arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.10149cs.CV
收藏

静态图像和视频中动作分类的判别字典设计

Discriminative Dictionary Design for Action Classification in Still Images and Videos

Nanyang Technological University(南洋理工大学);Indian Institute of Technology, Bombay(印度理工学院孟买分校);Edinburgh Napier University(爱丁堡龙比亚大学);Singapore University of Technology and Design(新加坡科技设计大学)

Abhinaba Roy, Biplab Banerjee, Amir Hussain, Soujanya Poria

摘要:

在本文中,我们解决的问题,从静止图像和视频的动作识别。传统的局部特征,如SIFT、STIP等,总是会带来两个潜在的问题:1)它们在给定类别的不同实体中的分布不均匀; 2)许多这样的特征并不排斥实体所表示的视觉概念。为了生成一个字典考虑到上述问题,我们提出了一种新的判别方法,用于识别鲁棒性和类别特定的局部特征,最大限度地提高类可分性在更大程度上。具体来说,我们提出的过滤为基础的特征选择问题,排名的基础上,一个新的独特性措施的每类本地功能的有效本地描述符的选择。随后基于学习的字典表示底层视觉实体,并且该阶段之后是使用随机森林模型的动作分类,之后是标签传播细化。该框架在基于静态图像(Stanford-40)和视频(UCF-50)的动作识别数据集上进行了验证,并表现出比文献中的代表性方法更优越的性能。

英文摘要:

In this paper, we address the problem of action recognition from still images and videos. Traditional local features such as SIFT, STIP etc. invariably pose two potential problems: 1) they are not evenly distributed in different entities of a given category and 2) many of such features are not exclusive of the visual concept the entities represent. In order to generate a dictionary taking the aforementioned issues into account, we propose a novel discriminative method for identifying robust and category specific local features which maximize the class separability to a greater extent. Specifically, we pose the selection of potent local descriptors as filtering based feature selection problem which ranks the local features per category based on a novel measure of distinctiveness. The underlying visual entities are subsequently represented based on the learned dictionary and this stage is followed by action classification using the random forest model followed by label propagation refinement. The framework is validated on the action recognition datasets based on still images (Stanford-40) as well as videos (UCF-50) and exhibits superior performances than the representative methods from the literature.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑