检索结果-内蒙古大学图书馆

7th International Conference on computer Information science and application Technology, CISAT 2024

作者： Su, Ruilin Zhang, Wanshan Yu, Dunhui Hubei University Wuhan China Wuhan430062 China Hubei University School of Computer Science and Information Engineering Wuhan430062 China Hubei University Hubei Key Laboratory of Big Data Intelligent Analysis and Application Wuhan430062 China Engineering and Technical Research Center of Hubei Province in Software Engineering Wuhan430062 China

ISBN: (纸本)9798350375107

Multi-hop Knowledge Reasoning is a task that involves generating an answer given a query and a knowledge graph. Existing sequence-to-sequence reasoning models use the Transformer to encode and decode sequences, but these models have some flaws, such as the inability to effectively handle long-sequence reasoning and susceptibility to exposure bias. To address these issues, we provides a sequence-to-sequence reasoning model named STSR, which is based on Retentive Network. aiming at improving training efficiency through parallel training, this model leverages the advantages in Retentive Network, reduce time overhead, and enhance reasoning efficiency through iterative reasoning. It effectively mitigates the problems of high spatial overhead and low efficiency in long-sequence reasoning faced by the Transformer. Moreover, it retains and updates historical information during the encoding and decoding process, enhancing the model's memory and generalization capabilities. Additionally, the Scheduled Sampling method is adopted to alleviate the exposure bias introduced during reasoning, which involves using the model's own output as the input for the next moment with a certain probability during training, instead of using the true label. We conduct the experiment on six public datasets, with the results showing that the proposed model outperforms existing baseline models in terms of precision and generation quality. This paper provides a new solution for the task of sequence-to-sequence multihop knowledge reasoning and also demonstrates the potential application of the Retentive Network in natural language processing. © 2024 IEEE.

关键词： Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

Pretraining Conformer with ASR for Speaker Verification 48

Pretraining Conformer with ASR for Speaker Verification

引用

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

作者： Cai, Danwei Wang, Weiqing Li, Ming Xia, Rui Huang, Chuanzeng Duke University Department of Electrical and Computer Engineering Durham United States Duke Kunshan University Data Science Research Center Kunshan China Group Bytedance China

ISBN: (纸本)9781728163277

This paper proposes to pretrain Conformer with automatic speech recognition (ASR) task for speaker verification. Conformer combines convolution neural network (CNN) and Transformer model for modeling local and global features, respectively. Recently, multi-scale feature aggregation Conformer (MFA-Conformer) has been proposed for automatic speaker verification. MFA-Conformer concatenates frame-level outputs from all Conformer blocks for further pooling. However, our experiments show that Conformer can be easily overfitted with limited speaker recognition training data. To avoid overfitting, we propose to transfer the knowledge learned from ASR to speaker verification. Specifically, an ASR pretrained Conformer is used to initialize the training of MFA-Conformer for speaker verification. Our experiments show that pretraining Conformer with ASR leads to significant performance gains across model sizes. The best model achieves 0.48%, 0.71% and 1.54% EER on Voxceleb1-O, Voxceleb1-E, and Voxceleb1-H, respectively. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

WheatNet: Attentional Path Aggregation Feature Pyramid Network for Precise Detection and Counting of Dense and Arbitrary-Oriented Wheat Spikes

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2024年第2期2卷 606-616页

作者： Jiao, Lin Liu, Qihuang Liu, Haiyun Chen, Peng Wang, Rujing Liu, Kang Dong, Shifeng Anhui University School of Internet Hefei230031 China Chinese Academy of Sciences National Engineering Research Center for Agro-Ecological Big Data Analysis and Application Hefei230031 China Chinese Academy of Sciences Institute of Intelligent Machines Hefei Institutes of Physical Science Hefei230031 China University of Science and Technology of China Hefei230031 China Anhui University National Engineering Research Center for Agro-Ecological Big Data Analysis and Application Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Internet Hefei230601 China Anhui University Institutes of Physical Science and Information Technology Hefei230601 China Chinese Academy of Science Institute of Intelligent Machines Hefei Institutes of Physical Science Hefei230031 China University of Sheffield Department of Computer Science SheffieldS10 2TN United Kingdom Institute of Dataspace Hefei230093 China

Achieving the precise and real-time detection of wheat spikes play a crucial role in wheat growth monitoring for precision agriculture community. Machine-learning methods are commonly introduced to automatically detect and count the wheat spikes, which need carefully selected hand-crafted feature descriptors, leading to time-consuming and poor performance. The deep learning has become a promising technology for the accurate detection wheat spikes, owing to its powerful ability of feature extraction. However, the obtained wheat spike images from UAV still have serious overlap, dense distribution, various orientations, and large aspect ratios, leading to poor performance of recent wheat spike detection method. To address the demand of precise and fast detection and counting of wheat spike with dense distribution and arbitrary-orientation, a novel deep learning-based method, WheatNet, has been proposed. The attention mechanism has been introduced the process of feature fusing to highlight the important features of wheat spike as well as inhibit the useless information. Additionally, to optimize the parameters of the network, a loss function with soft dynamic label assignment is adopted to reduce the number of low-quality matches, which provides significant performance gains over other wheat spike detectors. Furthermore, to achieve the precise detection of wheat spike with multi-orientations, a large-scale oriented wheat spike dataset has been constructed, named RoWheat, including 900 images and 50419 annotations with dense distribution and various orientation. Experimental studies demonstrate that the proposed WheatNet achieves a recall of 99.7% and mAP of 91.8%, showing its promising performance gain compared to other state-of-the-art methods. © 2023 IEEE.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Waveform Boundary Detection for Partially Spoofed Audio 48

Waveform Boundary Detection for Partially Spoofed Audio

引用

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

作者： Cai, Zexin Wang, Weiqing Li, Ming Duke University Department of Electrical and Computer Engineering DurhamNC27708 United States Duke Kunshan University Data Science Research Center Kunshan215316 China

ISBN: (纸本)9781728163277

The present paper proposes a waveform boundary detection system for audio spoofing attacks containing partially manipulated segments. Partially spoofed/fake audio, where part of the utterance is replaced, either with synthetic or natural audio clips, has recently been reported as one scenario of audio deepfakes. As deepfakes can be a threat to social security, the detection of such spoofing audio is essential. Accordingly, we propose to address the problem with a deep learning-based frame-level detection system that can detect partially spoofed audio and locate the manipulated pieces. Our proposed method is trained and evaluated on data provided by the ADD2022 Challenge. We evaluate our detection model concerning various acoustic features and network configurations. As a result, our detection system achieves an equal error rate (EER) of 6.58% on the ADD2022 challenge test set, which is the best performance in partially spoofed audio detection systems that can locate manipulated clips. © 2023 IEEE.

关键词： ADD challenge Anti-spoofing Partially spoofed audio detection Wav2Vec

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis: Indonesia Netflix User's Comment Using Multiple Lexicon-Based Dictionaries 4

Sentiment Analysis: Indonesia Netflix User's Comment Using M...

引用

4th International Conference on Intelligent Cybernetics Technology and applications, ICICyTA 2024

作者： Mola, Sebastianus Adi Santoso Widiastuti, Tiwuk Roma, Rosa V. K. Isabela Ohe Karnyoto, Andrea Stevens Pardamean, Bens University of Nusa Cendana Faculty of Science and Engineering Kupang Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331506490

A subscription movie streaming service from the United States, Netflix, has been present in Indonesia since 2016 and provides a wide variety of films without showing any single advertisements that can be viewed from anywhere, as long as there is access to the internet. Despite these advantages, many users have complained through the Google Play Store's comments column. Some of the common complaints include frequent buffering and connectivity issues, dissatisfaction with the limited selection of Indonesian movies, lack of subtitles for specific languages, or pricing concerns have also been raised. In this study developed two combined scenario methods using the InSet and SentiStrength-id dictionary to obtain better performance and compare them against independent InSet and SentiStrength-id. This study collected users' comments for the Netflix app in the Google Play Store as a dataset using web scraping techniques through the Google Collaboration tool. The dataset contains 3250 rows spanning the period from January 22, 2024, through June 6, 2024. To ensure proper processing of the text, data cleaning, lowercasing, normalization, tokenization, stemming, and stopwords removal are conducted. The results show that most user opinions are negative. The InSet dictionary has an accuracy of 92%, SentiStrength-id 78%, Combined scenario 1 is 87%, and scenario 2 reaches the highest among others which is 92.52%. © 2024 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Enhancing Breast Cancer Diagnosis with Vision Transformers: A Novel Approach using MaskGuided Attention for Ultrasound Image Classification

Enhancing Breast Cancer Diagnosis with Vision Transformers: ...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Deena Sivakumar Anamika Kumari Divya Dharshini K Samiksha S Hemachandran M Department of Computer Science and Engineering Sri Ramachandra Institute of Higher Education and Research Chennai Department of Computer Science (AI & Data Analytics) Sri Ramachandra Institute of Higher Education and Research Chennai

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Deep learning models, notably convolutional neural networks (CNNs), demonstrate great promise in medical image processing. Nonetheless, CNNs frequently encounter challenges in capture holistic context and long- range dependencies in high-resolution images, which are crucial for accurate medical diagnostics. A new state-of-the-art technique called Vision Transformers (ViTs) uses self-attention mechanisms for gathering global correlations between image patches, thereby addressing some of the inherent limitations of CNNs. This study investigates the application of ViTs for diagnosing breast cancer from ultrasound images of tumor. The findings suggest that ViTs not only achieve competitive accuracy in identifying breast cancer lesions but also offer superior interpretability through attention mechanism, which can aid clinicians in understanding model decisions. This paper highlights the potential of ViTs as a powerful tool in medical imaging, particularly for breast cancer diagnosis, and outlines future research directions for enhancing clinical applicability.

关键词： Deep learning computer vision Accuracy Attention mechanisms Ultrasonic imaging Transformers Breast cancer Convolutional neural networks Medical diagnosis Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

RoSe: Rotation-Invariant Sequence-Aware Consensus for Robust Correspondence Pruning 24

RoSe: Rotation-Invariant Sequence-Aware Consensus for Robust...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Liu, Yizhang Zhou, Weiwei Li, Yanping Zhao, Shengjie School of Software Engineering Tongji University Shanghai China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Technology Tongji University Shanghai China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai China

ISBN: (纸本)9798400706868

Correspondence pruning has recently drawn considerable attention as a crucial step in image matching. Existing methods typically achieve this by constructing neighborhoods for each feature point and imposing neighborhood consistency. However, the nearest-neighbor matching strategy often results in numerous many-to-one correspondences, thereby reducing the reliability of neighborhood information. Furthermore, the smoothness constraint fails in cases of large-scale rotations, leading to misjudgments. To address the above issues, this paper proposes a novel robust correspondence pruning method termed RoSe, which is based on rotation-invariant sequence-aware consensus. We formulate the correspondence pruning problem as a mathematical optimization problem and derive a closed-form solution. Specifically, we devise a rectified local neighborhood construction strategy that effectively enlarges the distribution between inliers and outliers. Meanwhile, to accommodate large-scale rotation, we propose a relative sequence-aware consistency as an alternative to existing smoothness constraints, which can better characterize the topological structure of inliers. Experimental results on image matching and registration tasks demonstrate the effectiveness of our method. Robustness analysis involving diverse feature descriptors and varying rotation degrees further showcases the efficacy of our method. © 2024 ACM.

关键词： correspondence pruning

来源：评论

学校读者我要写书评

暂无评论

LSGraph: A Locality-centric High-performance Streaming Graph Engine 24

LSGraph: A Locality-centric High-performance Streaming Graph...

引用

19th European Conference on computer Systems, EuroSys 2024

作者： Qi, Hao Wu, Yiyang He, Ligang Zhang, Yu Luo, Kang Cai, Minzhi Jin, Hai Zhang, Zhan Zhao, Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computer Science University of Warwick United Kingdom Zhejiang Lab China

ISBN: (纸本)9798400704376

Streaming graph has been broadly employed across various application domains. It involves updating edges to the graph and then performing analytics on the updated graph. However, existing solutions either suffer from poor data locality and high computation complexity for streaming graph analytics, or need high overhead to search and move graph data to ensure ordered neighbors during streaming graph update. This paper presents a novel locality-centric streaming graph engine, called LSGraph, to enable efficient both graph analytics and graph update. The main novelty of this engine is a differentiated hierarchical indexed streaming graph representation approach to achieve efficient data search and movement for graph update and also maintain data locality and ordered neighbors for efficient graph analytics simultaneously. Besides, a locality-aware streaming graph data update mechanism is also proposed to efficiently regulate the distance of data movement, minimizing the overhead of memory access during graph update. We have implemented LSGraph and conducted a systematic evaluation on both real-world and synthetic datasets. Compared with three cutting-edge streaming graph engines, i.e., Terrace, Aspen, and PaC-tree, LSGraph achieves 2.98×-81.08×, 1.46×-12.56×, and 1.26×-10.31× speedups during graph update, while obtaining 1.02×-4.28×, 1.58×-3.55×, and 1.20×-2.72× speedups during graph analytics, respectively. © 2024 Owner/Author.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

CNN-based Text-independent Automatic Speaker Identification Using Short Utterances 6

CNN-based Text-independent Automatic Speaker Identification ...

引用

6th International Conference on computer science and engineering, UBMK 2021

作者： Fasounaki, Mandana Yüce, Emirhan Burak Öncül, Serkan Ince, Gökhan Department of Computer Engineering Istanbul Technical University Istanbul Turkey Arçelik Research and Development Istanbul Turkey Department of Computer Engineering and AI and Data Science Application and Research Center Istanbul Technical University Istanbul Turkey

ISBN: (纸本)9781665429085

With the widespread use of voice-controlling services and devices, the research for developing robust and fast systems for automatic speaker identification had accelerated. In this paper, we present a Convolutional Neural Network (CNN) architecture for text-independent automatic speaker identification. The primary purpose is to identify a speaker, among many others, using a short speech segment. Most of the current researches focus on deep CNNs, which were initially designed for computer vision tasks. Besides, most of the existing speaker identification methods require audio samples longer than 3 seconds in the query phase for achieving a high accuracy. We created a CNN architecture appropriate for voice and speech-related classification tasks. We propose an optimum model that achieves 99.5% accuracy on LibriSpeech and 90% accuracy on VoxCeleb 1 dataset using only 1-second test utterances in our experiments. © 2021 IEEE

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

SC-GNN: A Communication-Efficient Semantic Compression for Distributed Training of GNNs 24

SC-GNN: A Communication-Efficient Semantic Compression for D...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Wang, Jihe Wu, Ying Wang, Danghui School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798400706011

Training big graph neural networks (GNNs) in distributed systems is quite time-consuming mainly because of the ubiquitous aggregate operations that involve a large amount of cross-partition communication for collecting embeddings/gradients during the forward and backward propagation. To reduce the volume of the communication, some recent approaches focused on decaying each of connections via sampling, quantifying, or delaying until satisfactory trade-off are obtained between volume and accuracy. However, when applied to popular GNNs, those approaches are found to be bounded by a common volume/accuracy Pareto frontier which shows that the decaying for individual connection cannot further accelerate the aggregate of training. In this work, SC-GNN, a semantic compression of the cross-partition communication, is proposed to concentrate a group of connections as a high-level semantics and transmit to a target partition. Since carrying the overall intent of a group, the semantics can keep transferring the interactions, i.e., embeddings/gradients, between a pair of remote partitions until GNN models converge. In addition, a connection-pattern based differential optimization is proposed to further prune those weak connections, while guaranteeing the training accuracy. The results show that, for multi-field datasets, the compression rate of SC-GNN is 40.8 × higher than SOTA methods and the epoch time is reduced to 31.8% on average. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph neural networks

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：