Method and apparatus for segmenting and summarizing media content

1. A method comprising:

segmenting, by a processor, a first media content item, among a plurality of media content items, into at least a first segment and a second segment;

associating, by the processor, a first keyword with the first segment;

assigning, by the processor, to the first keyword a first probability value indicating relevance of the first keyword to the first segment;

creating, by the processor, a summary of the plurality of media content items, that are provided respectively by a plurality of users and share at least one common originating characteristic, in response to a search query that includes the first keyword,

wherein the at least one common originating characteristic includes originating from an identical event, being captured at an identical location, being captured approximately at an identical time, being captured by an identical person or entity, or a combination thereof, and

wherein the summary is provided as a search result and includes the first segment and other segments from other content items based on probability values of the other segments; and

modifying, by the processor, the segmenting of the first segment based on the probability values of the other segments in the response to the search query.

2. The method of claim 1 , further comprising:

in response to a user selection of the search result, changing the first probability value.

3. The method of claim 1 , wherein at least one of the associating and the assigning is based upon at least one of metadata of the first media content item, content analysis on the first media content item, and user inputs.

4. The method of claim 1 , further comprising:

assigning to the first keyword a second probability value indicating relevance of the first keyword to the second segment;

selecting a higher probability between the first probability value and the second probability value; and

creating a first summary of the first media content item associated with the first keyword by including one of the first and second segments with the higher probability value into the first summary.

5. The method of claim 1 , further comprising:

segmenting a second media content item into at least a third segment and a fourth segment, the second media content item being associated with the first media content item by the at least one common originating characteristic;

associating the first keyword with the third segment;

assigning to the first keyword a third probability value indicating relevance of the first keyword to the third segment; and

creating a second summary of the first media content item and the second media content item associated with the first keyword based upon the first probability value and the third probability value.

6. The method of claim 5 , further comprising:

identifying that the first segment and the third segment represent identical content;

selecting a higher probability between the first probability value and the third probability value; and

including one of the first and third segments with the higher probability value into the second summary to create the second summary.

7. The method of claim 1 , further comprising:

updating the summary based on feedback provided by one or more users, wherein the feedback affects the corresponding probability values.

8. The method of claim 1 , further comprising:

representing the first key word with a feature vector indicating semantics in a vocabulary, an index to an ontology representation, or a combination thereof,

wherein the summary is generated based, at least in part, on the feature vector, the index, or a combination thereof.

9. The method of claim 1 , further comprising:

in response to the search query, retrieving one or more synonyms of the first key word, one or more translations of the first keyword to different languages, or a combination thereof,

wherein the summary is generated based, at least in part, on the one or more synonyms of the first key word, the one or more translations of the first keyword to different languages, or a combination thereof.

10. The method of claim 1 , further comprising:

receiving, by the processor, the plurality of media content items that are uploaded respectively by the plurality of users to a media sharing service.

11. An apparatus comprising:

at least one processor; and

at least one memory including computer program code,

wherein the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following:

segment a first media content item, among a plurality of media content items, into at least a first segment and a second segment,

associate a first keyword with the first segment,

assign to the first keyword a first probability value indicating relevance of the first keyword to the first segment,

create a summary of the plurality of media content items, that are provided respectively by a plurality of users and share at least one common originating characteristic, in response to a search query that includes the first keyword,

wherein the at least one common originating characteristic includes originating from an identical event, being captured at an identical location, being captured approximately at an identical time, being captured by an identical person or entity, or a combination thereof, and

wherein the summary is provided as a search result and includes the first segment and other segments from other content items based on the probability values of the other segments; and

modifying the segmenting of the first segment based on the probability values of the other segments in the response to the search query.

12. The apparatus of claim 11 , wherein at least one of the associating and the assigning is based upon at least one of metadata of the first media content item, content analysis on the first media content item, and user inputs.

13. The apparatus of claim 11 , wherein the apparatus is further caused to:

assign to the first keyword a second probability value indicating relevance of the first keyword to the second segment,

select a higher probability between the first probability value and the second probability value, and

create a first summary of the first media content item associated with the first keyword by including one of the first and second segments with the higher probability value into the first summary.

14. The apparatus of claim 11 , wherein the apparatus is further caused to:

segment a second media content item into at least a third segment and a fourth segment, the second media content item being associated with the first media content item by the at least one common originating characteristic,

associate the first keyword with the third segment,

assign to the first keyword a third probability value indicating relevance of the first keyword to the third segment, and

create a second summary of the first media content item and the second media content item associated with the first keyword based upon the first probability value and the third probability value.

15. The apparatus of claim 14 , wherein the apparatus is further caused to:

identify that the first segment and the third segment represent identical content,

select a higher probability between the first probability value and the third probability value, and

include one of the first and third segments with the higher probability value into the second summary to create the second summary.

16. The apparatus of claim 11 , wherein the apparatus is within a user terminal or a server.

17. An apparatus comprising:

at least one processor; and

at least one memory including computer program code,

wherein the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following:

receive a first media content item among a plurality of media content items, a first segmentation indicating at least a first segment and a second segment of the first media content item, a first keyword associated with the first segment, and a first probability value indicating relevance of the first keyword to the first segment,

create a summary of the plurality of media content items, that are provided respectively by a plurality of users and share at least one common originating characteristic, in response to a search query that includes the first keyword, wherein the at least one common originating characteristic includes originating from an identical event, being captured at an identical location, being captured approximately at an identical time, being captured by an identical person or entity, or a combination thereof, and wherein the summary is provided as a search result and includes the first segment and other segments from other content items based on the probability values of the other segments, and

in response to a user selection of the search result, change the first probability value, and

modify the segmenting of the first segment based on the probability values of the other segments in the response to the search query.

18. The apparatus of claim 17 , wherein the apparatus is further caused to:

assign to the first keyword a second probability value indicating relevance of the first keyword to the second segment,

select a higher probability between the first probability value and the second probability value, and

create a first summary of the first media content item associated with the first keyword by including one of the first and second segments with the higher probability value into the first summary.

19. The apparatus of claim 17 , wherein the apparatus is further caused to:

segment a second media content item into at least a third segment and a fourth segment, the second media content item being associated with the first media content item by the at least one common originating characteristic,

associate the first keyword with the third segment,

assign to the first keyword a third probability value indicating relevance of the first keyword to the third segment, and

create a second summary of the first media content item and the second media content item associated with the first keyword based upon the first probability value and the third probability value.

20. The apparatus of claim 19 , wherein the apparatus is further caused to:

identify that the first segment and the third segment represent identical content,

select a higher probability between the first probability value and the third probability value, and

include one of the first and third segments with the higher probability value into the second summary to create the second summary.