Methods, systems, and media for identifying videos containing objectionable content
Techniques are disclosed for identifying videos containing objectionable content. An example method comprises identifying, by a computing system, a video uploaded to a video sharing service, generating an embedding for the video using a neural network, wherein the embedding specifies a location of the video in a multi-dimensional space where a plurality of videos are located based on content of the videos, identifying from the videos a plurality of associated videos that each have an associated embedding that is located within a predetermined distance of the embedding, determining whether the video is likely to include a particular type of objectionable content by at least determining at least a predetermined amount of the associated videos that contain the particular type of objectionable content, and responsive to determining that the video is likely to include the particular type of objectionable content, causing the video to be blocked from the video sharing service.
1. A method comprising:
identifying, by a computing system using a hardware processor, a video that has been uploaded to a video sharing service;
generating, by the computing system, an embedding for the video using a neural network, wherein the embedding specifies a location of the video in a multi-dimensional space where a plurality of videos are located based on content of the plurality of videos;
identifying, by the computing system, from the plurality of videos a plurality of associated videos that each have an associated embedding that is located within a predetermined distance of the embedding of the video in the multi-dimensional space;
determining, by the computing system, whether the video is likely to include a particular type of objectionable content by at least determining at least a predetermined amount of the plurality of associated videos that contain the particular type of objectionable content; and
responsive to determining that the video is likely to include the particular type of objectionable content, causing, by the computing system, the video to be blocked from the video sharing service.
2. The method of claim 1 , further comprising transmitting, by the computing system, an indication of the video to a user account associated with a verifier prior to causing the video to be blocked from the video sharing service, wherein causing the video to be blocked is responsive to receiving, by the computing system, a verification from the user account associated with the verifier that the video includes the objectionable content.
3. The method of claim 1 , further comprising determining, by the computing system, a confidence level that the video includes the particular type of objectionable content based on the predetermined amount.
4. The method of claim 1 , wherein identifying the plurality of associated videos that each have the associated embedding that is located within the predetermined distance of the embedding of the video comprises transmitting, by the computing system, a query to a remote server that includes the embedding for the video.
5. The method of claim 1 , wherein causing the video to be blocked from the video sharing service comprises assigning, by the computing system, a viewer restriction to the video.
6. The method of claim 1 , wherein the predetermined amount is selected from the group consisting of a predetermined amount and a predetermined percentage.
7. The method of claim 2 , wherein transmitting the indication of the video to the user account associated with the verifier responsive to determining the at least the predetermined amount of the plurality of associated videos contain the particular type of objectionable content.
8. The method of claim 3 , further comprising:
determining, by the computing system, that the confidence level is below a predetermined threshold; and
responsive to determining that the confidence level is below the predetermined threshold, transmitting, by the computing system, an indication of the video to a user account associated with a verifier prior to causing the video to be blocked from the video sharing service, wherein causing the video to be blocked is responsive to receiving, by the computing system, a verification from the user account associated with the verifier that the video includes the objectionable content.
9. A computing system comprising:
a memory that stores instructions; and
processing circuitry that executes the instructions to:
identify a video that has been uploaded to a video sharing service;
generate an embedding for the video using a neural network, wherein the embedding specifies a location of the video in a multi-dimensional space where a plurality of videos are located based on content of the plurality of videos;
identify from the plurality of videos a plurality of associated videos that each have an associated embedding that is located within a predetermined distance of the embedding of the video in the multi-dimensional space;
determine whether the video is likely to include a particular type of objectionable content by at least determining at least a predetermined amount of the plurality of associated videos that contain the particular type of objectionable content; and
responsive to determining that the video is likely to include the particular type of objectionable content, cause the video to be blocked from the video sharing service.
10. The computing system of claim 9 , wherein the processing circuitry further executes the instructions to transmit an indication of the video to a user account associated with a verifier prior to causing the video to be blocked from the video sharing service, wherein causing the video to be blocked is responsive to receiving a verification from the user account associated with the verifier that the video includes the objectionable content.
11. The computing system of claim 9 , wherein the processing circuitry further executes the instructions to determine a confidence level that the video includes the particular type of objectionable content based on the predetermined amount.
12. The computing system of claim 9 , wherein to identify the plurality of associated videos that each have the associated embedding that is located within the predetermined distance of the embedding of the video the processing circuitry further executes the instructions to transmit a query to a remote server that includes the embedding for the video.
13. The computing system of claim 9 , wherein to cause the video to be blocked from the video sharing service the processing circuitry further executes the instructions to assign a viewer restriction to the video.
14. The computing system of claim 9 , wherein the predetermined amount is selected from the group consisting of a predetermined amount and a predetermined percentage.
15. The computing system of claim 10 , wherein transmitting the indication of the video to the user account associated with the verifier is responsive to determining the at least the predetermined amount of the plurality of associated videos contain the particular type of objectionable content.
16. The computing system of claim 11 , wherein the processing circuitry further executes the instructions to:
determine that the confidence level is below a predetermined threshold; and
responsive to determining that the confidence level is below the predetermined threshold, transmit an indication of the video to a user account associated with a verifier prior to causing the video to be blocked from the video sharing service, wherein causing the video to be blocked is responsive to receiving a verification from the user account associated with the verifier that the video includes the objectionable content.
17. A non-transitory computer-readable storage medium comprising instructions, that when executed by processing circuitry of a computing system, cause the processing circuitry to:
identify a video that has been uploaded to a video sharing service;
generate an embedding for the video using a neural network, wherein the embedding specifies a location of the video in a multi-dimensional space where a plurality of videos are located based on content of the plurality of videos;
identify from the plurality of videos a plurality of associated videos that each have an associated embedding that is located within a predetermined distance of the embedding of the video in the multi-dimensional space;
determine whether the video is likely to include a particular type of objectionable content by at least determining at least a predetermined amount of the plurality of associated videos that contain the particular type of objectionable content; and
responsive to determining that the video is likely to include the particular type of objectionable content, cause the video to be blocked from the video sharing service.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the instructions, when further executed by the processing circuitry, cause the processing circuitry to determine a confidence level that the video includes the particular type of objectionable content based on the predetermined amount.
19. The non-transitory computer-readable storage medium of claim 17 , wherein to cause the video to be blocked from the video sharing service the instructions, when further executed by the processing circuitry, cause the processing circuitry to assign a viewer restriction to the video.
20. The non-transitory computer-readable storage medium of claim 18 , wherein the instructions, when further executed by the processing circuitry, cause the processing circuitry to:
determine that the confidence level is below a predetermined threshold; and
responsive to determining that the confidence level is below the predetermined threshold, transmit an indication of the video to a user account associated with a verifier prior to causing the video to be blocked from the video sharing service, wherein causing the video to be blocked is responsive to receiving a verification from the user account associated with the verifier that the video includes the objectionable content.