MEDIA LABEL PROPAGATION IN AN AD HOC NETWORK

• US 20170031934A1
• Filed: 07/27/2015
• Published: 02/02/2017
• Est. Priority Date: 07/27/2015
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: SNOEK, Cornelis Gerardus Maria
• Granted Patent: US 10,002,136 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/13 File access structures, e.g. distributed indices arrangements of input from, or output to, record carriers G06F3/06
• CPC Class Codes: G06F 16/148 File search processing
• CPC Class Codes: G06F 16/41 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: H04L 45/08 Learning-based routing, e.g. using neural networks or artificial intelligence
• CPC Class Codes: H04W 84/18 Self-organising networks, e.g. ad-hoc networks or sensor networks

Abstract

A method of labeling media files includes connecting to at least one device on an ad hoc network and indexing media and corresponding labels in the ad hoc network. The method also includes comparing a computed feature representation of a seed media file with feature representations of other media files in the ad hoc network to create an ordered list. The method further includes determining whether a label corresponding to a media file on the ordered list matches the label of the seed media file and increasing a label frequency when the label corresponding to the media file on the ordered list matches the label of the seed media file.

Claims

1. A method of labeling media files, comprising:

connecting to at least one device on an ad hoc network;

indexing media and corresponding labels in the ad hoc network;

comparing a computed feature representation of a seed media file with feature representations of other media files in the ad hoc network to create an ordered list;

determining whether a label corresponding to a media file on the ordered list matches the label of the seed media file; and

increasing a label frequency when the label corresponding to the media file on the ordered list matches the label of the seed media file.

2. The method of claim 1, in which the comparing, determining, and increasing are repeated for other media files in the ad hoc network.

3. The method of claim 1, in which the media file contains at least one of image data, audio data, olfactory data, biosensor data, data collected on a smartphone, data collected on a vehicle, data collected on a medical device, data collected on a scientific instrument, or a combination thereof.

4. The method of claim 1, in which a similarity metric is determined based on the comparing of the computed feature representation of the seed media file with the computed feature representation of a second media file on the ad hoc network.

5. The method of claim 4, in which the determining of the similarity metric is adapted to data according to a means for metric learning.

6. The method of claim 1, further comprising labeling the media file based at least in part on the label frequency.

7. The method of claim 6, further comprising training a classifier based at least in part on labeled media files.

8. An apparatus configured to label media files, the apparatus comprising:

a memory; and

at least one processor coupled to the memory, the at least one processor being configured;

to connect to at least one device on an ad hoc network;

to index media and corresponding labels in the ad hoc network;

to compare a computed feature representation of a seed media file with feature representations of other media files in the ad hoc network to create an ordered list;

to determine whether a label corresponding to a media file on the ordered list matches the label of the seed media file; and

to increase a label frequency when the label corresponding to the media file on the ordered list matches the label of the seed media file.

9. The apparatus of claim 8, in which the at least one processor is further configured to repeat comparing the computed feature representation, determining whether the label corresponding to the media file on the ordered list matches the label of the seed media file, and increasing the label frequency when the label corresponding to the media file on the ordered list matches the label of the seed media file are repeated for other media files in the ad hoc network.

10. The apparatus of claim 8, in which the media file includes at least one of image data, audio data, olfactory data, biosensor data, data collected on a smartphone, data collected on a vehicle, data collected on a medical device, data collected on a scientific instrument, or a combination thereof.

11. The apparatus of claim 8, in which the at least one processor is further configured to determine a similarity metric based at least in part on the comparing of the computed feature representation of the seed media file with the computed feature representation of a second media file on the ad hoc network.

12. The apparatus of claim 11, in which the determining of the similarity metric is adapted to data according to a means for metric learning.

13. The apparatus of claim 8, in which the at least one processor is further configured to label the media file based at least in part on the label frequency.

14. The apparatus of claim 13, in which the at least one processor is further configured to train a classifier based at least in part on labeled media files.

15. An apparatus configured to label media files, the apparatus comprising:

means for connecting to at least one device on an ad hoc network;

means for indexing media and corresponding labels in the ad hoc network;

means for comparing a computed feature representation of a seed media file with feature representations of other media files in the ad hoc network to create an ordered list;

means for determining whether a label corresponding to a media file on the ordered list matches the label of the seed media file; and

means for increasing a label frequency when the label corresponding to the media file on the ordered list matches the label of the seed media file.

16. The apparatus of claim 15, in which the comparing, the determining, and the increasing are repeated for other media files in the ad hoc network.

17. The apparatus of claim 15, in which the media file includes at least one of image data, audio data, olfactory data, biosensor data, data collected on a smartphone, data collected on a vehicle, data collected on a medical device, data collected on a scientific instrument, or a combination thereof.

18. The apparatus of claim 15, in which a similarity metric is determined based on the comparing of the computed feature representation of the seed media file with the computed feature representation of a second media file on the ad hoc network.

19. The apparatus of claim 18, in which the means for determining the similarity metric is adapted to data according to a means for metric learning.

20. The apparatus of claim 15, further comprising means for labeling the media file based at least in part on the label frequency.

21. The apparatus of claim 20, further comprising means for training a classifier based at least in part on labeled media files.

22. A computer program product for labeling media files, the computer program product comprising:

a non-transitory computer readable medium having program code recorded thereon, the program code comprising;

program code to connect to at least one device on an ad hoc network;

program code to index media and corresponding labels in the ad hoc network;

program code to compare a computed feature representation of a seed media file with feature representations of other media files in the ad hoc network to create an ordered list;

program code to determine whether a label corresponding to a media file on the ordered list matches the label of the seed media file; and

program code to increase a label frequency when the label corresponding to the media file on the ordered list matches the label of the seed media file.

23. The computer program product of claim 22, further comprising program code to repeat the comparing, the determining, and the increasing for other media files in the ad hoc network.

24. The computer program product of claim 22, in which the media file includes at least one of image data, audio data, olfactory data, biosensor data, data collected on a smartphone, data collected on a vehicle, data collected on a medical device, data collected on a scientific instrument, or a combination thereof.

25. The computer program product of claim 22, further comprising program code to determine a similarity metric based on the comparing of the computed feature representation of the seed media file with the computed feature representation of a second media file on the ad hoc network.

26. The computer program product of claim 25, further comprising program code in which the determination of the similarity metric is adapted to data according to a device for metric learning.

27. The computer program product of claim 22, further including program code to label the media file based at least in part on the label frequency.

28. The computer program product of claim 27, further including program code to train a classifier based at least in part on labeled media files.