Automated cinematic decisions based on descriptive models

1. A method comprising:

accessing input data from one or more different input sources, the input sources comprising: one or more cameras, one or more microphones, and a social graph maintained by a social-networking system;

based on the input data, generating a current descriptive model for a current audio-video communication session that comprises one or more descriptive characteristics about (1) an environment associated with the current audio-video communication session, (2) one or more people within the environment, or (3) one or more contextual elements associated with the current audio-video communication session;

generating one or more instructions for the current audio-video communication session that are based the one or more descriptive characteristics; and

sending the one or more instructions to a computing device associated with the one or more cameras and the one or more microphones.

2. The method of claim 1 , wherein the one or more descriptive characteristics about the environment associated with the current audio-video communication session comprises:

a location for each of one or more walls within the environment;

a location for each of one or more doors within the environment;

a category of the environment; and

a location for each of one or more objects within the environment.

3. The method of claim 1 , wherein the one or more descriptive characteristics about the one or more people comprises, for each person of the one or more people:

an engagement metric with the current audio-video communication session; and

an affinity between the person and at least one other person of the one or more people.

4. The method of claim 3 , wherein the engagement metric for each person of the one or more people is based at least in part on a count of words spoken by the person, a physical distance between the person and the computing device, an amount of time the person has been in the environment during the current audio-video communication system, or social graph data associated with the person.

5. The method of claim 1 , further comprising generating a historical descriptive model based on a plurality of past audio-video communication sessions that have occurred within the environment, wherein the one or more descriptive characteristics are based at least in part on the historical descriptive model.

6. The method of claim 1 , wherein the one or more instructions comprise instructions to zoom in on a visual target, pan toward a visual target, beamform a microphone to an audio target, or cut a scene to a visual target.

7. The method of claim 1 , wherein the one or more contextual elements associated with the current audio-video communication session comprises a time of day for the current audio-video communication session, a data of the current audio-video communication session, or an event associated with the current audio-video communication session.

8. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

access input data from one or more different input sources, the input sources comprising: one or more cameras, one or more microphones, and a social graph maintained by a social-networking system;

based on the input data, generate a current descriptive model for a current audio-video communication session that comprises one or more descriptive characteristics about (1) an environment associated with the current audio-video communication session, (2) one or more people within the environment, or (3) one or more contextual elements associated with the current audio-video communication session;

generate one or more instructions for the current audio-video communication session that are based the one or more descriptive characteristics; and

send the one or more instructions to a computing device associated with the one or more cameras and the one or more microphones.

9. The media of claim 8 , wherein the one or more descriptive characteristics about the environment associated with the current audio-video communication session comprises:

a location for each of one or more walls within the environment;

a location for each of one or more doors within the environment;

a category of the environment; and

a location for each of one or more objects within the environment.

10. The media of claim 8 , wherein the one or more descriptive characteristics about the one or more people comprises, for each person of the one or more people:

an engagement metric with the current audio-video communication session; and

an affinity between the person and at least one other person of the one or more people.

11. The media of claim 10 , wherein the engagement metric for each person of the one or more people is based at least in part on a count of words spoken by the person, a physical distance between the person and the computing device, an amount of time the person has been in the environment during the current audio-video communication system, or social graph data associated with the person.

12. The media of claim 8 , wherein the software is further operable when executed to generate a historical descriptive model based on a plurality of past audio-video communication sessions that have occurred within the environment, wherein the one or more descriptive characteristics are based at least in part on the historical descriptive model.

13. The media of claim 8 , wherein the one or more instructions comprise instructions to zoom in on a visual target, pan toward a visual target, beamform a microphone to an audio target, or cut a scene to a visual target.

14. The media of claim 8 , wherein the one or more contextual elements associated with the current audio-video communication session comprises a time of day for the current audio-video communication session, a data of the current audio-video communication session, or an event associated with the current audio-video communication session.

15. A system comprising:

one or more processors; and

one or more computer-readable non-transitory storage media coupled to one or more of the processors and comprising instructions operable when executed by one or more of the processors to cause the system to:

access input data from one or more different input sources, the input sources comprising: one or more cameras, one or more microphones, and a social graph maintained by a social-networking system;

based on the input data, generate a current descriptive model for a current audio-video communication session that comprises one or more descriptive characteristics about (1) an environment associated with the current audio-video communication session, (2) one or more people within the environment, or (3) one or more contextual elements associated with the current audio-video communication session;

generate one or more instructions for the current audio-video communication session that are based the one or more descriptive characteristics; and

send the one or more instructions to a computing device associated with the one or more cameras and the one or more microphones.

16. The system of claim 15 , wherein the one or more descriptive characteristics about the environment associated with the current audio-video communication session comprises:

a location for each of one or more walls within the environment;

a location for each of one or more doors within the environment;

a category of the environment; and

a location for each of one or more objects within the environment.

17. The system of claim 15 , wherein the one or more descriptive characteristics about the one or more people comprises, for each person of the one or more people:

an engagement metric with the current audio-video communication session; and

an affinity between the person and at least one other person of the one or more people.

18. The system of claim 17 , wherein the engagement metric for each person of the one or more people is based at least in part on a count of words spoken by the person, a physical distance between the person and the computing device, an amount of time the person has been in the environment during the current audio-video communication system, or social graph data associated with the person.

19. The system of claim 15 , wherein the processors are further operable when executing the instructions to generate a historical descriptive model based on a plurality of past audio-video communication sessions that have occurred within the environment, wherein the one or more descriptive characteristics are based at least in part on the historical descriptive model.

20. The system of claim 15 , wherein the one or more instructions comprise instructions to zoom in on a visual target, pan toward a visual target, beamform a microphone to an audio target, or cut a scene to a visual target.