资源分类
》 资源 》论文》Kernel Codebooks for Scene Categorization

Kernel Codebooks for Scene Categorization

2020-03-30 | |  62 |   48 |   0

Abstract

This paper introduces a method for scene categorization by modeling ambiguity in the popular codebook approach. The codebook approach describes an image as a bag of discrete visual codewords, where the frequency distributions of these words are used for image categoriza- tion. There are two drawbacks to the traditional codebook model: code- word uncertainty and codeword plausibility. Both of these drawbacks stem from the hard assignment of visual features to a single codeword. We show that allowing a degree of ambiguity in assigning codewords improves categorization performance for three state-of-the-art datasets.

上一篇：Pro jected Texture for Ob ject Classification

下一篇：Fast and Accurate Rotation Estimation on the 2-Sphere without Correspondences

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...