Popular content in video sharing web sites (e.g., YouTube) is usually duplicated. Most scholars deļ¬ne near-duplicate video clips (NDVC) based on non-semantic features (e.g., diļ...
Mauro Cherubini, Rodrigo de Oliveira, Nuria Oliver
We present four approaches to the Amharic - French bilingual track at CLEF 2005. All experiments use a dictionary based approach to translate the Amharic queries into French Bags-...
Given a string s, the Parikh vector of s, denoted p(s), counts the multiplicity of each character in s. Searching for a match of Parikh vector q (a ājumbled stringā) in the tex...
Peter Burcsi, Ferdinando Cicalese, Gabriele Fici, ...
We address the classic problems of detection, segmenta-
tion and pose estimation of people in images with a novel
definition of a part, a poselet. We postulate two criteria
(1) ...
An algorithm for tracking a person's head is presented. The head's projection onto the image plane is modeled as an ellipse whose position and size are continually updat...