（转）Image Parsing with Regions and Per-Exemplar Detectors

这是Tomasz Malisiewicz在他的博客上推荐的一篇今年CVPR的论文。以下是转载自他的博客的内容（没有翻译）：

This paper combines ideas from segmentation-based "scene parsing" (see the below video for the output of their older ECCV2010 SuperParsing system) as well as per-exemplar detectors (see myExemplar-SVM paper, as well as my older Recognition by Association paper).  I have worked and published in these two separate lines of research, so when I tell you that this paper is worthy of reading, you should at least take a look.  Below I outline the two ideas which are being synthesized in this paper, but for all details you should read their paper (PDF link).  See the overview figure below:

Their system produces a per-pixel labeling of the input image, and as you can see below, the results are quite good.  Here are some more outputs of their system as compared to solely region-based as well as solely detector-based systems.  Using per-exemplar detectors clearly complements superpixel-based "segmentation-driven" approaches.

<a href="http://www.bfcat.com/wp-content/uploads/2013/06/tighe_parsing3.jpg" class="cboxElement" rel="example4" 3200"="" style="text-decoration: none; color: rgb(1, 150, 227);">

This paper will be presented as an oral in the Orals 3C session called "Context and Scenes" to be held on Thursday, June 27th at CVPR 2013 in Portland, Oregon.

Posted by Tomasz Malisiewicz at 4:37 PM