Labelling scene content, e.g. deriving syntactic or semantic representations

dense prediction labelling each pixel of an image or video with a corresponding class of what is being represented. semantic image segmentation labelling regions (e.g. set of pixels) of an image with a corresponding object class of what is being represented. syntactic pattern recognition a form of pattern recognition, in which each object can be represented by a variable-cardinality set of symbolic, nominal features. This allows for representing pattern structures, taking into account more complex interrelationships between attributes than is possible in the case of flat, numerical feature vectors of fixed dimensionality, that are used in statistical classification.