咨询与建议

限定检索结果

文献类型

  • 341 篇 会议
  • 2 篇 期刊文献

馆藏范围

  • 343 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 337 篇 工学
    • 327 篇 计算机科学与技术...
    • 262 篇 电气工程
    • 256 篇 机械工程
    • 8 篇 软件工程
    • 4 篇 电子科学与技术(可...
    • 4 篇 信息与通信工程
    • 4 篇 控制科学与工程
    • 2 篇 光学工程
    • 1 篇 仪器科学与技术
    • 1 篇 生物工程
  • 6 篇 理学
    • 3 篇 系统科学
    • 2 篇 物理学
    • 1 篇 数学
    • 1 篇 生物学
    • 1 篇 统计学(可授理学、...
  • 6 篇 医学
    • 6 篇 临床医学
    • 1 篇 基础医学(可授医学...
    • 1 篇 公共卫生与预防医...
  • 3 篇 管理学
    • 3 篇 管理科学与工程(可...
    • 1 篇 工商管理
  • 1 篇 经济学
    • 1 篇 应用经济学

主题

  • 141 篇 computer vision
  • 73 篇 images
  • 63 篇 training
  • 53 篇 estimation
  • 50 篇 visualization
  • 45 篇 modulation
  • 45 篇 filtration
  • 45 篇 field programmab...
  • 44 篇 ofdm
  • 44 篇 signal processin...
  • 44 篇 clocks
  • 36 篇 computer archite...
  • 36 篇 semantics
  • 30 篇 feature extracti...
  • 28 篇 computational mo...
  • 24 篇 neural networks
  • 23 篇 cameras
  • 21 篇 recognition (psy...
  • 21 篇 videotapes
  • 20 篇 dataset

机构

  • 12 篇 carnegie mellon ...
  • 11 篇 univ chinese aca...
  • 8 篇 stanford univ st...
  • 6 篇 australian natl ...
  • 5 篇 univ sci & techn...
  • 5 篇 mit cambridge ma...
  • 5 篇 kaust thuwal
  • 5 篇 chinese acad sci...
  • 5 篇 univ calif berke...
  • 4 篇 facebook ai res ...
  • 4 篇 boston univ bost...
  • 4 篇 univ sydney nsw
  • 4 篇 sun yat sen univ...
  • 4 篇 natl univ singap...
  • 4 篇 deepmind england
  • 4 篇 univ washington ...
  • 4 篇 microsoft res pe...
  • 4 篇 max planck inst ...
  • 3 篇 ist austria klos...
  • 3 篇 univ toronto on

作者

  • 5 篇 ghanem bernard
  • 5 篇 zafeiriou stefan...
  • 4 篇 darrell trevor
  • 4 篇 lin liang
  • 4 篇 schiele bernt
  • 4 篇 ramanan deva
  • 3 篇 swoboda paul
  • 3 篇 busch christoph
  • 3 篇 van gool luc
  • 3 篇 murino vittorio
  • 3 篇 fritz mario
  • 3 篇 feng jiashi
  • 3 篇 gupta abhinav
  • 3 篇 deng weihong
  • 3 篇 torr philip h. s...
  • 3 篇 pollefeys marc
  • 3 篇 leibe bastian
  • 3 篇 liu li
  • 3 篇 shao ling
  • 3 篇 mei tao

语言

  • 339 篇 英文
  • 2 篇 日文
  • 1 篇 其他
  • 1 篇 中文
检索条件"任意字段=30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017"
343 条 记 录,以下是51-60 订阅
Enhancing Video Summarization via vision-Language Embedding  30
Enhancing Video Summarization via Vision-Language Embedding
收藏 引用
30th ieee/CVF conference on computer vision and pattern recognition (cvpr)
作者: Plummer, Bryan A. Brown, Matthew Lazebnik, Svetlana Univ Illinois Urbana IL 61801 USA Google Res Mountain View CA USA
this paper addresses video summarization, or the problem of distilling a raw video into a shorter form while still capturing the original story. We show that visual representations supervised by freeform language make... 详细信息
来源: 评论
Temporal Attention-Gated Model for Robust Sequence Classification  30
Temporal Attention-Gated Model for Robust Sequence Classific...
收藏 引用
30th ieee/CVF conference on computer vision and pattern recognition (cvpr)
作者: Pei, Wenjie Baltrusaitis, Tadas Tax, David M. J. Morency, Louis-Philippe Delft Univ Technol Pattern Recognit Lab Delft Netherlands Carnegie Mellon Univ Language Technol Inst Pittsburgh PA 15213 USA
Typical techniques for sequence classification are designed for well-segmented sequences which have been edited to remove noisy or irrelevant parts. therefore, such methods cannot be easily applied on noisy sequences ... 详细信息
来源: 评论
A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching  30
A Study of Lagrangean Decompositions and Dual Ascent Solvers...
收藏 引用
30th ieee/CVF conference on computer vision and pattern recognition (cvpr)
作者: Swoboda, Paul Rother, Carsten Abu Alhaija, Hassan Kainmueller, Dagmar Savchynskyy, Bogdan IST Austria Klosterneuburg Austria Tech Univ Dresden Dresden Germany MPI CBG Dresden Germany
We study the quadratic assignment problem, in computer vision also known as graph matching. Two leading solvers for this problem optimize the Lagrange decomposition duals with sub-gradient and dual ascent (also known ... 详细信息
来源: 评论
Missing Modalities Imputation via Cascaded Residual Autoencoder  30
Missing Modalities Imputation via Cascaded Residual Autoenco...
收藏 引用
30th ieee/CVF conference on computer vision and pattern recognition (cvpr)
作者: Luan Tran Liu, Xiaoming Zhou, Jiayu Jin, Rong Michigan State Univ Dept Comp Sci & Engn E Lansing MI 48824 USA Alibaba Grp Holding Ltd Hangzhou Zhejiang Peoples R China
Affordable sensors lead to an increasing interest in acquiring and modeling data with multiple modalities. Learning from multiple modalities has shown to significantly improve performance in object recognition. Howeve... 详细信息
来源: 评论
A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems  30
A Dual Ascent Framework for Lagrangean Decomposition of Comb...
收藏 引用
30th ieee/CVF conference on computer vision and pattern recognition (cvpr)
作者: Swoboda, Paul Kuske, Jan Savchynskyy, Bogdan IST Austria Klosterneuburg Austria Heidelberg Univ Heidelberg Vic Australia Tech Univ Dresden Dresden Germany
We propose a general dual ascent framework for Lagrangean decomposition of combinatorial problems. Although methods of this type have shown their efficiency for a number of problems, so far there was no general algori... 详细信息
来源: 评论
Lip Reading Sentences in the Wild  30
Lip Reading Sentences in the Wild
收藏 引用
30th ieee/CVF conference on computer vision and pattern recognition (cvpr)
作者: Chung, Joon Son Senior, Andrew Vinyals, Oriol Zisserman, Andrew Univ Oxford Dept Engn Sci Oxford England DeepMind London England
the goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio. Unlike previous works that have focussed on recognising a limited number of words or phrases, we t... 详细信息
来源: 评论
Product Split Trees  30
Product Split Trees
收藏 引用
30th ieee/CVF conference on computer vision and pattern recognition (cvpr)
作者: Babenko, Artem Lempitsky, Victor Yandex Moscow Russia Natl Res Univ Higher Sch Econ Moscow Russia Skolkovo Inst Sci & Technol Skoltech Moscow Russia
In this work, we introduce a new kind of spatial partition trees for efficient nearest-neighbor search. Our approach first identifies a set of useful data splitting directions, and then learns a codebook that can be u... 详细信息
来源: 评论
the Impact of Typicality for Informative Representative Selection  30
The Impact of Typicality for Informative Representative Sele...
收藏 引用
30th ieee/CVF conference on computer vision and pattern recognition (cvpr)
作者: Bappy, Jawadul H. Paul, Sujoy Tuncel, Ertem Roy-Chowdhury, Amit K. Univ Calif Riverside Dept ECE Riverside CA 92521 USA
In computer vision, selection of the most informative samples from a huge pool of training data in order to learn a good recognition model is an active research problem. Furthermore, it is also useful to reduce the an... 详细信息
来源: 评论
Data Dropout: Optimizing Training Data for Convolutional Neural Networks  30
Data Dropout: Optimizing Training Data for Convolutional Neu...
收藏 引用
30th ieee International conference on Tools with Artificial Intelligence (ICTAI)
作者: Wang, Tianyang Huan, Jun Li, Bo Austin Peay State Univ Clarksville TN 37044 USA Baidu Res Beijing Peoples R China Univ Southern Mississippi Hattiesburg MS 39406 USA
Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters... 详细信息
来源: 评论
FASON: First and Second Order Information Fusion Network for Texture recognition  30
FASON: First and Second Order Information Fusion Network for...
收藏 引用
30th ieee/CVF conference on computer vision and pattern recognition (cvpr)
作者: Dai, Xiyang Ng, Joe Yue-Hei Davis, Larry S. Univ Maryland Inst Adv Comp Studies College Pk MD 20742 USA
Deep networks have shown impressive performance on many computer vision tasks. Recently, deep convolutional neural networks (CNNs) have been used to learn discriminative texture representations. One of the most succes... 详细信息
来源: 评论