GPU-accelerated scene categorization under multiscale category-specific visual word strategy

摘要

We utilize GPU to accelerate an essential component for computer vision and multimedia information retrieval, i.e. scene categorization. To construct bag of word models, we modify calculation of Euclidean distance so that feature clustering and visual word quantization can be processed in a parallel manner. We provide details of GPU implementations and conduct comprehensive experiments to verify the efficiency of GPU on multimedia analysis.