Media content metadata mapping
According to one implementation, a media content annotation system includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive a first version of media content and a second version of the media content altered with respect to the first version, and to map each of multiple segments of the first version of the media content to a corresponding one segment of the second version of the media content. The software code further aligns each of the segments of the first version of the media content with its corresponding one segment of the second version of the media content, and utilizes metadata associated with each of at least some of the segments of the first version of the media content to annotate its corresponding one segment of the second version of the media content.
1. A media content annotation system comprising:
a computing platform including a hardware processor and a system memory;
a software code stored in the system memory;
the hardware processor configured to execute the software code to:
receive a first version of a media content and a second version of the media content, wherein the second version of the media content is created by altering the first version of the media content;
map each of a plurality of first video shots of the first version of the media content to a corresponding one of a plurality of second video shots of the second version of the media content based on determining shot visual feature similarities between first video shot features of the plurality of first video shots and second video shot features of the corresponding one of the plurality of second video shots;
align, based on mapping the plurality of first video shots, each of the plurality of first video shots of the first version of the media content with the corresponding one of the plurality of second video shots of the second version of the media content, wherein each of the plurality of first video shots includes a plurality of first video frames, and each of the plurality of second video shots includes a plurality of second video frames;
after aligning each of the plurality of first video shots with the corresponding one of the plurality of second video shots, for each pair of the aligned one of the plurality of first video shots and the corresponding one of the plurality of second video shots:
map each of the plurality of first video frames to a corresponding one of the plurality of second video frames based on determining frame visual feature similarities between first video frame features of the plurality of first video frames and second video frame features of the corresponding one of the plurality of second video frames;
align, based on mapping the plurality of first video frames, each of the plurality of first video frames with the corresponding one of the plurality of second video frames; and
utilize metadata associated with a subset of the plurality of first video shots or a subset of the plurality of first video frames of the first version of the media content, to annotate the respective corresponding one of the plurality of second video shots or the plurality of second video frames of the second version of the media content.
2. The media content annotation system of claim 1 , wherein each of the plurality of first video shots of the first version of the media content and the corresponding one of the plurality of second video shots of the second version of the media content have a same temporal sequence.
3. The media content annotation system of claim 1 , wherein a temporal sequence of the plurality of second video shots of the second version of the media content is rearranged with respect to a temporal sequence of the plurality of first video shots of the first version of the media content.
4. The media content annotation system of claim 1 , wherein the hardware processor is further configured to execute the software code to utilize another metadata associated with each respective corresponding one of the plurality of second video shots or the plurality of second video frames of the second version of the media content, to annotate the subset of the plurality of first video shots or the subset of the plurality of first video frames of the first version of the media content.
5. The media content annotation system of claim 4 , wherein the another metadata is generated based on a viewer response to the second version of the media content.
6. A method for use by a media content annotation system including a computing platform having a hardware processor and a system memory storing a software code, the method comprising:
receiving, using the hardware processor, a first version of a media content and a second version of the media content, wherein the second version of the media content is created by altering the first version of the media content;
mapping, using the hardware processor, each of a plurality of first video shots of the first version of the media content to a corresponding one of a plurality of second video shots of the second version of the media content based on determining shot visual feature similarities between first video shot features of the plurality of first video shots and second video shot features of the corresponding one of the plurality of second video shots;
aligning, using the hardware processor and based on mapping the plurality of first video shots, each of the plurality of first video shots of the first version of the media content with the corresponding one of the plurality of second video shots of the second version of the media content, wherein each of the plurality of first video shots includes a plurality of first video frames, and each of the plurality of second video shots includes a plurality of second video frames;
after aligning each of the plurality of first video shots with the corresponding one of the plurality of second video shots, for each pair of the aligned one of the plurality of first video shots and the corresponding one of the plurality of second video shots:
mapping, using the hardware processor, each of the plurality of first video frames to a corresponding one of the plurality of second video frames based on determining frame visual feature similarities between first video frame features of the plurality of first video frames and second video frame features of the corresponding one of the plurality of second video frames;
aligning, using the hardware processor and based on mapping the plurality of first video frames, each of the plurality of first video frames with the corresponding one of the plurality of second video frames; and
utilizing, using the hardware processor, metadata associated with a subset of the plurality of first video shots or a subset of the plurality of first video frames of the first version of the media content, to annotate the respective corresponding one of the plurality of second video shots or the plurality of second video frames of the second version of the media content.
7. The method of claim 6 , wherein each of the plurality of first video shots of the first version of the media content and the corresponding one of the plurality of second video shots of the second version of the media content have a same temporal sequence.
8. The method of claim 6 , wherein a temporal sequence of the plurality of second video shots of the second version of the media content is rearranged with respect to a temporal sequence of the plurality of first video shots of the first version of the media content.
9. The method of claim 6 , further comprising utilizing another metadata associated with each respective corresponding one of the plurality of second video shots or the plurality of second video frames of the second version of the media content, to annotate the subset of the plurality of first video shots or the subset of the plurality of first video frames of the first version of the media content.
10. The method of claim 6 , wherein the another metadata is generated based on a viewer response to the second version of the media content.
11. The media content annotation system of claim 1 , wherein a first total number of the plurality of first video shots in the first version of the media content is greater than a second total number of the plurality of second video shots in the second version of the media content.
12. The media content annotation system of claim 1 , wherein a first total number of the plurality of first video shots in the first version of the media content is less than a second total number of the plurality of second video shots in the second version of the media content.
13. The method of claim 6 , wherein a first total number of the plurality of first video shots in the first version of the media content is greater than a second total number of the plurality of second video shots in the second version of the media content.
14. The method of claim 6 , wherein a first total number of the plurality of first video shots in the first version of the media content is less than a second total number of the plurality of second video shots in the second version of the media content.
15. The media content annotation system of claim 1 , wherein the first video shot features include first visual features of the first version of the media content, and the second video shot features include second visual features of the second version of the media content, and wherein the hardware processor is further configured to execute the software code to utilize a cost matrix to determine the shot visual feature similarities based on the first visual features and the second visual features.
16. The media content annotation system of claim 1 , wherein each of the first video shot features is represented by a corresponding one of a first plurality of feature vectors, wherein each of the second video shot features is represented by a corresponding one of a second plurality of feature vectors, and wherein the hardware processor is further configured to execute the software code to utilize a cost matrix to determine the shot visual feature similarities based on the first plurality of feature vectors and the second plurality of feature vectors.
17. The method of claim 6 , wherein the first video shot features include first visual features of the first version of the media content, and the second video shot features include second visual features of the second version of the media content, and wherein the method further comprises utilizing a cost matrix to determine the shot visual feature similarities based on the first visual features and the second visual features.
18. The method of claim 6 , wherein each of the first video shot features is represented by a corresponding one of a first plurality of feature vectors, wherein each of the second video shot features is represented by a corresponding one of a second plurality of feature vectors, and wherein the method further comprises utilizing a cost matrix to determine the shot visual feature similarities based on the first plurality of feature vectors and the second plurality of feature vectors.