Object categorization using co-occurrence, location and appearance
Object categorization using co-occurrence, location and appearance
复制标题
DOI：
10.1109/cvpr.2008.4587799
复制
发表时间：
2008-06
期刊：
影响因子：
--
通讯作者：
C. Galleguillos;Andrew Rabinovich;Serge J. Belongie
中科院分区：
文献类型：
--
作者：
C. Galleguillos;Andrew Rabinovich;Serge J. Belongie
在这项工作中，我们介绍了一种新的方法，对象分类，结合了两种类型的上下文同现和相对位置-与本地外观为基础的功能。我们的方法，名为CoLA（共现，位置和外观），使用条件随机场（CRF），以最大限度地提高对象标签协议根据语义和空间相关性。我们使用简单的成对特征来建模对象之间的相对位置。通过矢量量化这个特征空间，我们直接从数据中学习一小部分原型空间关系。我们在两个具有挑战性的数据集上评估了我们的结果：PASCAL 2007和MSRC。结果表明，与单独使用同现相比，将同现和空间上下文相结合可以提高多达一半类别的准确性。
In this work we introduce a novel approach to object categorization that incorporates two types of context-co-occurrence and relative location - with local appearance-based features. Our approach, named CoLA (for co-occurrence, location and appearance), uses a conditional random field (CRF) to maximize object label agreement according to both semantic and spatial relevance. We model relative location between objects using simple pairwise features. By vector quantizing this feature space, we learn a small set of prototypical spatial relationships directly from the data. We evaluate our results on two challenging datasets: PASCAL 2007 and MSRC. The results show that combining co-occurrence and spatial context improves accuracy in as many as half of the categories compared to using co-occurrence alone.