Using audio cues to improve object retrieval in video
First Claim
1. A method of object retrieval from visual data, the method comprising:
- annotating at least one portion of the visual data with a context keyword corresponding to an object, wherein the annotating is performed responsive to recognition of the context keyword by performing speech recognition in audio data corresponding to the at least one portion of the visual data;
receiving a query to retrieve the object, wherein the query comprises a query keyword associated with both the object and the context keyword;
identifying the at least one portion of the visual data based on the context keyword; and
searching for the object in the at least one portion of the visual data using an appearance model corresponding to the query keyword.
1 Assignment
0 Petitions
Accused Products
Abstract
A method of object retrieval from visual data is provided that includes annotating at least one portion of the visual data with a context keyword corresponding to an object, wherein the annotating is performed responsive to recognition of the context keyword in audio data corresponding to the at least one portion of the visual data, receiving a query to retrieve the object, wherein the query includes a query keyword associated with both the object and the context keyword, identifying the at least one portion of the visual data based on the context keyword, and searching for the object in the at least one portion of the visual data using an appearance model corresponding to the query keyword.
-
Citations
5 Claims
-
1. A method of object retrieval from visual data, the method comprising:
-
annotating at least one portion of the visual data with a context keyword corresponding to an object, wherein the annotating is performed responsive to recognition of the context keyword by performing speech recognition in audio data corresponding to the at least one portion of the visual data; receiving a query to retrieve the object, wherein the query comprises a query keyword associated with both the object and the context keyword; identifying the at least one portion of the visual data based on the context keyword; and searching for the object in the at least one portion of the visual data using an appearance model corresponding to the query keyword. - View Dependent Claims (2)
-
-
3. A digital system configured to perform object retrieval from visual data, the digital system comprising one or more processors configured to:
-
capture the visual data and corresponding audio data; annotate at least one portion of the visual data with a context keyword that is obtained from audio data corresponding to the at least one portion of the visual data; receive a query to retrieve an object, wherein the query comprises a query keyword associated with both the object and the context keyword; identify the at least one portion of the visual data based on the context keyword; and search for the object in the at least one portion of the visual data using an appearance model corresponding to the query keyword. - View Dependent Claims (4, 5)
-
Specification