In recent years several techniques have been proposed for modelling the low-dimensional manifolds, or `subspaces', of natural images. Examples include principal component anal...
This paper presents a method to infer hidden semantic cues by accumulating the knowledge learned from relevance feedback sessions. We propose to explicitly represent a semantic sp...
In this paper we propose a generic framework based on Hidden Markov Models (HMMs) for recognition of individuals from their gait. The HMM framework is suitable, because the gait o...
Aravind Sundaresan, Amit K. Roy Chowdhury, Rama Ch...
In this paper, we describe a statistical method to detect highlights in a baseball game video. The input video is first segmented into scene shots, within which the camera motion ...
Elevation maps are a widely used spatial data representation in geographical information systems (GIS). Paths on elevation maps can be characterized by profiles, which describe re...