Media content annotation
According to one implementation, a media content annotation system includes a computing platform including a hardware processor and a system memory storing a model-driven annotation software code. The hardware processor executes the model-driven annotation software code to receive media content for annotation, identify a data model corresponding to the media content, and determine a workflow for annotating the media content based on the data model, the workflow including multiple tasks. The hardware processor further executes the model-driven annotation software code to identify one or more annotation contributors for performing the tasks included in the workflow, distribute the tasks to the one or more annotation contributors, receive inputs from the one or more contributors responsive to at least some of the tasks, and generate an annotation for the media content based on the inputs.
1. A media content annotation system comprising:
a computing platform including a hardware processor and a system memory;
the system memory storing a model-driven annotation software code;
the hardware processor configured to execute the model-driven annotation software code to:
receive a video with timecodes for annotation, the video including scenes indexed to timecodes;
identify a data model corresponding to the video;
determine a workflow for annotating the video based on the data model, the workflow including multiple tasks;
identify at least one annotation contributor for performing the tasks including annotating the scenes using a plurality annotation entries comprising a location, a trait, an actor and an action type;
distribute the tasks to the at least one annotation contributor;
receive the plurality of annotation entries from the at least one annotation contributor responsive to at least some of the tasks; and
annotate the scenes in the video based on the received annotation entries indexed to the timecodes.
2. The media content annotation system of claim 1 , further comprising a non-relational annotation database stored in the system memory, wherein the hardware processor is further configured to execute the model-driven annotation software code to store the received annotation entries in the non-relational annotation database.
3. The media content annotation system of claim 2 , wherein the non-relational database comprises a triplestore.
4. The media content annotation system of claim 1 , wherein the data model corresponds to at least one of dramatic and comedic television content.
5. The media content annotation system of claim 1 , wherein the data model corresponds to movie content.
6. The media content annotation system of claim 1 , wherein the data model corresponds to news content.
7. The media content annotation system of claim 1 , wherein the hardware processor is further configured to execute the model-driven annotation software code to adapt the workflow based on the received annotation entries from the at least one annotation contributor.
8. The media content annotation system of claim 1 , wherein the at least one annotation contributor comprises at least first and second annotation contributors, the first annotation contributor being a human, and the second annotation contributor being a machine.
9. A method for use by a media content annotation system including a computing platform having a hardware processor and a system memory storing a model-driven annotation software code, the method comprising:
receiving, using the hardware processor, a video with timecodes for annotation, the video including scenes indexed to timecodes;
identifying, using the hardware processor, a data model corresponding to the video;
determining, using the hardware processor, a workflow for annotating the video based on the data model, the workflow including multiple tasks;
identifying, using the hardware processor, at least one annotation contributor for performing the tasks including annotating the scenes using a plurality annotation entries comprising a location, a trait, an actor and an action type;
distributing, using the hardware processor, the tasks to the at least one annotation contributor;
receiving, using the hardware processor, the plurality of annotation entries from the at least one annotation contributor responsive to at least some of the tasks; and
annotating, using the hardware processor, the scenes in the video based on the received annotation entries indexed to the timecodes.
10. The method of claim 9 , wherein the media content annotation system further comprises a non-relational annotation database stored in the system memory, and wherein the method further comprises storing, using the hardware processor, the received annotation entries in the non-relational annotation database.
11. The method of claim 10 , wherein the non-relational database comprises a triplestore.
12. The method of claim 9 , wherein the data model corresponds to at least one of dramatic and comedic television content.
13. The method of claim 9 , wherein the data model corresponds to movie content.
14. The method of claim 9 , wherein the data model is corresponds to news content.
15. The method of claim 9 , further comprising adapt the workflow, using the hardware processor, based on the received annotation entries from the at least one annotation contributor.
16. The method of claim 9 , wherein the at least one annotation contributor comprises at least first and second annotation contributors, the first annotation contributor being a human, and the second annotation contributor being a machine.