%0 Journal Article %F Jiang:Tomccap2010 %A Jiang, Wei %A Cotton, Courtenay %A Chang, Shih-Fu %A Ellis, Dan %A C. Loui, Alexander %T Audio-Visual Atoms for Generic Video Concept Classification %J ACM Transactions on Multimedia Computing, Communications and Applications %V 6 %N 3 %P 1-19 %I ACM %C New York, NY, USA %X We investigate the challenging issue of joint audio-visual analysis of generic videos targeting at concept detection. We extract a novel local representation, Audio-Visual Atom (AVA), which is defined as a region track associated with regional visual features and audio onset features. We develop a hierarchical algorithm to extract visual atoms from generic videos, and locate energy onsets from the corresponding soundtrack by time-frequency analysis. Audio atoms are extracted around energy onsets. Visual and audio atoms form AVAs, based on which discriminative audio-visual codebooks are constructed for concept detection. Experiments over Kodak's consumer benchmark videos confirm the effectiveness of our approach %U http://www.ee.columbia.edu/dvmm/publications/10/TOMCCAP10_avatoms.pdf %D 2010