Object detection grammars

Publisher Website
Google Scholar
Abstract
Summary form only given. In this talk I will discuss various aspects of object detection using compositional models, focusing on the framework of object detection grammars, discriminative training and efficient computation. Object detection grammars provide a formalism for expressing very general types of models for object detection. Over the past few years we have considered a sequence of increasingly richer models. Each model in this sequence builds on the structures and methods employed by the pre- vious models, while staying within the framework of dis- criminatively trained grammar models. Along the way, we have increased representational capacity, developed new machine learning techniques, and focused on efficient computation. We are now at a stage where grammar based models are starting to outperform simpler models. We have a complete implementation of the formalism that makes it possible to quickly define new types of models using a simple modeling language.

This publication has 0 references indexed in Scilit: