咨询与建议

限定检索结果

文献类型

  • 107 篇 期刊文献
  • 98 篇 会议
  • 4 册 图书

馆藏范围

  • 209 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 143 篇 工学
    • 108 篇 计算机科学与技术...
    • 99 篇 软件工程
    • 37 篇 信息与通信工程
    • 34 篇 光学工程
    • 27 篇 生物工程
    • 19 篇 机械工程
    • 16 篇 控制科学与工程
    • 15 篇 生物医学工程(可授...
    • 8 篇 化学工程与技术
    • 7 篇 电气工程
    • 6 篇 仪器科学与技术
    • 6 篇 建筑学
    • 5 篇 土木工程
    • 4 篇 电子科学与技术(可...
    • 3 篇 测绘科学与技术
    • 3 篇 环境科学与工程(可...
  • 92 篇 理学
    • 42 篇 物理学
    • 34 篇 生物学
    • 25 篇 数学
    • 9 篇 统计学(可授理学、...
    • 8 篇 化学
    • 5 篇 海洋科学
    • 3 篇 系统科学
  • 39 篇 管理学
    • 24 篇 图书情报与档案管...
    • 19 篇 管理科学与工程(可...
    • 4 篇 工商管理
  • 7 篇 医学
    • 7 篇 临床医学
    • 6 篇 基础医学(可授医学...
    • 5 篇 药学(可授医学、理...
  • 5 篇 法学
    • 5 篇 社会学
  • 2 篇 经济学
  • 1 篇 农学
  • 1 篇 艺术学

主题

  • 14 篇 computer vision
  • 12 篇 pattern recognit...
  • 11 篇 convolution
  • 8 篇 face recognition
  • 8 篇 feature extracti...
  • 8 篇 training
  • 7 篇 image segmentati...
  • 7 篇 databases
  • 7 篇 semantics
  • 6 篇 machine vision
  • 5 篇 distillation
  • 5 篇 hidden markov mo...
  • 5 篇 laboratories
  • 5 篇 visualization
  • 5 篇 clustering algor...
  • 4 篇 computer science
  • 4 篇 object detection
  • 4 篇 pattern matching
  • 4 篇 large dataset
  • 4 篇 neural networks

机构

  • 19 篇 shanghai ai labo...
  • 17 篇 shenzhen key lab...
  • 15 篇 university of ch...
  • 14 篇 xiamen key labor...
  • 11 篇 sensetime resear...
  • 11 篇 shanghai artific...
  • 10 篇 department of co...
  • 9 篇 shenzhen key lab...
  • 8 篇 national laborat...
  • 7 篇 department of in...
  • 6 篇 shenzhen key lab...
  • 6 篇 the university o...
  • 6 篇 fujian key labor...
  • 6 篇 shenzhen key lab...
  • 6 篇 university of ma...
  • 6 篇 school of electr...
  • 5 篇 school of artifi...
  • 5 篇 shenzhen key lab...
  • 5 篇 school of artifi...
  • 5 篇 college of compu...

作者

  • 22 篇 qiao yu
  • 19 篇 liu xin
  • 13 篇 wang yali
  • 13 篇 kälviäinen heikk...
  • 12 篇 eerola tuomas
  • 10 篇 dong chao
  • 9 篇 chen xiangyu
  • 8 篇 lensu lasse
  • 8 篇 yu qiao
  • 8 篇 wu xiao-jun
  • 8 篇 kittler josef
  • 7 篇 ming dong
  • 7 篇 yu zitong
  • 7 篇 yue huanjing
  • 7 篇 yang jingyu
  • 6 篇 umapada pal
  • 6 篇 he junjun
  • 6 篇 li hongsheng
  • 6 篇 chao dong
  • 5 篇 kraft kaisa

语言

  • 197 篇 英文
  • 10 篇 其他
  • 2 篇 中文
检索条件"机构=Computer Vision and Pattern Recognition Laboratory"
209 条 记 录,以下是101-110 订阅
Zero-Shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model
arXiv
收藏 引用
arXiv 2024年
作者: Cao, Cong Yue, Huanjing Liu, Xin Yang, Jingyu School of Electrical and Information Engineering Tianjin University Tianjin China Computer Vision and Pattern Recognition Laboratory School of Engineering Science Lappeenranta-Lahti University of Technology LUT Lappeenranta Finland
Diffusion-based zero-shot image restoration and enhancement models have achieved great success in various tasks of image restoration and enhancement. However, directly applying them to video restoration and enhancemen... 详细信息
来源: 评论
Learning to avoid poor images: Towards task-aware C-arm cone-beam CT trajectories
arXiv
收藏 引用
arXiv 2019年
作者: Zaech, Jan-Nico Gao, Cong Bier, Bastian Taylor, Russell Maier, Andreas Navab, Nassir Unberath, Mathias Laboratory for Computational Sensing and Robotics Johns Hopkins University Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Computer Vision Laboratory Eidgenössische Technische Hochschule Zürich
Metal artifacts in computed tomography (CT) arise from a mismatch between physics of image formation and idealized assumptions during tomographic reconstruction. These artifacts are particularly strong around metal im... 详细信息
来源: 评论
Motion constraint patterns
Motion constraint patterns
收藏 引用
IEEE Workshop on Qualitative vision
作者: C. Fermuller Department for Pattern Recognition and Image Processing Institute for Automation Technical University of of Vienna Vienna Austria Computer Vision Laboratory Center for Automation Research University of Maryland College Park MD USA
The problem of egomotion recovery has been treated by using as input local image motion, with the published algorithms utilizing the geometric constraint relating 2-D local image motion (optical flow, correspondence, ... 详细信息
来源: 评论
Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation
Box-driven Class-wise Region Masking and Filling Rate Guided...
收藏 引用
IEEE/CVF Conference on computer vision and pattern recognition
作者: Chunfeng Song Yan Huang Wanli Ouyang Liang Wang Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR) Institute of Automation Chinese Academy of Sciences (CASIA) The University of Sydney SenseTime Computer Vision Research Group
Semantic segmentation has achieved huge progress via adopting deep Fully Convolutional Networks (FCN). However, the performance of FCN based models severely rely on the amounts of pixel-level annotations which are exp... 详细信息
来源: 评论
Towards Accurate Scene Text recognition With Semantic Reasoning Networks
Towards Accurate Scene Text Recognition With Semantic Reason...
收藏 引用
Conference on computer vision and pattern recognition (CVPR)
作者: Deli Yu Xuan Li Chengquan Zhang Tao Liu Junyu Han Jingtuo Liu Errui Ding School of Artificial Intelligence University of Chinese Academy of Sciences National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Department of Computer Vision Technology(VIS) Baidu Inc.
Scene text image contains two levels of contents: visual texture and semantic information. Although the previous scene text recognition methods have made great progress over the past few years, the research on mining ... 详细信息
来源: 评论
Learning to predict context-adaptive convolution for semantic segmentation
arXiv
收藏 引用
arXiv 2020年
作者: Liu, Jianbo He, Junjun Ren, Jimmy S. Qiao, Yu Li, Hongsheng CUHK-SenseTime Joint Laboratory Chinese University of Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SenseTime Research
Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods [34] demonstrate that using global context for re-weighting feature channels c... 详细信息
来源: 评论
Finding a Semantic Structure Interactively in Image Databases
Finding a Semantic Structure Interactively in Image Database...
收藏 引用
IEEE International Conference on Multimedia and Expo (ICME)
作者: Manjeet Rege Ming Dong Farshad Fotouhi Machine Vision & Pattern Recognition Laboratory Department of Computer Science Wayne State University Detroit MI USA Database & Multimedia Systems Group Department of Computer Science Wayne State University Detroit MI USA
We present a new approach to organize an image database by finding a semantic structure interactively based on multi-user relevance feedback. By treating user relevance feedbacks as weak classifiers and combining them... 详细信息
来源: 评论
Co-Clustering Image Features and Semantic Concepts
Co-Clustering Image Features and Semantic Concepts
收藏 引用
IEEE International Conference on Image Processing
作者: Manjeet Rege Ming Dong Farshad Fotouhi Department of Computer Science Machine Vision & Pattern Recognition Laboratory Wayne State University Detroit MI USA Database & Multimedia Systems Group Wayne State University Detroit MI USA
In this paper, we present a novel idea of co-clustering image features and semantic concepts. We accomplish this by modelling user feedback logs and low-level features using a bipartite graph. Our experiments demonstr... 详细信息
来源: 评论
Learning dynamical human-joint affinity for 3D pose estimation in videos
arXiv
收藏 引用
arXiv 2021年
作者: Zhang, Junhao Wang, Yali Zhou, Zhipeng Luan, Tianyu Wang, Zhe Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of California Irvine United States Shanghai AI Laboratory Shanghai China
Graph Convolution Network (GCN) has been successfully used for 3D human pose estimation in videos. However, it is often built on the fixed human-joint affinity, according to human skeleton. This may reduce adaptation ... 详细信息
来源: 评论
DegAE: A New Pretraining Paradigm for Low-Level vision
DegAE: A New Pretraining Paradigm for Low-Level Vision
收藏 引用
Conference on computer vision and pattern recognition (CVPR)
作者: Yihao Liu Jingwen He Jinjin Gu Xiangtao Kong Yu Qiao Chao Dong Shanghai Artificial Intelligence Laboratory ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences The University of Sydney
Self-supervised pretraining has achieved remarkable success in high-level vision, but its application in low-level vision remains ambiguous and not well-established. What is the primitive intention of pretraining? Wha...
来源: 评论