Popular content in video sharing web sites (e.g., YouTube) is usually duplicated. Most scholars define near-duplicate video clips (NDVC) based on non-semantic features (e.g., di...
Mauro Cherubini, Rodrigo de Oliveira, Nuria Oliver
Traditional video scene analysis depends on accurate background modeling to identify salient foreground objects. However, in many important surveillance applications, saliency is ...
Brian Valentine, Senyo Apewokin, Linda M. Wills, D...
Visual information retrieval (VIR) is a research area with more than 300 scientific publications every year. Technological progress lets surveys become out of date within a short ...
Vector quantization (VQ) is an efficient coding algorithm due to its fast decoding efficiency. Indices of VQ will be lost during the transmission because of the signal interferenc...