咨询与建议

限定检索结果

文献类型

  • 217 篇 期刊文献
  • 119 篇 会议
  • 1 册 图书

馆藏范围

  • 337 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 209 篇 工学
    • 126 篇 计算机科学与技术...
    • 87 篇 软件工程
    • 61 篇 信息与通信工程
    • 40 篇 电子科学与技术(可...
    • 35 篇 光学工程
    • 28 篇 电气工程
    • 18 篇 控制科学与工程
    • 17 篇 生物工程
    • 11 篇 仪器科学与技术
    • 11 篇 材料科学与工程(可...
    • 10 篇 动力工程及工程热...
    • 9 篇 生物医学工程(可授...
    • 8 篇 机械工程
    • 8 篇 化学工程与技术
    • 6 篇 土木工程
    • 5 篇 力学(可授工学、理...
  • 170 篇 理学
    • 87 篇 物理学
    • 67 篇 数学
    • 28 篇 统计学(可授理学、...
    • 23 篇 生物学
    • 11 篇 化学
    • 9 篇 系统科学
    • 8 篇 天文学
  • 35 篇 管理学
    • 20 篇 管理科学与工程(可...
    • 16 篇 图书情报与档案管...
    • 10 篇 工商管理
  • 11 篇 医学
    • 10 篇 临床医学
    • 9 篇 基础医学(可授医学...
    • 5 篇 公共卫生与预防医...
  • 6 篇 农学
  • 4 篇 法学
  • 3 篇 教育学
  • 2 篇 经济学
  • 2 篇 文学
  • 1 篇 艺术学

主题

  • 12 篇 qubits
  • 12 篇 quantum algorith...
  • 8 篇 machine learning
  • 7 篇 quantum computat...
  • 6 篇 computer science
  • 6 篇 conferences
  • 5 篇 quantum simulati...
  • 5 篇 deep neural netw...
  • 5 篇 signal processin...
  • 5 篇 quantum error co...
  • 5 篇 quantum computer...
  • 5 篇 quantum gates
  • 4 篇 data mining
  • 4 篇 switches
  • 4 篇 atoms
  • 4 篇 stochastic syste...
  • 4 篇 complexity theor...
  • 4 篇 hardware
  • 4 篇 data structures
  • 4 篇 synchronization

机构

  • 37 篇 ntt computer and...
  • 32 篇 ntt computer and...
  • 17 篇 ntt computer and...
  • 16 篇 jst presto 4-1-8...
  • 16 篇 purple mountain ...
  • 13 篇 jst presto 4-1-8...
  • 12 篇 ntt communicatio...
  • 11 篇 the purple mount...
  • 11 篇 the department o...
  • 9 篇 school of scienc...
  • 8 篇 graduate school ...
  • 7 篇 sony computer sc...
  • 7 篇 department of ap...
  • 7 篇 computer and dat...
  • 6 篇 royal stoke univ...
  • 6 篇 cambridge univer...
  • 6 篇 graduate school ...
  • 6 篇 the national mob...
  • 5 篇 leeds institute ...
  • 5 篇 center for psych...

作者

  • 26 篇 suzuki yasunari
  • 20 篇 tokunaga yuuki
  • 20 篇 endo suguru
  • 17 篇 zhang rui
  • 16 篇 zeng yong
  • 14 篇 yuuki tokunaga
  • 14 篇 kumagai atsutosh...
  • 13 篇 jin shi
  • 12 篇 nielsen frank
  • 12 篇 yasunari suzuki
  • 11 篇 matsuzaki yuichi...
  • 11 篇 suguru endo
  • 8 篇 fujiwara yasuhir...
  • 8 篇 ryo masumura
  • 8 篇 shinobu saito
  • 7 篇 hakoshima hideak...
  • 7 篇 chijiwa daiki
  • 7 篇 yoshioka nobuyuk...
  • 7 篇 masumura ryo
  • 7 篇 asaoka rui

语言

  • 312 篇 英文
  • 25 篇 其他
  • 1 篇 日文
检索条件"机构=Computer And Data Science Laboratories"
337 条 记 录,以下是41-50 订阅
排序:
Text-to-Text Pre-Training with Paraphrasing for Improving Transformer-Based Image Captioning
Text-to-Text Pre-Training with Paraphrasing for Improving Tr...
收藏 引用
European Signal Processing Conference (EUSIPCO)
作者: Ryo Masumura Naoki Makishima Mana Ihori Akihiko Takashima Tomohiro Tanaka Shota Orihashi NTT Computer & Data Science Laboratories NTT Corporation
In this paper, we propose a novel training method for the transformer encoder-decoder based image captioning, which directly generates a captioning text from an input image. In general, many image- to- text paired dat...
来源: 评论
Covariance-Aware Feature Alignment with Pre-Computed Source Statistics for Test-Time Adaptation to Multiple Image Corruptions
Covariance-Aware Feature Alignment with Pre-Computed Source ...
收藏 引用
IEEE International Conference on Image Processing
作者: Kazuki Adachi Shin’Ya Yamaguchi Atsutoshi Kumagai NTT Computer and Data Science Laboratories Kyoto University
Real-world image recognition systems often face corrupted input images, which cause distribution shifts and degrade the performance of models. These systems often use a single prediction model in a central server and ...
来源: 评论
Recurrent Neural Networks for Learning Long-term Temporal Dependencies with Reanalysis of Time Scale Representation  12
Recurrent Neural Networks for Learning Long-term Temporal De...
收藏 引用
12th IEEE International Conference on Big Knowledge, ICBK 2021
作者: Ohno, Kentaro Kumagai, Atsutoshi NTT Computer Data Science Laboratories Japan
Recurrent neural networks with a gating mechanism such as an LSTM or GRU are powerful tools to model sequential data. In the mechanism, a forget gate, which was introduced to control information flow in a hidden state... 详细信息
来源: 评论
Receding-Horizon Trajectory Planning for Under-Actuated Autonomous Vehicles Based on Collaborative Neurodynamic Optimization
收藏 引用
IEEE/CAA Journal of Automatica Sinica 2022年 第11期9卷 1909-1923页
作者: Jiasen Wang Jun Wang Qing-Long Han IEEE the Future Network Research Center Purple Mountain LaboratoriesNanjing 211111China the Department of Computer Science the School of Data ScienceCity University of Hong KongHong KongChina the School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia
This paper addresses a major issue in planning the trajectories of under-actuated autonomous vehicles based on neurodynamic optimization.A receding-horizon vehicle trajectory planning task is formulated as a sequentia... 详细信息
来源: 评论
Complexity Reduction of Graph Signal Denoising Based on Fast Graph Fourier Transform
Complexity Reduction of Graph Signal Denoising Based on Fast...
收藏 引用
IEEE International Conference on Image Processing
作者: Takayuki Sasaki Yukihiro Bandoh Masaki Kitahara NTT Computer and Data Science Laboratories NTT Corporation
Denoising is one of the most fundamental and important problems in signal processing, and graph signal denoising methods have been actively studied. Several graph signal denoising methods based on mathematical program...
来源: 评论
Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models
arXiv
收藏 引用
arXiv 2025年
作者: Chijiwa, Daiki Hasegawa, Taku Nishida, Kyosuke Saito, Kuniko Takeuchi, Susumu NTT Computer and Data Science Laboratories NTT Corporation Japan NTT Human Informatics Laboratories NTT Corporation Japan
While foundation models have been exploited for various expert tasks through fine-tuning, any foundation model will become outdated due to its old knowledge or limited capability. Thus the underlying foundation model ... 详细信息
来源: 评论
End-to-End Joint Target and Non-Target Speakers ASR
arXiv
收藏 引用
arXiv 2023年
作者: Masumura, Ryo Makishima, Naoki Yamane, Taiga Yamazaki, Yoshihiko Mizuno, Saki Ihori, Mana Uchida, Mihiro Suzuki, Keita Sato, Hiroshi Tanaka, Tomohiro Takashima, Akihiko Suzuki, Satoshi Moriya, Takafumi Hojo, Nobukatsu Ando, Atsushi NTT Computer and Data Science Laboratories NTT Corporation Japan
This paper proposes a novel automatic speech recognition (ASR) system that can transcribe individual speaker’s speech while identifying whether they are target or non-target speakers from multi-talker overlapped spee... 详细信息
来源: 评论
Distilling Knowledge of Bidirectional Language Model for Scene Text Recognition
Distilling Knowledge of Bidirectional Language Model for Sce...
收藏 引用
IEEE International Conference on Image Processing
作者: Shota Orihashi Yoshihiro Yamazaki Mihiro Uchida Akihiko Takashima Ryo Masumura NTT Computer and Data Science Laboratories NTT Corporation Japan
This paper proposes a knowledge distillation method for an external bidirectional language model trained by masked language modeling to achieve high accuracy in scene text recognition. In Asian languages such as Japan...
来源: 评论
TRANSFERRING LEARNING TRAJECTORIES OF NEURAL NETWORKS
arXiv
收藏 引用
arXiv 2023年
作者: Chijiwa, Daiki NTT Computer and Data Science Laboratories NTT Corporation Japan
Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated or similar training runs in model ensemble or fine-tuning pre-trained models, for example. ... 详细信息
来源: 评论
OnDA-DETR: Online Domain Adaptation for Detection Transformers with Self-Training Framework
OnDA-DETR: Online Domain Adaptation for Detection Transforme...
收藏 引用
IEEE International Conference on Image Processing
作者: Satoshi Suzuki Taiga Yamane Naoki Makishima Keita Suzuki Atsushi Ando Ryo Masumura NTT Computer and Data Science Laboratories NTT Corporation Japan
This paper presents a novel method for online domain adaptation (OnDA) for DEtection TRansformer (DETR)-based object detection models called OnDA-DETR. OnDA is a domain adaptation paradigm that adapts a model trained ...
来源: 评论