Object recognition in video

A computer program product, the computer program product comprising a non-transitory computer-readable storage medium having program code embodied therewith, the program code executable by at least one hardware processor to:

• receive a video sequence;
• divide the video sequence into one or more scenes based on scene boundaries, wherein each scene comprises a plurality of temporally-contiguous image frames, and wherein said scene boundaries are being determined based on a similarity metric between two temporally-contiguous image frames meeting a dissimilarity threshold;
• and
• for each scene of the one or more scenes:
• (i) generate a plurality of preliminary classifications of an object appearing in at least some of said image frames in the scene, wherein each of said plurality of preliminary classifications has a confidence score, and
• (ii) calculate a combined classification of the object based on said plurality of preliminary classifications, wherein each of said preliminary classifications is weighted in accordance with its confidence score.

A system comprising:

• (a) a non-transient computer-readable storage medium having stored thereon instructions to:
• receive a video sequence,
• (i) divide the video sequence into scenes based on scene boundaries, wherein each scene comprises a plurality of temporally-contiguous image frames, and wherein said scene boundaries are being determined based on a distance metric between two temporally-contiguous image frames, and
• with respect to each scene of the scenes:
• (ii) generate a plurality of preliminary classifications of an object appearing in at least some of said image frames in the scene, wherein each of said plurality of preliminary classifications has a confidence score, and
• (iii) calculate a combined classification of the object based on said plurality of preliminary classifications, wherein each of said preliminary classifications is weighted in accordance with its confidence score, and
• iteratively repeat steps (i) through (iii), wherein for a next iteration, said dividing is based, at least in part, on said calculated combined classification;
• and
• (b) at least one hardware processor configured to execute the instructions.