multiple Model Algorithm for Maneuvering Target Tracking

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 566-568页

作者： Yiwei Tian Meiqin Liu Senlin Zhang Ronghao Zheng Shanling Dong College of Electrical Engineering Zhejiang University National key {1. of Industrial Control Technology Zhejiang University IEEE National key {1. of Human-machine Hybrid Augmented Intelligence Xi’an Jiaotong University

Dear Editor,This letter deals with the tracking problem for non-cooperative maneuvering targets based on the underwater sensor networks. Considering the acoustic intensity feature of underwater targets, a feature-aide... 详细信息

关键词： underwater Aided letter

A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation

在线全文

学校读者我要写书评

暂无评论

machine Intelligence Research 2024年第4期21卷 801-814页

作者： Feng Sun Ming-Kun Xie Sheng-Jun Huang MIIT key {1. of Pattern Analysis and machine Intelligence College of Computer Science and TechnologyNanjing University of AeronauticsandAstronauticsNanjing211106China

In this paper,we study the partial multi-label(PML)image classification problem,where each image is annotated with a candidate label set consisting of multiple relevant labels and other noisy *** PML methods typically design a disambiguation strategy to filter out noisy labels by utilizing prior knowledge with extra assumptions,which unfortunately is unavailable in many real ***,because the objective function for disambiguation is usually elaborately designed on the whole training set,it can hardly be optimized in a deep model with stochastic gradient descent(SGD)on *** this paper,for the first time,we propose a deep model for PML to enhance the representation and discrimination *** the one hand,we propose a novel curriculum-based disambiguation strategy to progressively identify ground-truth labels by incorporating the varied difficulties of different *** the other hand,consistency regularization is introduced for model training to balance fitting identified easy labels and exploiting potential relevant *** experimental results on the commonly used benchmark datasets show that the proposed method significantlyoutperforms the SOTA methods.

关键词： Partial multi-label image classification curriculum-based disambiguation consistency regularization label difficulty candidatelabel set.

Visual Semantic Segmentation Based on Few/Zero-Shot Learning:An Overview

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1106-1126页

作者： Wenqi Ren Yang Tang Qiyu Sun Chaoqiang Zhao Qing-Long Han key {1. of Smart Manufacturing in Energy Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China National key {1. of Air-Based Information perception and Fusion Aviation Industry Corporation of ChinaLuoyang 471000China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia

Visual semantic segmentation aims at separating a visual sample into diverse blocks with specific semantic attributes and identifying the category for each block,and it plays a crucial role in environmental *** learning-based visual semantic segmentation approaches count heavily on largescale training data with dense annotations and consistently fail to estimate accurate semantic labels for unseen *** obstruction spurs a craze for studying visual semantic segmentation with the assistance of few/zero-shot *** emergence and rapid progress of few/zero-shot visual semantic segmentation make it possible to learn unseen categories from a few labeled or even zero-labeled samples,which advances the extension to practical ***,this paper focuses on the recently published few/zero-shot visual semantic segmentation methods varying from 2D to 3D space and explores the commonalities and discrepancies of technical settlements under different segmentation ***,the preliminaries on few/zeroshot visual semantic segmentation,including the problem definitions,typical datasets,and technical remedies,are briefly reviewed and ***,three typical instantiations are involved to uncover the interactions of few/zero-shot learning with visual semantic segmentation,including image semantic segmentation,video object segmentation,and 3D ***,the future challenges of few/zero-shot visual semantic segmentation are discussed.

关键词： Visual segmentation separating