Machine learning in video classification
Described herein are systems and methods that search videos and other media content to identify items, objects, faces, or other entities within the media content. Detectors identify objects within media content by, for instance, detecting a predetermined set of visual features corresponding to the objects. Detectors configured to identify an object can be trained using a machine learned model (e.g., a convolutional neural network) as applied to a set of example media content items that include the object. The systems provide user interfaces that allow users to review search results, pinpoint relevant portions of media content items where the identified objects are determined to be present, review detector performance and retrain detectors, providing search result feedback, and/or reviewing video monitoring results and analytics.
1. A computer-implemented method, comprising:
receiving, from a user, a search query;
classifying frames of a video using a first set of detectors configured to, for each frame of the video, process the frame and output a first confidence score indicating a likelihood that a first object associated with the search query is present within the frame;
classifying frames of the video using a second set of detectors configured to, for each frame of the video, process the frame and output a second confidence score indicating a likelihood that a second object associated with the search query is present within the frame;
identifying a first set of video segments each comprising consecutive frames associated with the first confidence score greater than a first threshold confidence score;
identifying a second set of video segments each comprising consecutive frames associated with the second confidence score greater than a second threshold confidence score; and
modifying a progress bar interface element comprising a first color to display highlighted locations within the progress bar interface element that correspond to the first set of video segments in a second color different from the first color and that correspond to the second set of video segments in a third color different from the first and second colors.
2. The method of claim 1 , wherein the first confidence score and the second confidence score each comprise an average of confidence scores outputted by the first set of detectors and the second set of detectors, respectively.
3. The method of claim 1 , wherein each video segment in the first set of video segments and the second set of video segments comprises at least a threshold number of consecutive frames.
4. The method of claim 1 , wherein the first confidence score comprises an average confidence score of the consecutive frames of video segment in the first set of video segments, and wherein at least one confidence score associated with a frame of the consecutive frames is less than the first threshold confidence score.
5. The method of claim 1 , wherein the first threshold confidence score and the second threshold confidence score are different.
6. The method of claim 1 , wherein the first threshold confidence score and the second threshold confidence score are received from the user.
7. The method of claim 1 , further comprising:
monitoring a displayed frame of the video during playback of the video; and
providing the first confidence score or the second confidence associated with the displayed frame for display.
8. A non-transitory computer-readable storage medium storing executable instructions that, when executed by a hardware processor, cause the hardware processor to perform steps comprising:
receiving, from a user, a search query;
classifying frames of a video using a first set of detectors configured to, for each frame of the video, process the frame and output a first confidence score indicating a likelihood that a first object associated with the search query is present within the frame;
classifying frames of the video using a second set of detectors configured to, for each frame of the video, process the frame and output a second confidence score indicating a likelihood that a second object associated with the search query is present within the frame;
identifying a first set of video segments each comprising consecutive frames associated with the first confidence score greater than a first threshold confidence score;
identifying a second set of video segments each comprising consecutive frames associated with the second confidence score greater than a second threshold confidence score; and
modifying a progress bar interface element comprising a first color to display highlighted locations within the progress bar interface element that correspond to the first set of video segments in a second color different from the first color and that correspond to the second set of video segments in a third color different from the first and second colors.
9. The non-transitory computer-readable storage medium of claim 8 , wherein the first confidence score and the second confidence score each comprise an average of confidence scores outputted by the first set of detectors and the second set of detectors, respectively.
10. The non-transitory computer-readable storage medium of claim 8 , wherein each video segment in the first set of video segments and the second set of video segments comprises at least a threshold number of consecutive frames.
11. The non-transitory computer-readable storage medium of claim 8 , wherein the first confidence score comprises an average confidence score of the consecutive frames of video segment in the first set of video segments, and wherein at least one confidence score associated with a frame of the consecutive frames is less than the first threshold confidence score.
12. The non-transitory computer-readable storage medium of claim 8 , wherein the first threshold confidence score and the second threshold confidence score are different.
13. The non-transitory computer-readable storage medium of claim 8 , wherein the first threshold confidence score and the second threshold confidence score are received from the user.
14. The non-transitory computer-readable storage medium of claim 8 , wherein the instructions, when executed by the hardware processor, cause the hardware processor to perform further steps comprising:
monitoring a displayed frame of the video during playback of the video; and
providing the first confidence score or the second confidence associated with the displayed frame for display.
15. A system, comprising:
a computer processor; and
a non-transitory memory storing executable computer instructions that when executed by the computer processor are configured to cause the computer processor to perform steps comprising:
receiving, from a user, a search query;
classifying frames of a video using a first set of detectors configured to, for each frame of the video, process the frame and output a first confidence score indicating a likelihood that a first object associated with the search query is present within the frame;
classifying frames of the video using a second set of detectors configured to, for each frame of the video, process the frame and output a second confidence score indicating a likelihood that a second object associated with the search query is present within the frame;
identifying a first set of video segments each comprising consecutive frames associated with the first confidence score greater than a first threshold confidence score;
identifying a second set of video segments each comprising consecutive frames associated with the second confidence score greater than a second threshold confidence score; and
modifying a progress bar interface element comprising a first color to display highlighted locations within the progress bar interface element that correspond to the first set of video segments in a second color different from the first color and that correspond to the second set of video segments in a third color different from the first and second colors.
16. The system of claim 15 , wherein the first confidence score and the second confidence score each comprise an average of confidence scores outputted by the first set of detectors and the second set of detectors, respectively.
17. The system of claim 15 , wherein each video segment in the first set of video segments and the second set of video segments comprises at least a threshold number of consecutive frames.
18. The system of claim 15 , wherein the first confidence score comprises an average confidence score of the consecutive frames of video segment in the first set of video segments, and wherein at least one confidence score associated with a frame of the consecutive frames is less than the first threshold confidence score.
19. The system of claim 15 , wherein the first threshold confidence score and the second threshold confidence score are different.
20. The system of claim 15 , wherein the first threshold confidence score and the second threshold confidence score are received from the user.