This paper presents an new framework for homographybased analysis of pedestrian-vehicle activity in crowded scenes. Planar homography constraint is exploited to extract view-invar...
As the consequence of semantic gap, visual similarity does not guarantee semantic similarity, which in general is conflicting with the inherent assumption of many generativebased ...
My thesis aims to contribute towards building autonomous agents that are able to understand their surrounding environment through the use of both audio and visual information. To ...
This paper describes an interface which helps people maintain a sense of spatial context while navigating virtual real-world scenes. First, a single panoramic image of the entire ...
Abstract. Text detection in urban scenes is a hard task due to the high variability of text appearance: different text fonts, changes in the point of view, or partial occlusion are...