Photo clustering into moments
View Patent ↗In one embodiment, a method includes automatically and without user input grouping one or more images captured by a first user into clusters of particular moments based at least in part on metadata associated with one or more of the images or data determined through analysis of one or more of the images. Each particular moment being associated with a particular geo-location and time. The method also includes, for each of one or more of the clusters, determining curating information corresponding to the cluster based at least in part on the metadata associated with images in the cluster, the data determined through analysis of images in the cluster, or social-graph information associated with images in the cluster; and providing the clusters of images and at least some of the curating information corresponding to them for display on a computing device of the first user.
1. A method comprising:
by a computing device, automatically and without user input grouping one or more images captured by a first user into clusters of particular moments based at least in part on metadata associated with one or more of the images or data determined through analysis of one or more of the images, each particular moment being associated with a particular geo-location and time;
by the computing device, for one or more of the clusters, determining curating information comprising information identifying one or more second users present at the particular geo-location and time, the determining being based at least in part on:
social-graph information associated with the first user;
social-graph information associated with one or more of the second users; and
socially relevant activity of one or more of the second users that is related to the particular geo-location and time, wherein the social-graph information comprises a social graph including a plurality of nodes and edges connecting the nodes, and wherein at least one node in the social graph corresponds to the first user and at least one node in the social graph corresponds to one of the second users; and
by the computing device, providing, for each of the one or more of the clusters, the images and a selected portion of the curating information for display on a computing device of the first user, wherein the provided curating information identifying one or more of the second users present at the particular geo-location and time is selected based on one or more edges in the social graph connecting one of the nodes corresponding to the second users to the node corresponding to the first user.
2. The method of claim 1 , wherein the identification of one or more of the second users is further based at least in part on analyzing facial-recognition data, location data associated a computing device of one or more of the second users, or a content object of one or more of the second users on the social-networking system that is socially relevant to the first user.
3. The method of claim 2 , wherein the content object comprises a status update, check-in, or event invitation that includes the first user.
4. The method of claim 1 , wherein grouping comprises, by the computing device, grouping a current image with a previous image based at least in part on a pre-determined time or distance differential threshold between the current image and the previous image.
5. The method of claim 4 , wherein the distance differential threshold comprises a standard deviation of an average amount of movement of the images.
6. The method of claim 1 , wherein the grouping comprises, by the computing device, grouping a current image with a previous image based at least in part on the current image having similar characteristics or composition as the previous image.
7. The method of claim 6 , wherein the similar characteristics comprise one or more objects or second users common to the current image and the previous image.
8. One or more computer-readable non-transitory storage media comprising memory embodying software configured when executed to:
automatically and without user input group one or more images captured by a first user into clusters of particular moments based at least in part on metadata associated with one or more of the images or data determined through analysis of one or more of the images, each particular moment being associated with a particular geo-location and time;
for one or more of the clusters, determine curating information comprising information identifying one or more second users present at the particular geo-location and time, the determining being based at least in part on:
social-graph information associated with the first user;
social-graph information associated with one or more of the second users; and
socially relevant activity of one or more of the second users that is related to the particular geo-location and time, wherein the social-graph information comprises a social graph including a plurality of nodes and edges connecting the nodes, and wherein at least one node in the social graph corresponds to the first user and at least one node in the social graph corresponds to one of the second users; and
provide, for each of the one or more of the clusters, the images and a selected portion of the curating information for display on a computing device of the first user, wherein the provided curating information identifying one or more of the second users present at the particular geo-location and time is selected based on one or more edges in the social graph connecting one of the nodes corresponding to the second users to the node corresponding to the first user.
9. The media of claim 8 , wherein the identification of one or more of the second users is further based at least in part on analyzing facial-recognition data, location data associated a computing device of one or more of the second users, or a content object of one or more of the second users on the social-networking system that is socially relevant to the first user.
10. The media of claim 9 , wherein the content object comprises a status update, check-in, or event invitation that includes the first user.
11. The media of claim 8 , wherein the software is configured to group a current image with a previous image based at least in part on a pre-determined time or distance differential threshold between the current image and the previous image.
12. The media of claim 11 , wherein the distance differential threshold comprises a standard deviation of an average amount of movement of the images.
13. The media of claim 8 , wherein the software is further configured to group a current image with a previous image based at least in part on the current image having similar characteristics or composition as the previous image.
14. The media of claim 13 , wherein the similar characteristics comprise one or more objects or second users common to the current image and the previous image.
15. A device comprising:
a processor; and
one or more computer-readable non-transitory storage media coupled to the processor and embodying software that:
automatically and without user input group one or more images captured by a first user into clusters of particular moments based at least in part on metadata associated with one or more of the images or data determined through analysis of one or more of the images, each particular moment being associated with a particular geo-location and time;
for one or more of the clusters, determine curating information comprising information identifying one or more second users present at the particular geo-location and time, the determining being based at least in part on:
social-graph information associated with the first user;
social-graph information associated with one or more of the second users; and
socially relevant activity of one or more of the second users that is related to the particular geo-location and time, wherein the social-graph information comprises a social graph including a plurality of nodes and edges connecting the nodes, and wherein at least one node in the social graph corresponds to the first user and at least one node in the social graph corresponds to one of the second users; and
provide, for each of the one or more of the clusters, the images and a selected portion of the curating information for display on a computing device of the first user, wherein the provided curating information identifying one or more of the second users present at the particular geo-location and time is selected based on one or more edges in the social graph connecting one of the nodes corresponding to the second users to the node corresponding to the first user.
16. The device of claim 15 , wherein the identification of one or more of the second users is further based at least in part on analyzing facial-recognition data, location data associated a computing device of one or more of the second users, or a content object of one or more of the second users on the social-networking system that is socially relevant to the first user.
17. The device of claim 15 , wherein the software is configured to group a current image with a previous image based at least in part on a pre-determined time or distance differential threshold between the current image and the previous image.
18. The device of claim 17 , wherein the distance differential threshold comprises a standard deviation of an average amount of movement of the images.