咨询与建议

限定检索结果

文献类型

  • 11,416 篇 会议
  • 9 篇 期刊文献

馆藏范围

  • 11,425 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 7,983 篇 工学
    • 7,536 篇 计算机科学与技术...
    • 805 篇 机械工程
    • 401 篇 电气工程
    • 393 篇 软件工程
    • 233 篇 控制科学与工程
    • 59 篇 光学工程
    • 42 篇 生物工程
    • 37 篇 信息与通信工程
    • 19 篇 生物医学工程(可授...
    • 14 篇 电子科学与技术(可...
    • 13 篇 化学工程与技术
    • 9 篇 安全科学与工程
    • 8 篇 交通运输工程
    • 6 篇 仪器科学与技术
    • 5 篇 土木工程
    • 3 篇 建筑学
  • 3,139 篇 医学
    • 3,139 篇 临床医学
    • 8 篇 基础医学(可授医学...
    • 5 篇 药学(可授医学、理...
    • 4 篇 公共卫生与预防医...
  • 310 篇 理学
    • 200 篇 系统科学
    • 66 篇 物理学
    • 43 篇 生物学
    • 32 篇 数学
    • 16 篇 化学
    • 15 篇 统计学(可授理学、...
  • 29 篇 管理学
    • 17 篇 图书情报与档案管...
    • 13 篇 管理科学与工程(可...
    • 5 篇 工商管理
  • 3 篇 法学
    • 3 篇 社会学
  • 2 篇 教育学
  • 2 篇 农学
  • 1 篇 经济学
  • 1 篇 艺术学

主题

  • 5,612 篇 computer vision
  • 2,584 篇 training
  • 2,092 篇 pattern recognit...
  • 1,682 篇 computational mo...
  • 1,496 篇 visualization
  • 1,343 篇 three-dimensiona...
  • 1,098 篇 semantics
  • 1,007 篇 benchmark testin...
  • 1,005 篇 codes
  • 927 篇 computer archite...
  • 898 篇 deep learning
  • 790 篇 task analysis
  • 708 篇 feature extracti...
  • 571 篇 conferences
  • 563 篇 face recognition
  • 520 篇 transformers
  • 517 篇 neural networks
  • 493 篇 object detection
  • 476 篇 image segmentati...
  • 452 篇 cameras

机构

  • 172 篇 univ sci & techn...
  • 150 篇 univ chinese aca...
  • 148 篇 tsinghua univ pe...
  • 145 篇 carnegie mellon ...
  • 136 篇 chinese univ hon...
  • 116 篇 peng cheng lab p...
  • 106 篇 zhejiang univ pe...
  • 97 篇 swiss fed inst t...
  • 96 篇 sensetime res pe...
  • 95 篇 tsinghua univers...
  • 91 篇 shanghai ai lab ...
  • 85 篇 shanghai jiao to...
  • 83 篇 alibaba grp peop...
  • 81 篇 peng cheng labor...
  • 80 篇 zhejiang univers...
  • 80 篇 stanford univ st...
  • 78 篇 univ hong kong p...
  • 77 篇 university of ch...
  • 75 篇 australian natl ...
  • 75 篇 tech univ munich...

作者

  • 64 篇 timofte radu
  • 60 篇 van gool luc
  • 50 篇 zhang lei
  • 44 篇 yang yi
  • 39 篇 tao dacheng
  • 35 篇 loy chen change
  • 32 篇 tian qi
  • 31 篇 zhou jie
  • 31 篇 sun jian
  • 30 篇 liu yang
  • 29 篇 vasconcelos nuno
  • 29 篇 qi tian
  • 29 篇 zha zheng-jun
  • 28 篇 chen chen
  • 27 篇 boxin shi
  • 26 篇 li xin
  • 26 篇 luc van gool
  • 26 篇 pollefeys marc
  • 25 篇 liu xiaoming
  • 25 篇 ying shan

语言

  • 11,420 篇 英文
  • 5 篇 其他
检索条件"任意字段=2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021"
11425 条 记 录,以下是241-250 订阅
排序:
Virtual Fully-Connected Layer: Training a Large-Scale Face recognition Dataset with Limited Computational Resources
Virtual Fully-Connected Layer: Training a Large-Scale Face R...
收藏 引用
ieee/cvf conference on computer vision and pattern recognition (cvpr)
作者: Li, Pengyu Wang, Biao Zhang, Lei Alibaba Grp Artificial Intelligence Ctr DAMO Acad Hangzhou Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China
Recently, deep face recognition has achieved significant progress because of Convolutional Neural Networks (CNNs) and large-scale datasets. However, training CNNs on a large-scale face recognition dataset with limited... 详细信息
来源: 评论
Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations
Continual Semantic Segmentation via Repulsion-Attraction of ...
收藏 引用
ieee/cvf conference on computer vision and pattern recognition (cvpr)
作者: Michieli, Umberto Zanuttigh, Pietro Univ Padua Dept Informat Engn Padua Italy
Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new cat... 详细信息
来源: 评论
3D Spatial recognition without Spatially Labeled 3D
3D Spatial Recognition without Spatially Labeled 3D
收藏 引用
ieee/cvf conference on computer vision and pattern recognition (cvpr)
作者: Ren, Zhongzheng Misra, Ishan Schwing, Alexander G. Girdhar, Rohit Facebook AI Res Menlo Pk CA 94025 USA Univ Illinois Urbana IL 61801 USA
We introduce WyPR, a Weakly-supervised framework for Point cloud recognition, requiring only scene-level class tags as supervision. WyPR jointly addresses three core 3D recognition tasks: point-level semantic segmenta... 详细信息
来源: 评论
DeepLM: Large-scale Nonlinear Least Squares on Deep Learning Frameworks using Stochastic Domain Decomposition
DeepLM: Large-scale Nonlinear Least Squares on Deep Learning...
收藏 引用
ieee/cvf conference on computer vision and pattern recognition (cvpr)
作者: Huang, Jingwei Huang, Shan Sun, Mingwei Huawei Technol Rieman Lab Shenzhen Guangdong Peoples R China Wuhan Univ Wuhan Hubei Peoples R China
We propose a novel approach for large-scale nonlinear least squares problems based on deep learning frameworks. Nonlinear least squares are commonly solved with the Levenberg-Marquardt (LM) algorithm for fast converge... 详细信息
来源: 评论
Wasserstein Contrastive Representation Distillation
Wasserstein Contrastive Representation Distillation
收藏 引用
ieee/cvf conference on computer vision and pattern recognition (cvpr)
作者: Chen, Liqun Wang, Dong Gan, Zhe Liu, Jingjing Henao, Ricardo Carin, Lawrence Duke Univ Durham NC 27706 USA Microsoft Corp Redmond WA 98052 USA
The primary goal of knowledge distillation (KD) is to encapsulate the information of a model learned from a teacher network into a student network, with the latter being more compact than the former. Existing work, e.... 详细信息
来源: 评论
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers
Deep Occlusion-Aware Instance Segmentation with Overlapping ...
收藏 引用
ieee/cvf conference on computer vision and pattern recognition (cvpr)
作者: Ke, Lei Tai, Yu-Wing Tang, Chi-Keung Hong Kong Univ Sci & Technol Hong Kong Peoples R China Kuaishou Technol Beijing Peoples R China
Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries. Unlike previous two-stage instance segmentation methods, we model i... 详细信息
来源: 评论
Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation
Building Reliable Explanations of Unreliable Neural Networks...
收藏 引用
ieee/cvf conference on computer vision and pattern recognition (cvpr)
作者: Lim, Dohun Lee, Hyeonseok Kim, Sungchan Jeonbuk Natl Univ Div Comp Sci & Engn Jeonju South Korea
We present a novel method for reliably explaining the predictions of neural networks. We consider an explanation reliable if it identifies input features relevant to the model output by considering the input and the n... 详细信息
来源: 评论
Cloud2Curve: Generation and Vectorization of Parametric Sketches
Cloud2Curve: Generation and Vectorization of Parametric Sket...
收藏 引用
ieee/cvf conference on computer vision and pattern recognition (cvpr)
作者: Das, Ayan Yang, Yongxin Hospedales, Timothy Xiang, Tao Song, Yi-Zhe Univ Surrey CVSSP SketchX Guildford Surrey England iFlyTek Surrey Joint Res Ctr Artificial Intellige Guildford Surrey England Univ Edinburgh Edinburgh Midlothian Scotland
Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations. We further aim to model sketches as a sequence of low-dimensional pa... 详细信息
来源: 评论
Towards Real-World Blind Face Restoration with Generative Facial Prior
Towards Real-World Blind Face Restoration with Generative Fa...
收藏 引用
ieee/cvf conference on computer vision and pattern recognition (cvpr)
作者: Wang, Xintao Li, Yu Zhang, Honglun Shan, Ying Tencent PCG Appl Res Ctr ARC Shenzhen Peoples R China
Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric pri... 详细信息
来源: 评论
Delta Sampling R-BERT for limited data and low-light action recognition
Delta Sampling R-BERT for limited data and low-light action ...
收藏 引用
ieee/cvf conference on computer vision and pattern recognition (cvpr)
作者: Hira, Sanchit Das, Ritwik Modi, Abhinav Pakhomov, Daniil Johns Hopkins Univ Baltimore MD 21218 USA
We present an approach to perform supervised action recognition in the dark. In this work, we present our results on the ARID dataset[60]. Most previous works only evaluate performance on large, well illuminated datas... 详细信息
来源: 评论