咨询与建议

限定检索结果

文献类型

  • 552 篇 期刊文献
  • 336 篇 会议
  • 15 篇 学位论文
  • 1 册 图书

馆藏范围

  • 904 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 849 篇 工学
    • 571 篇 计算机科学与技术...
    • 326 篇 电气工程
    • 130 篇 软件工程
    • 89 篇 信息与通信工程
    • 77 篇 控制科学与工程
    • 58 篇 仪器科学与技术
    • 48 篇 测绘科学与技术
    • 40 篇 生物医学工程(可授...
    • 33 篇 土木工程
    • 28 篇 环境科学与工程(可...
    • 27 篇 机械工程
    • 24 篇 电子科学与技术(可...
    • 19 篇 石油与天然气工程
    • 14 篇 动力工程及工程热...
    • 11 篇 水利工程
    • 10 篇 光学工程
    • 10 篇 材料科学与工程(可...
    • 10 篇 交通运输工程
    • 9 篇 力学(可授工学、理...
    • 8 篇 建筑学
  • 189 篇 理学
    • 83 篇 物理学
    • 47 篇 地球物理学
    • 35 篇 生物学
    • 26 篇 化学
    • 13 篇 数学
  • 171 篇 医学
    • 130 篇 临床医学
    • 26 篇 基础医学(可授医学...
    • 21 篇 特种医学
  • 61 篇 管理学
    • 56 篇 管理科学与工程(可...
  • 10 篇 文学
    • 8 篇 外国语言文学
  • 7 篇 农学
  • 5 篇 艺术学
  • 2 篇 法学
  • 1 篇 经济学
  • 1 篇 教育学

主题

  • 904 篇 encoder-decoder
  • 159 篇 deep learning
  • 81 篇 attention mechan...
  • 60 篇 attention
  • 54 篇 semantic segment...
  • 48 篇 feature extracti...
  • 46 篇 lstm
  • 38 篇 transformer
  • 36 篇 decoding
  • 35 篇 convolutional ne...
  • 32 篇 cnn
  • 24 篇 semantics
  • 22 篇 image captioning
  • 22 篇 u-net
  • 22 篇 convolutional ne...
  • 21 篇 speech recogniti...
  • 20 篇 task analysis
  • 20 篇 machine learning
  • 19 篇 long short-term ...
  • 18 篇 image segmentati...

机构

  • 8 篇 univ chinese aca...
  • 8 篇 univ sci & techn...
  • 6 篇 chinese acad sci...
  • 6 篇 univ sci & techn...
  • 6 篇 univ sci & techn...
  • 5 篇 nanjing univ sci...
  • 4 篇 jiangnan univ sc...
  • 4 篇 microsoft corp r...
  • 4 篇 chongqing univ c...
  • 4 篇 wuhan univ sch r...
  • 4 篇 shenyang siasun ...
  • 4 篇 southeast univ s...
  • 4 篇 univ sci & techn...
  • 4 篇 toyota technol i...
  • 4 篇 iflytek res peop...
  • 4 篇 google inc mount...
  • 4 篇 shanghai jiao to...
  • 4 篇 northeastern uni...
  • 4 篇 tianjin univ sch...
  • 4 篇 chinese acad sci...

作者

  • 8 篇 watanabe shinji
  • 7 篇 du jun
  • 6 篇 liu yang
  • 6 篇 chen kai
  • 6 篇 zhang jianshu
  • 5 篇 ling zhen-hua
  • 5 篇 zhang limao
  • 5 篇 wang feng
  • 5 篇 wang jun
  • 4 篇 gaur yashesh
  • 4 篇 zhang chunyu
  • 4 篇 wu chengdong
  • 4 篇 wang qing
  • 4 篇 wang bing
  • 4 篇 li chen
  • 4 篇 song xiao
  • 4 篇 xu bo
  • 4 篇 xu fang
  • 4 篇 jiao licheng
  • 4 篇 toshniwal shubha...

语言

  • 838 篇 英文
  • 32 篇 其他
  • 31 篇 中文
  • 2 篇 法文
检索条件"主题词=Encoder-Decoder"
904 条 记 录,以下是891-900 订阅
MANet: A Modal Attention Network for Describing Videos  17
MANet: A Modal Attention Network for Describing Videos
收藏 引用
25th ACM International Conference on Multimedia (MM)
作者: Phan, Sang Miyao, Yusuke Satoh, Shin'ichi Natl Inst Informat Tokyo Japan
Exploiting multimodal features has become a standard approach towards many video applications, including the video captioning task. One problem with the existing work is that it models the relevance of each type of fe... 详细信息
来源: 评论
Question Answering with Character-Level LSTM encoders and Model-Based Data Augmentation
Question Answering with Character-Level LSTM Encoders and Mo...
收藏 引用
第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会
作者: Run-Ze Wang Chen-Di Zhan Zhen-Hua Ling National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of ChinaHefeiChina
This paper presents a character-level encoder-decoder mod-eling method for question answering(QA)from large-scale knowledge bases(KB).This method improves the existing approach [9] from three ***,long short-term memor... 详细信息
来源: 评论
面向事件的社交媒体文本自动摘要研究
面向事件的社交媒体文本自动摘要研究
收藏 引用
作者: 官宸宇 武汉大学
学位级别:硕士
自动文本摘要技术是自然语言处理领域重要的一个分支,初期主要广泛应用于长文本摘要任务中,例如科技论文、新闻领域等。近年来微博、Twitter等短文本形式的社交媒体快速广泛地流行起来,其方便和快捷的使用方式以及平台上的海量信息资源... 详细信息
来源: 评论
Perceptual Loss with Fully Convolutional for Image Residual Denoising
Perceptual Loss with Fully Convolutional for Image Residual ...
收藏 引用
7th Chinese Conference on Pattern Recognition (CCPR)
作者: Tao Pan Fu Zhongliang Wang Lili Zhu Kai Chinese Acad Sci Chengdu Inst Comp Applicat Chengdu 610041 Sichuan Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China
In this paper we propose a fully convolutional encoder-decoder framework for image residual transformation tasks. Instead of only using per-pixel loss function, the proposed framework learn end-to-end mapping combined... 详细信息
来源: 评论
JOINTLY LEARNING TO ALIGN AND CONVERT GRAPHEMES TO PHONEMES WITH NEURAL ATTENTION MODELS
JOINTLY LEARNING TO ALIGN AND CONVERT GRAPHEMES TO PHONEMES ...
收藏 引用
IEEE Workshop on Spoken Language Technology (SLT)
作者: Toshniwal, Shubham Livescu, Karen Toyota Technol Inst Chicago IL 60637 USA
We propose an attention-enabled encoder-decoder model for the problem of grapheme-to-phoneme conversion. Most previous work has tackled the problem via joint sequence models that require explicit alignments for traini... 详细信息
来源: 评论
ANALYSIS OF SEQUENCE TO SEQUENCE NEURAL NETWORKS ON GRAPHEME TO PHONEME CONVERSION TASK
ANALYSIS OF SEQUENCE TO SEQUENCE NEURAL NETWORKS ON GRAPHEME...
收藏 引用
International Joint Conference on Neural Networks (IJCNN)
作者: Achanta, Sivanand Pandey, Ayushi Gangashetty, Suryakanth V. IIIT Speech & Vis Lab Hyderabad Andhra Pradesh India
In this paper, we analyze the performance of various sequence to sequence neural networks on the task of grapheme to phoneme (G2P) conversion. G2P is a very important component in applications like text-to-speech, aut... 详细信息
来源: 评论
DIALOG STATE TRACKING WITH ATTENTION-BASED SEQUENCE-TO-SEQUENCE LEARNING
DIALOG STATE TRACKING WITH ATTENTION-BASED SEQUENCE-TO-SEQUE...
收藏 引用
IEEE Workshop on Spoken Language Technology (SLT)
作者: Hori, Takaaki Wang, Hai Hori, Chiori Watanabe, Shinji Harsham, Bret Le Roux, Jonathan Hershey, John R. Koji, Yusuke Jing, Yi Zhu, Zhaocheng Aikawa, Takeyuki Mitsubishi Elect Res Labs Cambridge MA 02139 USA Toyota Technol Inst Chicago IL USA Mitsubishi Electr Corp Informat Technol R&D Ctr Tokyo Tokyo Japan Peking Univ Beijing Peoples R China
We present an advanced dialog state tracking system designed for the 5th Dialog State Tracking Challenge (DSTC5). The main task of DSTC5 is to track the dialog state in a human-human dialog. For each utterance, the tr... 详细信息
来源: 评论
Topic-specific Image Caption Generation
Topic-specific Image Caption Generation
收藏 引用
第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会
作者: Chang Zhou Yuzhao Mao Xiao jie Wang School of Computer Beijing University of Posts and TelecommunicationsBeijingChina
Recently,image caption which aims to generate a textual description for an image automatically has attracted researchers from various *** performance has been achieved by applying deep neural *** of these works aim at... 详细信息
来源: 评论
A linear approach for sparse coding by a two-layer neural network
收藏 引用
NEUROCOMPUTING 2015年 第PartC期149卷 1315-1323页
作者: Montalto, Alessandro Tessitore, Giovanni Prevete, Roberto Univ Ghent Data Anal Dept Ghent Belgium Univ Naples Federico II Dept Phys Sci Naples Italy Univ Naples Federico II DIETI Naples Italy
Many approaches to transform classification problems from non-linear to linear by feature transformation have been recently presented in the literature. These notably include sparse coding methods and deep neural netw... 详细信息
来源: 评论
Design of Digital Functional Blocks using Hybrid Memristor Structures  35
Design of Digital Functional Blocks using Hybrid Memristor S...
收藏 引用
IEEE Region 10 Conference
作者: Kumar, Gaurav Datta, Kamalika Natl Inst Technol Dept Comp Sci & Engn Shillong Meghalaya India
The memristor device has emerged as the missing fourth fundamental circuit element after resistor, inductor and capacitor. Various implementations of memristors have been reported, with the one using a TiO2 layer sand... 详细信息
来源: 评论