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:。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

Fu Q#, Hu Y, Wang Q, Liu Y, Li N, Xu B, Kim S, Chiamvimonvat N, Xiang YK#. High-fat diet induces protein kinase A and G-protein receptor kinase phosphorylation of β(2) -adrenergic receptor and impairs cardiac adrenergic reserve in animal hearts. J Physiol. 2017 Mar 15;595(6):1973-1986. (*co-corresponding author)

Release time:2021-06-10  Hits:

  • Indexed by:会议论文
  • First Author:Wang,Xinggang,Wang,Xinggang
  • Correspondence Author:Wang,Xinggang
  • Co-author:Wang,Tu,Zhuowen,Liu,Wenyu,Bai,Xiang,Wang,Baoyuan
  • Journal:International Conference on Machine Learning (ICML), Atlanta, June, 2013
  • Date of Publication:2013-06-17
  • Abstract:Dictionary learning has became an increasingly important task in machine learning, as it is fundamental to the representation problem. A number of emerging techniques specifically include a codebook learning step, in which a critical knowledge abstraction process is carried out. Existing approaches in dictionary (codebook) learning are either generative (unsupervised e.g. k-means) or discriminative (supervised e.g. extremely randomized forests). In this paper, we propose a multiple instance learning (MIL) strategy (along the line of weakly supervised learning) for dictionary learning. Each code is represented by a classifier, such as a linear SVM, which naturally performs metric fusion for multi-channel features. We design a formulation to simultaneously learn mixtures of codes by maximizing classification margins in MIL. State-of-the-art results are observed in image classification benchmarks based on the learned codebooks, which observe both compactness and effectiveness.