High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
In recent years, digital multimedia technologies have evolved significantly, and are finding numerous applications, over the internet, and even over mobile networks. Thus, the vid...
Alexia Briassouli, Vasileios Mezaris, Ioannis Komp...
— A new method for detecting shot boundaries in video sequences by fusing features obtained by singular value decomposition (SVD) and mutual information (MI) is proposed. The fi...
This paper presents an Enhanced Heuristic Segmenter (EHS) and an improved neural-based segmentation technique for segmenting cursive words and validating prospective segmentation ...
Abstract Computer vision is full of problems elegantly expressed in terms of energy minimization. We characterize a class of energies with hierarchical costs and propose a novel hi...
Andrew Delong, Lena Gorelick, Olga Veksler, Yuri B...