Generating tags for a digital video

1. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computer system to:

extract a set of frames from a video;

generate, utilizing a neural network, feature vectors for the set of frames;

identify a set of tagged feature vectors corresponding to a set of media content items, the set of tagged feature vectors comprising feature vectors generated from particular media content items and tagged with labels that correspond to the particular media content items;

select one or more tagged feature vectors from the set of tagged feature vectors based on distances between the feature vectors and the one or more tagged feature vectors from the set of tagged feature vectors; and

generate a set of tags to associate with the video by:

selecting tags from the one or more tagged feature vectors; and

aggregating the tags selected from the one or more tagged feature vectors.

2. The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:

generate the feature vectors for the set of frames by:

generating, utilizing the neural network, a set of initial feature vectors, wherein the set of initial feature vectors comprise a feature vector for each frame from the set of frames; and

generating an aggregated feature vector based on the set of initial feature vectors; and

select the one or more tagged feature vectors from the set of tagged feature vectors based on distances between the aggregated feature vector and the one or more tagged feature vectors from the set of tagged feature vectors.

3. The non-transitory computer-readable medium of claim 1 , wherein each feature vector within the set of tagged feature vectors is generated from a media content item and tagged with labels that describe depictions within a particular media content item.

4. The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:

select the one or more tagged feature vectors from the set of tagged feature vectors by:

determining distance values between the feature vectors and the one or more tagged feature vectors from the set of tagged feature vectors; and

selecting the one or more tagged feature vectors that correspond to distance values that meet a threshold distance value.

5. The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computer system to identify the set of tagged feature vectors from one or more videos associated with actions.

6. The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computer system to generate the set of tags to associate with the video by aggregating action based tags corresponding to the one or more tagged feature vectors.

7. The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computer system to identify the set of tagged feature vectors by:

identifying a media content item comprising text representing one or more verbs;

generating, utilizing the neural network, a tagged feature vector for the media content item;

assigning tags to the tagged feature vector by assigning the one or more verbs to the tagged feature vector; and

associating the tagged feature vector with the set of tagged feature vectors.

8. The non-transitory computer-readable medium of claim 1 , further comprising instructions that, when executed by the at least one processor, cause the computer system to associate the set of tags with a temporal segment of the video comprising the set of frames.

9. The non-transitory computer-readable medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:

provide graphical user interface displaying the video;

provide a timeline for the video in the graphical user interface; and

place a tag indicator associated with a tag of the set of tags on the timeline at a position corresponding to the temporal segment of the video.

10. The non-transitory computer-readable medium of claim 7 , further comprising instructions that, when executed by the at least one processor, cause the computer system to identify the media content item comprising text representing one or more verbs by identifying one or more gerunds within text associated with the media content item.

11. A system comprising:

memory comprising a neural network and a set of tagged feature vectors corresponding to a set of media content items, the set of tagged feature vectors comprising feature vectors generated from particular media content items and tagged with labels that correspond to the particular media content items;

at least one processor; and

at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to:

extract a set of frames from a video;

generate, utilizing the neural network, feature vectors for the set of frames; and

generate a set of tags to associate with the video by:

determining distance values between the feature vectors for the set of frames and one or more tagged feature vectors from the set of tagged feature vectors;

selecting tags from the one or more tagged feature vectors from the set of tagged feature vectors based on the determined distance values; and

aggregating the tags selected from the one or more tagged feature vectors.

12. The system of claim 11 , further comprising instructions that, when executed by the at least one processor, cause the system to:

generate the feature vectors for the set of frames by:

generating, utilizing the neural network, a set of initial feature vectors, wherein the set of initial feature vectors comprise a feature vector for each frame from the set of frames; and

generating an aggregated feature vector based on the set of initial feature vectors; and

generate the set of tags associated with the video by determining the distance values between the aggregated feature vector and the one or more tagged feature vectors from the set of tagged feature vectors.

13. The system of claim 12 , wherein generating the aggregated feature vector comprises combining the set of initial feature vectors utilizing averaging or max pooling.

14. The system of claim 11 , further comprising instructions that, when executed by the at least one processor, cause the system to select the one or more tags associated with the one or more tagged feature vectors from the set of tagged feature vectors based on the determined distance values by utilizing a k-nearest neighbor algorithm.

15. The system of claim 11 , further comprising instructions that, when executed by the at least one processor, cause the system to generate the set of tags to associate the set of tags with a temporal segment of the video comprising the set of frames.

16. A computer-implemented method for automatic tagging of videos, the computer-implemented method comprising:

extracting a set of frames from a video;

generating, utilizing a neural network, feature vectors for the set of frames;

performing a step for generating an aggregated feature vector from the feature vectors;

determining one or more tagged feature vectors similar to the aggregated feature vector based on distances between the aggregated feature vector and the one or more tagged feature vectors, wherein the one or more tagged feature vectors are associated with an identified set of tagged feature vectors corresponding to a set of media content items and comprising feature vectors generated from particular media content items and tagged with labels that correspond to the particular media content items; and

generating a set of tags to associate with the video by:

selecting tags from the one or more tagged feature vectors based on the distances between the aggregated feature vector and the one or more tagged feature vectors; and

aggregating the tags selected from the one or more tagged feature vectors.

17. The computer-implemented method of claim 16 , wherein performing the step for generating the aggregated feature vector from the feature vectors comprises combining the feature vectors by utilizing max pooling.

18. The computer-implemented method of claim 16 , further comprising determining the one or more tagged feature vectors that are similar to the aggregated feature vector based on the distances utilizing a k-nearest neighbor algorithm.

19. The computer-implemented method of claim 16 , further comprising generating the set of tags to associate with the video from action based tags corresponding to the one or more tagged feature vectors.

20. The computer-implemented method of claim 16 , further comprising identifying the one or more tagged feature vectors from one or more videos associated with actions.