Learn More
Graph matching is a powerful tool for computer vision and machine learning. In this paper, a novel approach to graph matching is developed based on the sequential Monte Carlo framework. By constructing a sequence of intermediate target distributions, the proposed algorithm sequentially performs a sampling and importance resampling to maximize the graph(More)
Graph matching is a fundamental problem in computer vision. In this paper, we propose a novel graph matching algorithm based on tabu search [13]. The proposed method solves graph matching problem by casting it into an equivalent weighted maximum clique problem of the corresponding association graph, which we further penalize through introducing negative(More)
Feature correspondence plays a central role in various computer vision applications. It is widely formulated as a graph matching problem due to its robust performance under challenging conditions, such as background clutter, object deformation and repetitive patterns. A variety of fast and accurate algorithms have been proposed for graph matching. However,(More)
Regression tree used Single regression tree is trained to output the offset to the nearest joint position. How to inference? All joint positions (without labels) estimated using simple K-means clustering. Localization problem: The 15 3D position of each joint must be accurately estimated for human pose. Identification Problem: Joint positions must be(More)
Feature correspondence is widely formulated as a graph matching problem due to its robust performance under challenging conditions. A variety of fast and accurate algorithms have been proposed for graph matching. However, most of them focus on improving the recall of the solution while rarely considering its precision, thus inducing a solution with numerous(More)
1. Additional Experimental Results In this section, we provide more comparative experimental results.In Section 1.1, the experimental results on the whole object classes in the Willow dataset are given. Some qualitative matching results of the Willow dataset are shown in Section 1.2. 1.1. Willow Object Dataset Under the same experimental settings explained(More)
We propose a new method for human pose estimation from a single image. Since both appearance and locations of different body parts strongly depends on each other in an image, considering their relationship helps identifying the underlying poses. However, most of the existing methods cannot fully utilize this contextual information by using simplified model(More)
We propose a novel approach to 3D human pose estimation from a single depth map. Recently, convolutional neural network (CNN) has become a powerful paradigm in computer vision. Many of computer vision tasks have benefited from CNNs, however, the conventional approach to directly regress 3D body joint locations from an image does not yield a noticeably(More)
  • 1