US 12,340,551 B2
Cognitive placement of captioned text
Juan Carlos Pinzon Estupinan, Sacramento, CA (US); Ashutosh Vishwas Mate, San Jose, CA (US); Vinayak Harnoor, Pleasanton, CA (US); and Evelyn Bahiyyih Pirnia, San Mateo, CA (US)
Assigned to International Business Machines Corporation, Armonk, NY (US); and MASSACHUSETTS INSTITUTE OF TECHNOLOGY, Cambridge, MA (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Jan. 13, 2023, as Appl. No. 18/154,302.
Prior Publication US 2024/0242465 A1, Jul. 18, 2024
Int. Cl. G06V 10/26 (2022.01); G06V 20/40 (2022.01); G06V 20/62 (2022.01); H04N 5/278 (2006.01)
CPC G06V 10/267 (2022.01) [G06V 20/41 (2022.01); G06V 20/635 (2022.01); H04N 5/278 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer system comprising a processor communicatively coupled to a memory, wherein the processor performs processor operations comprising:
accessing video information having a plurality of image regions;
accessing text associated with the video information;
performing a relevance evaluation on each of the plurality of image regions to determine a set of relevance results;
wherein the relevance evaluation comprises an assessment, based at least in part on the text, of a viewer's understanding of the plurality of image regions;
determining a first group of relevance results within the set of relevance results;
determining a first group of image regions within the plurality of image regions that are associated with the first group of relevance results; and
incorporating the text within an image region selected from the first group of image regions.