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 laboratory 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

Corporate Credit Ratings Based on Hierarchical Heterogeneous Graph Neural Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

machine Intelligence Research 2024年第2期21卷 257-271页

作者： Bo-Jing Feng Xi Cheng Hao-Nan Xu Wen-Fang Xue Center for Research on Intelligent perception and Computing National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of SciencesBeijing 100190China

order to help investors understand the credit status of target corporations and reduce investment risks,the corporate credit rating model has become an important evaluation tool in the financial *** models are based on statistical learning,machine learning and deep learning especially graph neural networks(GNNs).However,we found that only few models take the hierarchy,heterogeneity or unlabeled data into account in the actual corporate credit rating ***,we propose a novel framework named hierarchical heterogeneous graph neural networks(HHGNN),which can fully model the hierarchy of corporate features and the heterogeneity of relationships between *** addition,we design an adversarial learning block to make full use of the rich unlabeled samples in the financial *** experiments conducted on the public-listed corporate rating dataset prove that HHGNN achieves SOTA compared to the baseline methods.

关键词： Corporate credit rating hierarchical relation heterogeneous graph neural networks adversarial learning

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 laboratory 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

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 laboratory 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

Boosting Multi-modal Ocular Recognition via Spatial Feature Reconstruction and Unsupervised Image Quality Estimation

在线全文

学校读者我要写书评

暂无评论

machine Intelligence Research 2024年第1期21卷 197-214页

作者： Zihui Yan Yunlong Wang Kunbo Zhang Zhenan Sun Lingxiao He Center for Research on Intelligent perception and Computing National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of SciencesBeijing 100190China JD AI Research Beijing 100176China

In the daily application of an iris-recognition-at-a-distance(IAAD)system,many ocular images of low quality are *** the iris part of these images is often not qualified for the recognition requirements,the more accessible periocular regions are a good complement for *** further boost the performance of IAAD systems,a novel end-to-end framework for multi-modal ocular recognition is *** proposed framework mainly consists of iris/periocular feature extraction and matching,unsupervised iris quality assessment,and a score-level adaptive weighted fusion ***,ocular feature reconstruction(OFR)is proposed to sparsely reconstruct each probe image by high-quality gallery images based on proper feature ***,a brand new unsupervised iris quality assessment method based on random multiscale embedding robustness is *** from the existing iris quality assess-ment methods,the quality of an iris image is measured by its robustness in the embedding *** last,the fusion strategy exploits the iris quality score as the fusion weight to coalesce the complementary information from the iris and periocular *** experi-mental results on ocular datasets prove that the proposed method is obviously better than unimodal biometrics,and the fusion strategy can significantly improve therecognition performance.

关键词： Iris recognition periocular recognition spatial feature reconstruction fully convolutional network flexible matching unsupervised iris quality assessment adaptive weight fusion

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 laboratory of Tourism Multisource Data perception and Decision Ministry of Culture and TourismChongqing University of Posts and TelecommunicationsChongqing 400065China Chongqing Key laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Chongqing Key laboratory 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

Causal reasoning in typical computer vision tasks

在线全文

维普期刊数据库

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 laboratory of Advanced Control and Optimization for Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China National Key laboratory 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

CASIA-Iris-Africa:A Large-scale African Iris Image Database

在线全文

学校读者我要写书评

暂无评论

machine Intelligence Research 2024年第2期21卷 383-399页

作者： Jawad Muhammad Yunlong Wang Junxing Hu Kunbo Zhang Zhenan Sun School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent perception and Computing National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of SciencesBeijing 100190China

Iris biometrics is a phenotypic biometric trait that has proven to be agnostic to human natural physiological *** on iris biometrics has progressed tremendously,partly due to publicly available iris *** databases have been available to researchers that address pressing iris biometric challenges such as constraint,mobile,multispectral,synthetics,long-distance,contact lenses,liveness detection,***,these databases mostly contain subjects of Caucasian and Asian docents with very few *** many investigative studies on racial bias in face biometrics,very few studies on iris biometrics have been published,mainly due to the lack of racially diverse large-scale databases containing sufficient iris samples of Africans in the public ***,most of these databases contain a relatively small number of subjects and labelled *** paper proposes a large-scale African database named Chinese Academy of Sciences Institute of Automation(CASIA)-Iris-Africa that can be used as a complementary database for the iris recognition community to mediate the effect of racial biases on *** database contains 28717 images of 1023 African subjects(2046 iris classes)with age,gender,and ethnicity attributes that can be useful in demographically sensitive studies of *** of specific application protocols are incorporated with the database to ensure the database’s variability and *** results of some open-source state-of-the-art(SOTA)algorithms on the database are presented,which will serve as baseline *** relatively poor performances of the baseline algorithms on the proposed database despite better performance on other databases prove that racial biases exist in these iris recognition algorithms.

关键词： African iris recognition racial bias iris image database biometrics iris recognition

Joint Active and Passive Beamforming Design in Intelligent Reflecting Surface(IRS)-Assisted Covert Communications:A Multi-Agent DRL 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9期21卷 11-26页

作者： Gao Ang Ren Xiaoyu Deng Bin Sun Xinshun Zhang Jiankang School of Electronic Information Northwestern Polytechnical UniversityXi’an 710072China Key laboratory of Near Ground Detection and perception Technology Wuxi 214035China Department of Computing and Informatics Bournemouth UniversityUK

Intelligent Reflecting Surface(IRS),with the potential capability to reconstruct the electromagnetic propagation environment,evolves a new IRSassisted covert communications paradigm to eliminate the negligible detection of malicious eavesdroppers by coherently beaming the scattered signals and suppressing the signals ***,when multiple IRSs are involved,accurate channel estimation is still a challenge due to the extra hardware complexity and communication *** the crossinterference caused by massive reflecting paths,it is hard to obtain the close-formed solution for the optimization of covert *** this basis,the paper improves a heterogeneous multi-agent deep deterministic policy gradient(MADDPG)approach for the joint active and passive beamforming(Joint A&P BF)optimization without the channel estimation,where the base station(BS)and multiple IRSs are taken as different types of agents and learn to enhance the covert spectrum efficiency(CSE)*** to the‘centralized training and distributed execution’feature of MADDPG,each agent can execute the active or passive beamforming independently based on its partial observation without referring to *** results demonstrate that the proposed deep reinforcement learning(DRL)approach could not only obtain a preferable CSE of legitimate users and a low detection of probability(LPD)of warden,but also alleviate the communication overhead and simplify the IRSs deployment.

关键词： covert communications deep reinforcement learning intelligent reflecting surface