Xinggang Wang   Associate professor

王兴刚,华中科技大学,电信息学院,华中卓越学者晨星岗副教授。主要研究方向为计算机视觉和深度学习,研究工作见:https://xinggangw.info。分别于2009年和2014年在华中科技大学获得学士和博士学位,博士期间在美国天普大学、加州大学洛杉矶分校(UCLA)访问研究。在IEEE TPAMI、CVPR、ICML等顶级期刊会议发表学术论文50余篇。谷歌学术引用次数超过7000次。担任CVPR 2022领域主席,Pattern Recognition (IF 7.196)、Image and ...Detials

Feature Context for Image Classification and Object Detection

Release time:2021-06-10  Hits:

  • Indexed by:会议论文
  • First Author:Wang,Xinggang,Wang,Xinggang
  • Correspondence Author:Wang,Xinggang
  • Co-author:Latecki,Jan,Longin,Liu,Wenyu,Bai,Xiang
  • Journal:2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • Date of Publication:2011-06-20
  • Abstract:In this paper, we presents a new method to encode the spatial information of local image features, which is a natural extension of Shape Context (SC), so we call it Feature Context (FC). Given a position in a image, SC computes histogram of other points belonging to the target binary shape based on their distances and angles to the position. The value of each histogram bin of SC is the number of the shape points in the region assigned to the bin. Thus, SC requires knowing the location of the points of the target shape. In other words, an image point can have only two labels, it belongs to the shape or not. In contrast, FC can be applied to the whole image without knowing the location of the target shape in the image. Each image point can have multiple labels depending on its local features. The value of each histogram bin of FC is a histogram of various features assigned to points in the bin region. We also introduce an efficient coding method to encode the local image features, call Radial Basis Coding (RBC). Combining RBC and FC together, and using a linear SVM classifier, our method is suitable for both image classification and object detection.