IP Library Granted Patent US 10,277,946
Granted Patent B2
US 10,277,946 · App. 15/699,446 · Granted Apr 30, 2019

Methods and systems for aggregation and organization of multimedia data acquired from a plurality of sources

Inventors: Shih-Fu Chang (New York, NY); Brendan Jou (Rego Park, NY); Hongzhi Li (New York, NY); Joseph G. Ellis (New York, NY); Daniel Morozoff-Abezgauz (New York, NY); Svebor Karaman (New York, NY)
Assignee: THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK
H04N21/4622G06F17/30784H04N21/4332H04N21/4334H04N21/4394H04N21/44008H04N21/458H04N21/4821H04N21/4826H04N21/4884H04N21/8126H04N21/858
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,277,946
App. No.
15/699,446
Granted
Apr 30, 2019
Kind
B2
Abstract

A system for aggregation and organization of multimedia data acquired from a plurality of sources can include a data collection element, a multimedia segmentation element, a memory, an extraction element, and a user interface. The data collection element can be configured to receive multimedia data. The multimedia segmentation element can be coupled to the data collection element and can be configured to separate the multimedia data into a plurality of multimedia data segments. The memory can be configured to store hierarchical category information having a plurality of categories. The extraction element can be coupled to the multimedia segmentation element and the memory and can be configured to associate at least one of the plurality of categories with each of the plurality of multimedia data segments.

Claims (23)

1. A system for linking one or more segments of multimedia data to social media, comprising:

a processor configured to extract hierarchical category information by:

identifying at least one text region in each of the one or more segments, if any, containing text and extracting the text from the at least one text region in each of the one or more segments, if any, or

identifying a speaker based on a detected face track, applying a detected name in on-screen text and applying that to the speaker, or applying a detected name in an audio transcript based on temporal proximity to the speaker in each of the one or more segments, if any;

a memory, coupled to the processor, and configured to store the hierarchical category information based on the extracted text or the identified speaker; and

the processor further configured for:

associating the extracted hierarchical category information with the one or more segments of multimedia data, and

linking the one or more associated segments of multimedia data to social media based on a social media identifier.

2. The system of claim 1 , wherein the social media identifier is a hashtag.

3. The system of claim 1 , wherein a representation of the social media identifier is constructed by aggregating content tagged with the social media identifier.

4. The system of claim 3 , wherein a similarity metric is generated that compares the representation of the social media identifier to the one or more associated segments of multimedia data.

5. The system of claim 4 , wherein when the similarity metric exceeds a predefined threshold, the social medial identifier is linked the one or more associated segments of multimedia data.

6. A method for linking one or more segments of multimedia data to social media, comprising:

extracting, by a processor, hierarchical category information by:

identifying at least one text region in each of the one or more segments, if any, containing text and extracting the text from the at least one text region in each of the one or more segments, if any, or

identifying a speaker based on a detected face track, applying a detected name in on-screen text and applying that to the speaker, or applying a detected name in an audio transcript based on temporal proximity to the speaker in each of the one or more segments, if any;

storing, by a memory, the hierarchical category information based on the extracted text or the identified speaker;

associating, by the processor, the extracted hierarchical category information with the one or more segments of multimedia data; and

linking the one or more associated segments of multimedia data to social media based on a social media identifier.

7. The method of claim 6 , wherein the social media identifier is a hashtag.

8. The method of claim 6 , wherein a representation of the social media identifier is constructed by aggregating content tagged with the social media identifier.

9. The method of claim 8 , wherein a similarity metric is generated that compares the representation of the social media identifier to the one or more associated segments of multimedia data.

10. The method of claim 9 , wherein when the similarity metric exceeds a predefined threshold, the social medial identifier is linked the one or more associated segments of multimedia data.

Continuity (4)
Continuation 15095718 · Apr 11, 2016
Continuation In Part PCTUS2014060127 · Oct 10, 2014
Provisional Application 61889472 · Oct 10, 2013
Related Publication 20180109843A1 · Apr 19, 2018
Cited By (1)
US 12,306,864