Shimojima and Katagiri have demonstrated that diagrams reduce "inferential load" during reasoning by scaffolding visual-spatial aspects of memory. In response, we wondere...
We present a method for picture detection in document page images, which can come from scanned or camera images, or rendered from electronic file formats. Our method uses OCR to s...
In this paper we present a framework for semantic scene parsing and object recognition based on dense depth maps. Five viewindependent 3D features that vary with object class are e...
Abstract. New methods of data collection, in particular the wide range of sensors and sensor networks that are being constructed, with the ability to collect real-time data streams...
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...