Automatic personalized story generation for visual media
Exemplary embodiments relate to the automatic generation of captions for visual media, including photos, photo albums, non-live video, and live video. The visual media may be analyzed to determine contextual information (such as location information, people and objects in the video, time, etc.). A system may integrate this information with information from the user's social network and a personalized language model built using public-facing language from the user. The personalized language model captures the user's way of speaking to make the generated captions more detailed and personalized. The language model may account for the context in which the video was generated. The captions maybe used to simplify and encourage content generation, and may also be used to index visual media, rank the media, and recommend the media to users likely to engage with the media.
1. A method, comprising: accessing visual media;
analyzing information associated with the visual media to identify a context of the visual media;
providing the context to a personalized language model configured to reflect a personal narrative style of the user; and
generating a caption for the visual media in the user's personal narrative style using the personalized language model, wherein generating the caption comprises applying the personalized language model in a first personal narrative style specific to the user for a first context and a second personal narrative style specific to the same user, differing from the first narrative style, in a second context differing from the first context.
2. The method of claim 1 , wherein the context includes location information, a person in the visual media, a recognized object in the visual media, a location of the visual media, or a time at which the visual media is recorded.
3. The method of claim 1 , wherein the personalized language model is configured using public-facing language collected from the user.
4. The method of claim 1 , wherein the user is connected to a second user in a social graph, and wherein the personalized language model is configured using public-facing language of the second user.
5. The method of claim 1 , wherein the caption serves as an index to the visual media for ranking or recommending the visual media.
6. The method of claim 1 , wherein the visual media is provided through an API call from a third-party source.
7. A non-transitory computer-readable medium storing instructions configured to cause one or more processors to:
access visual media;
analyze information associated with the visual media to identify a context of the visual media;
provide the context to a personalized language model configured to reflect a personal narrative style of the user; and
generate a caption for the visual media in the user's personal narrative style using the personalized language model, wherein generating the caption comprises applying the personalized language model in a first personal narrative style specific to the user for a first context and a second personal narrative style specific to the same user, differing from the first narrative style, in a second context differing from the first context.
8. The medium of claim 7 , wherein the context includes location information, a person in the visual media, a recognized object in the visual media, a location of the visual media, or a time at which the visual media is recorded.
9. The medium of claim 7 , wherein the personalized language model is configured using public-facing language collected from the user.
10. The medium of claim 7 , wherein the user is connected to a second user in a social graph, and wherein the personalized language model is configured using public-facing language of the second user.
11. The medium of claim 7 , wherein the caption serves as an index to the visual media for ranking or recommending the visual media.
12. The medium of claim 7 , wherein the visual media is provided through an API call from a third-party source.
13. An apparatus comprising:
a non-transitory computer readable medium configured to store instructions for interacting with visual media; and
a processor configured to execute the instructions, the instructions configured to cause the processor to:
access the visual media;
analyze information associated with the visual media to identify a context of the visual media;
provide the context to a personalized language model configured to reflect a personal narrative style of the user; and
generate a caption for the visual media in the user's personal narrative style using the personalized language model, wherein generating the caption comprises applying the personalized language model in a first personal narrative style specific to the user for a first context and a second personal narrative style specific to the same user, differing from the first narrative style, in a second context differing from the first context.
14. The apparatus of claim 13 , wherein the context includes location information, a person in the visual media, a recognized object in the visual media, a location of the visual media, or a time at which the visual media is recorded.
15. The apparatus of claim 13 , wherein the personalized language model is configured using public-facing language collected from the user.
16. The apparatus of claim 13 , wherein the user is connected to a second user in a social graph, and wherein the personalized language model is configured using public-facing language of the second user.
17. The apparatus of claim 13 , wherein the caption serves as an index to the visual media for ranking or recommending the visual media.