2013 · 167 citations · 32 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionImage AnnotationImage LabelingObject DetectionObject RecognitionScene UnderstandingUnsupervised LearningProposal FormulationSaliency DetectionSaliency MappingSalient Object DetectionSamplingVisual SaliencyWeakly Supervised AnnotationWeakly Supervised Labeling
We propose a principled probabilistic formulation of object saliency as a sampling problem. This novel formulation allows us to learn, from a large corpus of unlabelled images, which patches of an image are of the greatest interest and most likely to correspond to an object. We then sample the object saliency map to propose object locations. We show that using only a single object location proposal per image, we are able to correctly select an object in over 42% of the images in the Pascal VOC 2007 dataset, substantially outperforming existing approaches. Furthermore, we show that our object proposal can be used as a simple unsupervised approach to the weakly supervised annotation problem. Our simple unsupervised approach to annotating objects of interest in images achieves a higher annotation accuracy than most weakly supervised approaches.
32
The Pascal Visual Object Classes (VOC) Challenge
Mark Everingham, Luc Van Gool, Christopher K. I. Williams et al. · International Journal of Computer Vision · 2009 · 19.5K citations · Full text
Object recognition from local scale-invariant features
David Lowe · 1999 · 16.2K citations
A feature-integration theory of attention
Anne Treisman, Garry A. Gelade · Cognitive Psychology · 1980 · 12.4K citations
Medicine, Psychology, Vision Science +12