From Dictionary of Visual Words to Subspaces: Locality-constrained Affine Subspace Coding

被引:0
|
作者
Li, Peihua [1 ]
Lu, Xiaoxiao [1 ]
Wang, Qilong [1 ]
机构
[1] Dalian Univ Technol, Sch Informat & Commun Engn, Dalian Shi, Liaoning Sheng, Peoples R China
关键词
REDUCTION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The locality-constrained linear coding (LLC) is a very successful feature coding method in image classification. It makes known the importance of locality constraint which brings high efficiency and local smoothness of the codes. However, in the LLC method the geometry of feature space is described by an ensemble of representative points (visual words) while discarding the geometric structure immediately surrounding them. Such a dictionary only provides a crude, piecewise constant approximation of the data manifold. To approach this problem, we propose a novel feature coding method called locality-constrained affine subspace coding (LASC). The data manifold in LASC is characterized by an ensemble of subspaces attached to the representative points (or affine subspaces), which can provide a piecewise linear approximation of the manifold. Given an input descriptor, we find its top-k neighboring subspaces, in which the descriptor is linearly decomposed and weighted to form the first-order LASC vector. Inspired by the success of usage of higher-order information in image classification, we propose the second-order LASC vector based on the Fisher information metric for further performance improvement. We make experiments on challenging benchmarks and experiments have shown the LASC method is very competitive.
引用
收藏
页码:2348 / 2357
页数:10
相关论文
共 50 条
  • [1] Locality-constrained affine subspace coding for image classification and retrieval
    Zhang, Bingbing
    Wang, Qilong
    Lu, Xiaoxiao
    Wang, Fasheng
    Li, Peihua
    [J]. PATTERN RECOGNITION, 2020, 100 (100)
  • [2] Detecting anomalies in crowded scenes via locality-constrained affine subspace coding
    Fan, Yaxiang
    Wen, Gongjian
    Qiu, Shaohua
    Li, Deren
    [J]. JOURNAL OF ELECTRONIC IMAGING, 2017, 26 (04)
  • [3] Spatial and Temporal Features Aggregation Convolutional Network Model Based on Locality-Constrained Affine Subspace Coding
    基于局部约束仿射子空间编码的时空特征聚合卷积网络模型
    [J]. Li, Pei-Hua (peihuali@dlut.edu.cn), 1600, Science Press (43): : 1589 - 1603
  • [4] Graph Regularized and Locality-Constrained Coding for Robust Visual Tracking
    Zhou, Tao
    Bhaskar, Harish
    Liu, Fanghui
    Yang, Jie
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2017, 27 (10) : 2153 - 2164
  • [5] 3D Action Recognition Using Depth-based Feature and Locality-constrained Affine Subspace Coding
    Liang, Chengwu
    Chen, Enqing
    Qi, Lin
    Guan, Ling
    [J]. PROCEEDINGS OF 2016 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM), 2016, : 261 - 266
  • [6] 3D Human Action Recognition Using a Single Depth Feature and Locality-Constrained Affine Subspace Coding
    Liang, Chengwu
    Qi, Lin
    He, Yifeng
    Guan, Ling
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2018, 28 (10) : 2920 - 2932
  • [7] Locality-Constrained Discriminative Learning and Coding
    Wang, Shuyang
    Fu, Yun
    [J]. 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2015,
  • [8] Locality-constrained least squares regression for subspace clustering
    Chen, Yuanyuan
    Yi, Zhang
    [J]. KNOWLEDGE-BASED SYSTEMS, 2019, 163 : 51 - 56
  • [9] Action Classification with Locality-constrained Linear Coding
    Rahmani, Hossein
    Mahmood, Arif
    Huynh, Du
    Mian, Ajmal
    [J]. 2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, : 3511 - 3516
  • [10] Locality-constrained Linear Coding for Image Classification
    Wang, Jinjun
    Yang, Jianchao
    Yu, Kai
    Lv, Fengjun
    Huang, Thomas
    Gong, Yihong
    [J]. 2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2010, : 3360 - 3367