Behavioral measurements in a video stream focalized on keywords

1. A computer-implemented method comprising:

extracting a plurality of salient fragments from a video, a salient fragment being a video sequence tracking a salient object through a subset of a series of frames in the video;

associating a time anchor with an utterance of a first keyword in an audio track associated with the video;

generating a video segment focalized on the time anchor associated with the utterance of the first keyword from one or more of the plurality of salient fragments of the video;

tagging a human subject in the video segment with a unique identifier; and

analyzing behavior of the human subject, using the video segment, to generate a behavior score associated with the unique identifier and the first keyword.

2. The computer-implemented method of claim 1 , further comprising:

storing the behavior score as a record in a database using the unique identifier and the first keyword as attributes.

3. The computer-implemented method of claim 2 , further comprising:

performing a query on the database based on selection criteria that is selected from the group consisting of a date of record, the unique identifier, the time anchor, the first keyword, the behavior score, a minimum behavior score, a maximum behavior score, and an average behavior score.

4. The computer-implemented method of claim 1 , further comprising:

generating a baseline behavior for a behavioral attribute; and

producing a contrastive behavior score by comparing the behavior of the human subject to the baseline behavior.

5. The computer-implemented method of claim 4 , wherein generating the baseline behavior comprises analyzing behavior of the human subject at a time anchor associated with an utterance of a second keyword in the audio track associated with the video.

6. The computer-implemented method of claim 1 , wherein the first keyword is a slogan.

7. The computer-implemented method of claim 1 , wherein the first keyword is included in a set of keywords and the behavior score is associated with the unique identifier and the set of keywords.

8. The computer-implemented method of claim 7 , wherein the set of keywords is extracted from a syllabus describing a course of study.

9. The computer-implemented method of claim 7 , wherein the set of keywords includes safety terms included in a safety training program.

10. The computer-implemented method of claim 7 , wherein the set of keywords is extracted from a transcript of a meeting.

11. A computer program product comprising a non-transitory computer readable medium storing a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:

extract a plurality of salient fragments from a video, a salient fragment being a video sequence tracking a salient object through a subset of a series of frames in the video;

associate a time anchor with an utterance of a first keyword in an audio track associated with the video;

generate a video segment focalized on the time anchor associated with the utterance of the first keyword from one or more of the plurality of salient fragments of the video;

tag a human subject in the video segment with a unique identifier; and

analyze behavior of the human subject, using the video segment, to generate a behavior score associated with the unique identifier and the first keyword.

12. The computer program product of claim 11 , wherein the computer readable program when executed on the computer further causes the computer to:

store the behavior score as a record in a database using the unique identifier and the first keyword as attributes.

13. The computer program product of claim 12 , wherein the computer readable program when executed on the computer further causes the computer to:

perform a query on the database based on selection criteria that is selected from the group consisting of a date of record, the unique identifier, the time anchor, the first keyword, the behavior score, a minimum behavior score, a maximum behavior score, and an average behavior score.

14. The computer program product of claim 11 , wherein the computer readable program when executed on the computer further causes the computer to:

generate a baseline behavior for a behavioral attribute; and

produce a contrastive behavior score by comparing the behavior of the human subject to the baseline behavior.

15. The computer program product of claim 14 , wherein to generate the baseline behavior, the computer readable program when executed on the computer further causes the computer to:

analyze behavior of the human subject at a time anchor associated with an utterance of a second keyword in the audio track associated with the video.

16. A system comprising:

one or more processors; and

a memory, the memory storing instructions which when executed cause the one or more processors to:

extract a plurality of salient fragments from a video, a salient fragment being a video sequence tracking a salient object through a subset of a series of frames in the video;

associate a time anchor with an utterance of a first keyword in an audio track associated with the video;

generate a video segment focalized on the time anchor associated with the utterance of the first keyword from one or more of the plurality of salient fragments of the video;

tag a human subject in the video segment with a unique identifier; and

analyze behavior of the human subject, using the video segment, to generate a behavior score associated with the unique identifier and the first keyword.

17. The system of claim 16 , wherein the instructions further cause the one or more processors to:

store the behavior score as a record in a database using the unique identifier and the first keyword as attributes.

18. The system of claim 17 , wherein the instructions further cause the one or more processors to:

perform a query on the database based on selection criteria that is selected from the group consisting of a date of record, the unique identifier, the time anchor, the first keyword, the behavior score, a minimum behavior score, a maximum behavior score, and an average behavior score.

19. The system of claim 16 , wherein the instructions further cause the one or more processors to:

generate a baseline behavior for a behavioral attribute; and

produce a contrastive behavior score by comparing the behavior of the human subject to the baseline behavior.

20. The system of claim 19 , wherein to generate the baseline behavior, the instructions further cause the one or more processors to:

analyze behavior of the human subject at a time anchor associated with an utterance of a second keyword in the audio track associated with the video.