Adjusting a configuration associated with a video output during a video conference

1 . A method, comprising:

detecting a trigger event by a client application connected to a video conference, wherein the client application is associated with a communications system used during the video conference, wherein the communications system includes a camera that generates a video output, and wherein the trigger event is associated with the camera;

responsive to detecting the trigger event, adjusting a configuration associated with the video output by dynamically changing a virtual background to deemphasize areas outside a region of interest within the video output and either changing a focal point associated with the camera or inverting an image of the video output, wherein the region of interest is selected based on detecting a participant or an object movement within the video output by a machine learning model trained to capture an intent of the participant;

sending a message indicating how the configuration associated with the video output was adjusted, wherein the message includes at least one image from the video output that reflects the configuration as adjusted during the video conference; and

training, based on feedback received with respect to the message, the machine learning model to more accurately capture the intent of the participant when adjusting the configuration.

2 . The method of claim 1 , wherein detecting the trigger event comprises:

receiving an input from a sensor indicating a movement of the camera.

3 . The method of claim 1 , wherein detecting the trigger event comprises:

detecting a change in an image of the video output indicating a movement of the camera.

4 . The method of claim 1 , wherein detecting the trigger event comprises:

detecting an audio statement via a microphone of the communications system.

5 . The method of claim 1 , wherein detecting the trigger event comprises:

detecting a movement of an object in an image of the video output.

6 . The method of claim 1 , wherein detecting the trigger event comprises:

using a machine learning model, wherein the machine learning model determines whether a change in an image of the video output should cause the trigger event.

7 . The method of claim 1 , wherein the machine learning model determines whether to adjust at least one of:

a focal point associated with the camera;

an orientation of an image of the video output; or

the virtual background.

8 . The method of claim 1 , wherein adjusting the configuration comprises:

changing a region of interest in an image of the video output.

9 . The method of claim 1 , wherein the message is sent after ending the video conference.

10 . An apparatus, comprising:

a communications system including a camera configured to generate a video output;

a memory; and

a processor configured to execute instructions stored in the memory to:

connect to a video conference;

detect a trigger event by a client application connected to the video conference, wherein the client application is associated with the communications system used during the video conference, and wherein the trigger event is associated with the camera;

responsive to detecting the trigger event, adjust a configuration associated with the video output by dynamically changing a virtual background to deemphasize areas outside a region of interest within the video output and either changing a focal point associated with the camera or inverting an image of the video output, wherein the region of interest is selected based on detecting a participant or an object movement within the video output by a machine learning model trained to capture an intent of the participant;

send a message indicating how the configuration associated with the video output was adjusted, wherein the message includes at least one image from the video output that reflects the configuration as adjusted during the video conference; and

train, based on feedback received with respect to the message, the machine learning model to more accurately capture the intent of the participant when adjusting the configuration.

11 . The apparatus of claim 10 , wherein detecting the trigger event comprises:

receiving an input from a sensor indicating a movement of the camera.

12 . The apparatus of claim 10 , wherein detecting the trigger event comprises:

detecting a change in an image of the video output indicating a movement of the camera.

13 . The apparatus of claim 10 , wherein the message is sent after ending the video conference.

14 . The apparatus of claim 10 , wherein the machine learning model determines whether to adjust at least one of:

a focal point associated with the camera;

an orientation of an image of the video output; or

the virtual background.

15 . The apparatus of claim 10 , wherein adjusting the configuration comprises changing a region of interest in an image of the video output.

16 . A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:

detecting a trigger event by a client application connected to a video conference, wherein the client application is associated with a communications system used during the video conference, wherein the communications system includes a camera that generates a video output, and wherein the trigger event is associated with the camera;

responsive to detecting the trigger event, adjusting a configuration associated with the video output by dynamically changing a virtual background to deemphasize areas outside a region of interest within the video output and either changing a focal point associated with the camera or inverting an image of the video output, wherein the region of interest is selected based on detecting a participant or an object movement within the video output by a machine learning model trained to capture an intent of the participant;

sending a message indicating how the configuration associated with the video output was adjusted, wherein the message includes at least one image from the video output that reflects the configuration as adjusted during the video conference; and

training, based on feedback received with respect to the message, the machine learning model to more accurately capture the intent of the participant when adjusting the configuration.

17 . The non-transitory computer readable medium storing instructions of claim 16 , wherein detecting the trigger event comprises:

receiving an input from a sensor indicating a movement of the camera.

18 . The non-transitory computer readable medium storing instructions of claim 16 , wherein detecting the trigger event comprises:

detecting a change in an image of the video output indicating a movement of the camera.

19 . The non-transitory computer readable medium storing instructions of claim 16 , wherein the message is sent after ending the video conference.

20 . The non-transitory computer readable medium storing instructions of claim 16 , wherein the machine learning model determines whether to adjust at least one of:

a focal point associated with the camera;

an orientation of an image of the video output; or

the virtual background.