Object Detection with Grammar Models

Part of Advances in Neural Information Processing Systems 24 (NIPS 2011)

Bibtex »Metadata »Paper »SpotlightSlide »

Authors

Ross Girshick, Pedro Felzenszwalb, David McAllester

Abstract

<p>Compositional models provide an elegant formalism for representing the visual appearance of highly variable objects. While such models are appealing from a theoretical point of view, it has been difficult to demonstrate that they lead to performance advantages on challenging datasets. Here we develop a grammar model for person detection and show that it outperforms previous high-performance systems on the PASCAL benchmark. Our model represents people using a hierarchy of deformable parts, variable structure and an explicit model of occlusion for partially visible objects. To train the model, we introduce a new discriminative framework for learning structured prediction models from weakly-labeled data.</p>