US 11,935,300 B2
Techniques for generating candidate match cuts
Boris Anthony Chen, Palo Alto, CA (US); Amirreza Ziai, Menlo Park, CA (US); Kelli Rebecca Griggs, Running Springs, CA (US); and Rebecca Suzanne Tucker, Boulder, CO (US)
Assigned to NETFLIX, INC., Los Gatos, CA (US)
Filed by NETFLIX, INC., Los Gatos, CA (US)
Filed on Nov. 5, 2021, as Appl. No. 17/520,505.
Prior Publication US 2023/0147904 A1, May 11, 2023
Int. Cl. G06V 20/40 (2022.01); G06F 18/2413 (2023.01)
CPC G06V 20/49 (2022.01) [G06F 18/24147 (2023.01); G06V 20/46 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
detecting a plurality of shot sequences within one or more video sequences;
generating, for each shot sequence included in the plurality of shot sequences, an encoding associated with the shot sequence;
comparing a first encoding associated with a first shot sequence included in the plurality of shot sequences with a plurality of other encodings associated with a plurality of other shot sequences included in the plurality of shot sequences to identify one or more shot sequences associated with encodings similar to the first encoding; and
generating one or more candidate match cuts for the first shot sequence based on the one or more shot sequences.