Models for representing images and video
Applications of learned models: solving computer vision tasks by learning and inference. Local spatial and spatio-temporal descriptors of image properties. Representing images and videos with a set of local descriptors. Selection of a representative set of image patches. Representing images and videos by vectors. Image kernels and similarity functions between images and videos. Generative and discriminative models of image contents. Models for representing the structure of an image or an image collection. Learning the model from training samples. Inference using the learned models: examples of classification and segmentation. Applying learned models for detection and localization of objects and actions as well as for image and video categorization, retrieval and ranking.
Christopher M. Bishop (2016.), Pattern Recognition and Machine Learning, Springer
Simon J. D. Prince (2012.), Computer Vision, Cambridge University Press
Richard Szeliski (2010.), Computer Vision, Springer Science & Business Media
L1 English Level