开课单位--牛津布鲁克斯大学
1 1/1

1
Combining Appearance and Structure from Motion Features for Road Scene Understanding[结合运动特征的外观和结构来理解道路场景]
   Paul Sturgess(牛津布鲁克斯大学) Combining Appearance and Structure from Motion Features for Road Scene Understanding
热度：32

2
Improved Initialisation and Gaussian Mixture Pairwise Terms for Dense Random Fields with Mean-field Inference[具有平均场推断的密集随机场的改进初始化和高斯混合成对项]
  Vibhav Vineet(牛津布鲁克斯大学) Recently, Krahenbuhl and Koltun proposed an efficient inference method for densely connected pairwise random fields using the mean-field approximation...
热度：117

3
Learning discriminative space-time actions from weakly labelled videos[歧视性的时空行为从弱标记的视频学习]
  Michael Sapienza(牛津布鲁克斯大学) Current state-of-the-art action classification methods extract feature representations from the entire video clip in which the action unfolds, however...
热度：51

4
Filter-based Mean-Field Inference for Random Fields with Higher Order Terms and Product Label-Spaces[基于滤波器的高阶项和产品标签空间随机域均值场推断]
  Laurent Itti, Vibhav Vineet, Ramin Zabih(牛津布鲁克斯大学) Recently, a number of cross bilateral filtering methods have been proposed for solving multi-label problems in computer vision, such as stereo, optica...
热度：36
1 1/1