检索结果-内蒙古大学图书馆

FGSSI: A Feature-Enhanced Framework with Transferability for Sequential Source Identification

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Hou, Dongpeng Gao, Chao Wang, Zhen Li, Xuelong Shaanxi Xi'an710072 China Shaanxi Xi'an710072 China School of iOPEN NWPU Shaanxi Xi'an710072 China

Source localization based on snapshot observations has gained popularity owing to its low cost and accessibility. However, current methods do not adequately address the impact of user interaction in time-varying infection scenarios, leading to reduced accuracy in heterogeneous interaction environments. To address these issues and ensure transferability and applicability in different scenarios, this paper proposes an inductive localization framework based on sequence-to-sequence architecture, named Feature-representation-based Graph Sequential Source Identification (FGSSI). Particularly, FGSSI employs a user-feature-construction-based encoder to construct low-dimensional embeddings of each individual by evaluating their dynamic and static behavioral attributes at different timestamps. Additionally, FGSSI uses a graph-GRU based decoder with temporal attention to infer the source by incorporating graph topology information into the sequential model and handling imbalanced infection information under temporal characteristics. It is worth mentioning that FGSSI can detect sources in new scenarios without prior knowledge owing to the proposed inductive learning approach. Comprehensive experiments using SOTA methods demonstrate FGSSI's superior detection performance and transferability. © 2004-2012 IEEE.

关键词： inductive learning sequence-to-sequence learning Source identification temporal attention user's interactive behavior

来源：评论

学校读者我要写书评

暂无评论

Linear-Time Korean Morphological Analysis Using an Action-based Local Monotonic Attention Mechanism

引用

ETRI JOURNAL 2020年第1期42卷 101-107页

作者： Hwang, Hyunsun Lee, Changki Kangwon Natl Univ Dept Comp Sci Chunchon South Korea

For Korean language processing, morphological analysis is a critical component that requires extensive work. This morphological analysis can be conducted in an end-to-end manner without requiring a complicated feature design using a sequence-to-sequence model. However, the sequence-to-sequence model has a time complexity of O(n(2)) for an input length n when using the attention mechanism technique for high performance. In this study, we propose a linear-time Korean morphological analysis model using a local monotonic attention mechanism relying on monotonic alignment, which is a characteristic of Korean morphological analysis. The proposed model indicates an extreme improvement in a single threaded environment and a high morphometric F1-measure even for a hard attention model with the elimination of the attention mechanism formula.

关键词： deep learning korean morphological analysis local attention mechanism natural language processing sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

sequence-to-sequence Emotional Voice Conversion With Strength Control

引用

IEEE ACCESS 2021年 9卷 42674-42687页

作者： Choi, Heejin Hahn, Minsoo Korea Adv Inst Sci & Technol KAIST Dept Elect Engn Daejeon 34141 South Korea

This paper proposes an improved emotional voice conversion (EVC) method with emotional strength and duration controllability. EVC methods without duration mapping generate emotional speech with identical duration to that of the neutral input speech. In reality, even the same sentences would have different speeds and rhythms depending on the emotions. To solve this, the proposed method adopts a sequence-to-sequence network with an attention module that enables the network to learn attention in the neutral input sequence should be focused on which part of the emotional output sequence. Besides, to capture the multi-attribute aspects of emotional variations, an emotion encoder is designed for transforming acoustic features into emotion embedding vectors. By aggregating the emotion embedding vectors for each emotion, a representative vector for the target emotion is obtained and weighted to reflect emotion strength. By introducing a speaker encoder, the proposed method can preserve speaker identity even after the emotion conversion. Objective and subjective evaluation results confirm that the proposed method is superior to other previous works. Especially, in emotion strength control, we achieve in getting successful results.

关键词： Acoustics Decoding Training Feature extraction Vocoders Linguistics Indexes Voice conversion emotional voice conversion emotion strength sequence-to-sequence learning controllable emotional voice conversion

来源：评论

学校读者我要写书评

暂无评论

SLOAN: Scale-Adaptive Orientation Attention Network for Scene Text Recognition

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2021年 30卷 1687-1701页

作者： Dai, Pengwen Zhang, Hua Cao, Xiaochun Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing 100195 Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing 100049 Peoples R China Cyberspace Secur Res Ctr Peng Cheng Lab Shenzhen 518055 Peoples R China

Scene text recognition, the final step of the scene text reading system, has made impressive progress based on deep neural networks. However, existing recognition methods devote to dealing with the geometrically regular or irregular scene text. They are limited to the semantically arbitrary-orientation scene text. Meanwhile, previous scene text recognizers usually learn the single-scale feature representations for various-scale characters, which cannot model effective contexts for different characters. In this paper, we propose a novel scale-adaptive orientation attention network for arbitrary-orientation scene text recognition, which consists of a dynamic log-polar transformer and a sequence recognition network. Specifically, the dynamic log-polar transformer learns the log-polar origin to adaptively convert the arbitrary rotations and scales of scene texts into the shifts in the log-polar space, which is helpful to generate the rotation-aware and scale-aware visual representation. Next, the sequence recognition network is an encoder-decoder model, which incorporates a novel character-level receptive field attention module to encode more valid contexts for various-scale characters. The whole architecture can be trained in an end-to-end manner, only requiring the word image and its corresponding ground-truth text. Extensive experiments on several public datasets have demonstrated the effectiveness and superiority of our proposed method.

关键词： Scene text recognition arbitrary orientation log-polar transformation attention mechanism sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

Approximate Computing for Long Short Term Memory (LSTM) Neural Networks

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2018年第11期37卷 2266-2276页

作者： Sen, Sanchari Raghunathan, Anand Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA

Long Short Term Memory (LSTM) networks are a class of recurrent neural networks that are widely used for machine learning tasks involving sequences, including machine translation, text generation, and speech recognition. Large-scale LSTMs, which are deployed in many real-world applications, are highly compute intensive. To address this challenge, we propose AxLSTM, an application of approximate computing to improve the execution efficiency of LSTMs. An LSTM is composed of cells, each of which contains a cell state along with multiple gating units that control the addition and removal of information from the state. The LSTM execution proceeds in timesteps, with a new symbol of the input sequence processed at each timestep. AxLSTM consists of two techniques-Dynamic Timestep Skipping (DTS) and Dynamic State Reduction (DSR). DTS identifies, at runtime, input symbols that are likely to have little or no impact on the cell state and skips evaluating the corresponding timesteps. In contrast, DSR reduces the size of the cell state in accordance with the complexity of the input sequence, leading to a reduced number of computations per timestep. We describe how AxLSTM can be applied to the most common application of LSTMs, viz., sequence-to-sequence learning. We implement AxLSTM within the TensorFlow deep learning framework and evaluate it on 3 state-of-the-art sequence-to-sequence models. On a 2.7 GHz Intel Xeon server with 128 GB memory and 32 processor cores, AxLSTM achieves 1.08 x -1.31x speedups with minimal loss in quality, and 1.12 x -1.37x speedups when moderate reductions in quality are acceptable.

关键词： Approximate computing long short term memory (LSTM) networks sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

E2S2: Encoding-Enhanced sequence-to-sequence Pretraining for Language Understanding and Generation

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第12期36卷 8037-8050页

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Du, Bo Tao, Dacheng Wuhan Univ Inst Artificial Intelligence Natl Engn Res Ctr Multimedia Software Sch Comp Sci Wuhan 430072 Peoples R China Wuhan Univ Hubei Key Lab Multimedia Network Commun Engn Wuhan 430072 Peoples R China Univ Sydney Fac Engn Sch Comp Sci Sydney Australia

-sequence-to-sequence (seq2seq) learning is a popular fashion for large-scale pretraining language models. However, the previous seq2seq pretraining models generally focus on reconstructive objectives on the decoder side and neglect the effect of encoder-side supervision, which we argue may lead to sub-optimal performance. To verify our hypothesis, we first empirically study the functionalities of the encoder and decoder in seq2seq pretrained language models, and find that the encoder takes an important but under-exploitation role than the decoder regarding the downstream performance and neuron activation. Therefore, we propose an encoding-enhanced seq2seq pretraining strategy, namely E2S2, which improves the seq2seq models via integrating more efficient self-supervised information into the encoders. Specifically, E2S2 adopts two self-supervised objectives on the encoder side from two aspects: 1) locally denoising the corrupted sentence (denoising objective);and 2) globally learning better sentence representations (contrastive objective). With the help of both objectives, the encoder can effectively distinguish the noise tokens and capture high-level (i.e., syntactic and semantic) knowledge, thus strengthening the ability of seq2seq model to accurately achieve the conditional generation. On a large diversity of downstream natural language understanding and generation tasks, E2S2 dominantly improves the performance of its powerful backbone models, e.g., BART and T5. For example, upon BART backbone, we achieve +1.1% averaged gain on the general language understanding evaluation (GLUE) benchmark and +1.75% F 0 . 5 score improvement on CoNLL2014 dataset. We also provide in-depth analyses to show the improvement stems from better linguistic representation. We hope that our work will foster future self-supervision research on seq2seq language model pretraining.

关键词： Language understanding and generation pretraining self-supervised learning self-supervised learning sequence-to-sequence learning sequence-to-sequence learning self-supervised learning sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

Neuro-evolutionary for time series forecasting and its application in hourly energy consumption prediction

引用

NEURAL COMPUTING & APPLICATIONS 2023年第29期35卷 21697-21707页

作者： Son, Nguyen Ngoc Van Cuong, Nguyen Ind Univ Ho Chi Minh City Fac Elect Technol Ho Chi Minh City Vietnam Ind Univ Ho Chi Minh City IUQ Ho Chi Minh City Vietnam

This paper proposed an ensemble methodology comprising neural networks, modified differential evolution algorithm and nonlinear autoregressive network with exogenous inputs (NARX) (called neuro-evolutionary NARX or NE-NARX model) for time series forecasting. In NE-NARX, the structure is designed by connecting the neural model and NARX model, and the weight value connection is optimized by a modified differential evolution algorithm. The effectiveness of the proposed NE-NARX model is tested on two well-known benchmark datasets, including the Canadian lynx and the Wolf sunspot. The proposed model is compared to other models, including the classical backpropagation algorithm, particle swarm optimization, differential evolution (DE) and DE variants. Additionally, an ARIMA model is employed as the benchmark for evaluating the capacity of the proposed model. And then, NE-NARX model is used for hourly energy consumption prediction through comparison with other machine learning models including gated recurrent units, convolutional neural networks (CNN), long short-term memory (LSTM), a hybrid CNN-LSTM and sequence-to-sequence learning. Results show convincingly the superiority of the proposed NE-NARX model over other models.

关键词： Neuro-evolutionary ARIMA Differential evolution GRU LSTM CNN sequence-to-sequence learning

来源：评论

学校读者我要写书评

暂无评论

learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks

引用

ROBOTICS AND AUTONOMOUS SYSTEMS 2018年 109卷 13-26页

作者： Plappert, Matthias Mandery, Christian Asfour, Tamim Karlsruhe Inst Technol High Performance Humanoid Technol H2T Adenauerring 2Bldg 50-20 D-76131 Karlsruhe Germany

Linking human whole-body motion and natural language is of great interest for the generation of semantic representations of observed human behaviors as well as for the generation of robot behaviors based on natural language input. While there has been a large body of research in this area, most approaches that exist today require a symbolic representation of motions (e.g. in the form of motion primitives), which have to be defined a-priori or require complex segmentation algorithms. In contrast, recent advances in the field of neural networks and especially deep learning have demonstrated that sub-symbolic representations that can be learfied end-to-end usually outperform more traditional approaches, for applications such as machine translation. In this paper we propose a generative model that learns a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks (RNNs) and sequence-to-sequence learning. Our approach does not require any segmentation or manual feature engineering and learns a distributed representation, which is shared for all motions and descriptions. We evaluate our approach on 2 846 human whole-body motions and 6 187 natural language descriptions thereof from the KIT Motion-Language Dataset. Our results clearly demonstrate the effectiveness of the proposed model: We show that our model generates a wide variety of realistic motions only from descriptions thereof in form of a single sentence. Conversely, our model is also capable of generating correct and detailed natural language descriptions from human motions. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Human whole-body motion Natural language sequence-to-sequence learning Recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

MNET plus plus : Music-Driven Pluralistic Dancing Toward Multiple Dance Genre Synthesis

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第12期45卷 15036-15050页

作者： Kim, Jinwoo Kwon, Beom Kim, Jongyoo Lee, Sanghoon Yonsei Univ Dept Elect & Elect Engn Seoul 120749 South Korea Dongduk Womens Univ Div Interdisciplinary Studies Cultural Intelligen Data Sci Major Seoul 02748 South Korea Microsoft Res Asia Beijing 100080 Peoples R China

Numerous task-specific variants of autoregressive networks have been developed for dance generation. Nonetheless, a severe limitation remains in that all existing algorithms can return repeated patterns for a given initial pose, which may be inferior. We examine and analyze several key challenges of previous works, and propose variations in both model architecture (namely MNET++) and training methods to address these. In particular, we devise the beat synchronizer and dance synthesizer. First, generated dance should be locally and globally consistent with given music beats, circumvent repetitive patterns, and look realistic. To achieve this, the beat synchronizer implicitly catches the rhythm enabling it to stay in sync with the music as it dances. Then, the dance synthesizer infers the dance motions in a seamless patch-by-patch manner conditioned by music. Second, to generate diverse dance lines, adversarial learning is performed by leveraging the transformer architecture. Furthermore, MNET++ learns a dance genre-aware latent representation that is scalable for multiple domains to provide fine-grained user control according to the dance genre. Compared with the state-of-the-art methods, our method synthesizes plausible and diverse outputs according to multiple dance genres as well as generates remarkable dance sequences qualitatively and quantitatively.

关键词： Adversarial learning motion synthesis music to dance generation sequence-to-sequence learning transformer

来源：评论

学校读者我要写书评

暂无评论

Question Generation With Doubly Adversarial Nets

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2018年第11期26卷 2230-2239页

作者： Bao, Junwei Gong, Yeyun Duan, Nan Zhou, Ming Zhao, Tiejun Harbin Inst Technol Sch Comp Sci & Technol Harbin 150001 Heilongjiang Peoples R China Microsoft Res Asia Nat Language Comp Grp Beijing 100080 Peoples R China Microsoft Res Asia Beijing 100080 Peoples R China

We study the problem of question generation on a specific domain, where there are no labeled data. To address this problem, we propose a novel neural question generation approach called DoubAN, or doubly adversarial nets, which fully utilizes labeled data from other domains (source domains) and unlabeled data from the target domain. learning a DoubAN involves two adversarial procedures between a question generator and two adversaries. One adversary is a domain-classification discriminator (DC-Dis), which is designed to help the generator learn domain-general representations of the input text. The other is a questionans-wering discriminator (QA-Dis), which provides more training data with estimated reward scores for generated text-question pairs. We conduct experiments on the SQuAD dataset as target-domain unlabeled data and the NewsQA dataset as source-domain labeled data. Experiment results show that our DoubAN achieves better results than baselines. Compared to model variants, which adopt only DC-Dis or QA-Dis, we find that the DC-Dis and QA-Dis indirectly interact with each other and jointly improve the quality of generated questions on the target domain. Moreover, extensive analysis and discussion prove the reasonableness and effectiveness of our proposed approach.

关键词： Question generation doubly-adversarial net sequence-to-sequence learning neural networks natural language processing artificial intelligence

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：