US 12,293,779 B2
Techniques for automatically extracting compelling portions of a media content item
Apurvakumar Dilipkumar Kansara, San Jose, CA (US)
Assigned to NETFLIX, INC., Los Gatos, CA (US)
Filed by NETFLIX, INC., Los Gatos, CA (US)
Filed on May 16, 2022, as Appl. No. 17/745,718.
Application 17/745,718 is a continuation of application No. 16/689,019, filed on Nov. 19, 2019, granted, now 11,334,752.
Prior Publication US 2022/0277564 A1, Sep. 1, 2022
Int. Cl. G11B 27/031 (2006.01); G06F 18/23213 (2023.01); G06V 10/762 (2022.01); G06V 20/40 (2022.01); G06V 40/16 (2022.01)
CPC G11B 27/031 (2013.01) [G06F 18/23213 (2023.01); G06V 10/762 (2022.01); G06V 20/40 (2022.01); G06V 20/41 (2022.01); G06V 20/47 (2022.01); G06V 20/49 (2022.01); G06V 40/164 (2022.01); G06V 40/172 (2022.01)] 16 Claims
OG exemplary drawing
 
1. A computer-implemented method for generating clips for media content items, the method comprising:
computing, for each shot sequence included in a first plurality of different shot sequences of a media content item, at least one appearance value for an appearance metric, wherein the media content item has previously been partitioned into the first plurality of different shot sequences based on each shot sequence included in the first plurality of different shot sequences being captured from a different respective point of capture than one or more temporally adjacent shot sequences;
identifying a plurality of different temporally sequential shot sequences within the first plurality of different shot sequences based on similarities in appearance values across a subset of appearance values for the plurality of different temporally sequential shot sequences to generate a first shot cluster;
generating a clip for the media content item based on the first shot cluster; and
transmitting the clip to an endpoint device for display.