咨询与建议

限定检索结果

文献类型

  • 6,639 篇 会议
  • 34 篇 期刊文献
  • 5 册 图书

馆藏范围

  • 6,677 篇 电子文献
  • 1 种 纸本馆藏

日期分布

学科分类号

  • 3,950 篇 工学
    • 3,725 篇 计算机科学与技术...
    • 1,476 篇 软件工程
    • 807 篇 光学工程
    • 323 篇 信息与通信工程
    • 240 篇 控制科学与工程
    • 206 篇 机械工程
    • 169 篇 电气工程
    • 85 篇 生物医学工程(可授...
    • 73 篇 电子科学与技术(可...
    • 70 篇 生物工程
    • 65 篇 仪器科学与技术
    • 38 篇 建筑学
    • 36 篇 土木工程
    • 34 篇 力学(可授工学、理...
    • 32 篇 航空宇航科学与技...
    • 29 篇 安全科学与工程
    • 23 篇 化学工程与技术
    • 21 篇 材料科学与工程(可...
  • 1,498 篇 理学
    • 969 篇 物理学
    • 929 篇 数学
    • 369 篇 统计学(可授理学、...
    • 136 篇 生物学
    • 40 篇 系统科学
    • 26 篇 化学
  • 210 篇 医学
    • 210 篇 临床医学
    • 23 篇 基础医学(可授医学...
  • 165 篇 管理学
    • 123 篇 图书情报与档案管...
    • 44 篇 管理科学与工程(可...
    • 29 篇 工商管理
  • 21 篇 法学
    • 21 篇 社会学
  • 10 篇 农学
  • 9 篇 教育学
  • 6 篇 经济学
  • 2 篇 军事学
  • 1 篇 艺术学

主题

  • 2,364 篇 computer vision
  • 848 篇 pattern recognit...
  • 663 篇 cameras
  • 634 篇 computer science
  • 592 篇 face recognition
  • 558 篇 layout
  • 541 篇 conferences
  • 527 篇 image segmentati...
  • 514 篇 shape
  • 454 篇 object recogniti...
  • 453 篇 robustness
  • 394 篇 humans
  • 339 篇 feature extracti...
  • 324 篇 training
  • 305 篇 object detection
  • 263 篇 image recognitio...
  • 260 篇 application soft...
  • 249 篇 lighting
  • 248 篇 computational mo...
  • 238 篇 image reconstruc...

机构

  • 44 篇 microsoft resear...
  • 27 篇 department of co...
  • 21 篇 swiss fed inst t...
  • 21 篇 school of comput...
  • 21 篇 carnegie mellon ...
  • 20 篇 department of co...
  • 19 篇 swiss fed inst t...
  • 18 篇 department of co...
  • 17 篇 department of in...
  • 17 篇 the robotics ins...
  • 17 篇 institute of com...
  • 16 篇 univ sci & techn...
  • 16 篇 robotics institu...
  • 15 篇 tsinghua univ pe...
  • 14 篇 department of el...
  • 14 篇 center for autom...
  • 14 篇 school of comput...
  • 14 篇 school of comput...
  • 13 篇 univ maryland co...
  • 13 篇 microsoft resear...

作者

  • 39 篇 timofte radu
  • 28 篇 s.k. nayar
  • 25 篇 huang thomas s.
  • 24 篇 xiaoou tang
  • 22 篇 t. kanade
  • 20 篇 chellappa rama
  • 20 篇 t.s. huang
  • 19 篇 van gool luc
  • 19 篇 nayar shree k.
  • 19 篇 t. darrell
  • 17 篇 a.k. jain
  • 17 篇 a. zisserman
  • 17 篇 heung-yeung shum
  • 17 篇 jain anil k.
  • 17 篇 zisserman andrew
  • 16 篇 g. healey
  • 16 篇 torralba antonio
  • 16 篇 l. van gool
  • 15 篇 ying wu
  • 15 篇 m. shah

语言

  • 6,659 篇 英文
  • 11 篇 其他
  • 8 篇 中文
检索条件"任意字段=2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2003"
6678 条 记 录,以下是1431-1440 订阅
排序:
Bilateral space video segmentation
Bilateral space video segmentation
收藏 引用
2016 ieee conference on computer vision and pattern recognition, cvpr 2016
作者: Märki, Nicolas Perazzi, Federico Wang, Oliver Sorkine-Hornung, Alexander ETH Zurich Switzerland Disney Research United States Adobe Systems Inc. United States
In this work, we propose a novel approach to video segmentation that operates in bilateral space. We design a new energy on the vertices of a regularly sampled spatiotemporal bilateral grid, which can be solved effici... 详细信息
来源: 评论
Solving temporal puzzles
Solving temporal puzzles
收藏 引用
2016 ieee conference on computer vision and pattern recognition, cvpr 2016
作者: Dicle, Caglayan Yilmaz, Burak Camps, Octavia Sznaier, Mario Dept. of Electrical and Computer Engineering Northeastern University United States
Many physical phenomena, within short time windows, can be explained by low order differential relations. In a discrete world, these relations can be described using low order difference equations or equivalently low ... 详细信息
来源: 评论
Progressive prioritized multi-view stereo
Progressive prioritized multi-view stereo
收藏 引用
2016 ieee conference on computer vision and pattern recognition, cvpr 2016
作者: Locher, Alex Perdoch, Michal Van Gool, Luc Computer Vision Laboratory ETH Zurich Switzerland VISICS KU Leuven Belgium
This work proposes a progressive patch based multiview stereo algorithm able to deliver a dense point cloud at any time. This enables an immediate feedback on the reconstruction process in a user centric scenario. Wit... 详细信息
来源: 评论
Automated 3D face reconstruction from multiple images using quality measures
Automated 3D face reconstruction from multiple images using ...
收藏 引用
2016 ieee conference on computer vision and pattern recognition, cvpr 2016
作者: Piotraschke, Marcel Blanz, Volker Institute for Vision and Graphics University of Siegen Germany
Automated 3D reconstruction of faces from images is challenging if the image material is difficult in terms of pose, lighting, occlusions and facial expressions, and if the initial 2D feature positions are inaccurate ... 详细信息
来源: 评论
Simultaneous clustering and model selection for tensor affinities
Simultaneous clustering and model selection for tensor affin...
收藏 引用
2016 ieee conference on computer vision and pattern recognition, cvpr 2016
作者: Li, Zhuwen Yang, Shuoguang Cheong, Loong-Fah Toh, Kim-Chuan National University of Singapore Singapore Columbia University United States
Estimating the number of clusters remains a difficult model selection problem. We consider this problem in the domain where the affinity relations involve groups of more than two nodes. Building on the previous formul... 详细信息
来源: 评论
Unsupervised cross-dataset transfer learning for person re-identification
Unsupervised cross-dataset transfer learning for person re-i...
收藏 引用
2016 ieee conference on computer vision and pattern recognition, cvpr 2016
作者: Peng, Peixi Xiang, Tao Wang, Yaowei Pontil, Massimiliano Gong, Shaogang Huang, Tiejun Tian, Yonghong National Engineering Laboratory for Video Technology Peking University Beijing China School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Department of Electronic Engineering Beijing Institute of Technology China Italian Institute of Technology Italy Cooperative Medianet Innovation Center China
Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training. This severely limits their scalability in... 详细信息
来源: 评论
Fast temporal activity proposals for efficient detection of human actions in untrimmed videos
Fast temporal activity proposals for efficient detection of ...
收藏 引用
2016 ieee conference on computer vision and pattern recognition, cvpr 2016
作者: Heilbron, Fabian Caba Niebles, Juan Carlos Ghanem, Bernard Saudi Arabia Department of Computer Science Stanford University United States Universidad del Norte Colombia
In many large-scale video analysis scenarios, one is interested in localizing and recognizing human activities that occur in short temporal intervals within long untrimmed videos. Current approaches for activity detec... 详细信息
来源: 评论
Bottom-up and top-down reasoning with hierarchical rectified gaussians
Bottom-up and top-down reasoning with hierarchical rectified...
收藏 引用
2016 ieee conference on computer vision and pattern recognition, cvpr 2016
作者: Hu, Peiyun Ramanan, Deva UC Irvine United States Carnegie Mellon University United States
Convolutio remarkable pe tend to work i fashion. How idence tells u larly for deta explores "bidi top-down fee lower and hig We do so in a quadratic erarchical Re that RGs can that can in tu work (with rectified ... 详细信息
来源: 评论
Multi-scale patch aggregation (MPA) for simultaneous detection and segmentation
Multi-scale patch aggregation (MPA) for simultaneous detecti...
收藏 引用
2016 ieee conference on computer vision and pattern recognition, cvpr 2016
作者: Liu, Shu Qi, Xiaojuan Shi, Jianping Zhang, Hong Jia, Jiaya Chinese University of Hong Kong Hong Kong SenseTime Group Limited China
Aiming at simultaneous detection and segmentation (SD-S), we propose a proposal-free framework, which detect and segment object instances via mid-level patches. We design a unified trainable network on patches, which ... 详细信息
来源: 评论
Dense monocular depth estimation in complex dynamic scenes
Dense monocular depth estimation in complex dynamic scenes
收藏 引用
2016 ieee conference on computer vision and pattern recognition, cvpr 2016
作者: Ranftl, René Vineet, Vibhav Chen, Qifeng Koltun, Vladlen Intel Labs United States Stanford University United States
We present an approach to dense depth estimation from a single monocular camera that is moving through a dynamic scene. The approach produces a dense depth map from two consecutive frames. Moving objects are reconstru... 详细信息
来源: 评论