A new architecture for region of interest (ROI) image coding is proposed. ROIs are defined as image regions containing objects of interest, and an efficient algorithm proposed for...
This work provides a framework for learning sequential attention in real-world visual object recognition, using an architecture of three processing stages. The first stage rejects...
Close-up (CU) is a photographic technique which tightly frames a person or an object. In movies, it is applied to guide audience attention and to evoke audience emotion. In this p...
Huiying Liu, Min Xu, Qingming Huang, Jesse S. Jin,...
This paper formalizes a novel, intrinsic geometric scale space (IGSS) of 3D surface shapes. The intrinsic geometry of a surface is diffused by means of the Ricci flow for the gener...
Abstract— Autonomous mobile agents require object recognition for high level interpretation and localization in complex scenes. In urban environments, recognition of buildings mi...