FIELD: data processing.
SUBSTANCE: invention relates to video content search tools. Video search method comprises steps of: receiving, via an input component of a computing device, a plurality of time slices of video content; performing extraction of audio-video descriptor on the time slices of video content; generating an audio-video signature associated with the time slices of video content based on the audio-video descriptor having been extracted, wherein the audio-video signature includes a video hash bit associated with the time slice of video content; sending the audio-video signature associated with the one or more time slices of video content as a query toward a dataset; continuing to receive candidate results of the query; and presenting candidate results, while continuing to receive time slices of video content.
EFFECT: technical result is wider range of video search means.
10 cl, 11 dwg
