Systems and methods to automatically perform actions based on media content
Systems and methods are provided for automatically arranging the display of a plurality of videos on a display of a computing device. One example method includes receiving, at the computing device, a plurality of video streams. An order in which to display the video streams is determined, based on the video of the video streams. The plurality of video streams is displayed on a display of the computing device based on the determined order.
1. A method for automatically arranging the display of a plurality of videos on a display of a computing device, the method comprising:
receiving, at the computing device, a plurality of video streams of a videoconference, the videoconference comprising a plurality of participants, and wherein the computing device transmits and receives messages comprising text and/or images from other videoconference participants;
determining a frequency of transmitting and receiving of messages between participants of the videoconference;
determining, based on the frequency of transmitting and receiving messages with a participant, an order in which to display the video streams;
displaying, based on the determined order, the plurality of video streams on a display of the computing device.
2. The method of claim 1 , wherein the video streams further comprise audio and the determining an order to display the videos further comprises:
determining, using natural language processing, context of the audio; and
basing the order in which to display the plurality of video streams on the context of the audio.
3. The method of claim 1 , wherein the wherein the video streams further comprise audio and the determining an order to display the video streams further comprises:
identifying a lead video stream of the plurality of video streams;
determining, using natural language processing and a participant recognition model, context of the audio of the lead video stream; and
basing the order in which to display the plurality of video streams on the context of the audio.
4. The method of claim 1 , wherein the wherein the video streams further comprise audio and the determining an order to display the video streams further comprises:
identifying a lead video stream of the plurality of video streams;
determining, using natural language processing and a participant recognition model, whether the name of a participant displayed in one of the remaining video streams is mentioned in the audio of the lead video stream; and
if a participant is mentioned in the audio of the lead video stream, basing the order in which to display the video streams on the mentioned participant.
5. The method of claim 1 , wherein the determining an order to display the video stream further comprises:
determining an entropy value for each video of the plurality of video streams; and
basing the order in which to display the plurality of video streams on the entropy values.
6. The method of claim 1 , wherein the determining an order to display the video streams further comprises:
determining, with a model trained to filter out non-human actions, an entropy value that reflects the actions of people in the video for each video of the plurality of video streams; and
basing the order in which to display the plurality of video streams on the entropy values.
7. The method of claim 1 , wherein the determining an order to display the video streams further comprises basing the order in which to display the plurality of video streams on the order in which participants in the videoconference join the videoconference.
8. The method of claim 1 , wherein the video streams are video streams of a videoconference, the videoconference comprising a plurality of participants, and wherein the determining an order to display the video streams further comprises basing the order in which to display the plurality of video streams on a label that participants in the videoconference have been assigned.
9. A system for automatically arranging the display of a plurality of videos on a display of a computing device, the system comprising:
a communication port; and
control circuitry configured to:
receive, at the computing device, a plurality of video streams from a video conference comprising a plurality of participants;
transmit and receive messages comprising text and/or images from other videoconference participants at the computing device;
determine, based on a frequency of transmitting and receiving messages with a participant, an order in which to display the video streams;
display, based on the determined order, the plurality of video streams on a display of the computing device.
10. The system of claim 9 , wherein:
the control circuitry configured to receive a plurality of video streams is further configured to receive video streams comprising audio; and
the control circuitry configured to determine an order in which to display the video streams is further configured to:
use natural language processing to determine the context of the video; and
base the order in which to display the plurality of video streams on the context of the audio.
11. The system of claim 9 , wherein:
the control circuitry configured to receive a plurality of video streams is further configured to receive video streams comprising audio; and
the control circuitry configured to determine an order in which to display the video streams is further configured to:
identify a lead video stream of the plurality of video streams;
determine, using natural language processing and a participant recognition model, context of the audio of the lead video stream; and
base the order in which to display the plurality of video streams on the context of the audio.
12. The system of claim 9 , wherein:
the control circuitry configured to receive a plurality of video streams is further configured to receive video streams comprising audio; and
the control circuitry configured to determine an order in which to display the video streams is further configured to:
determine, using natural language processing and a participant recognition model, whether the name of a participant displayed in one of the remaining video streams is mentioned in the audio of the lead video stream; and
if a participant is mentioned in the audio of the lead video stream, base the order in which to display the video streams on the mentioned participant.
13. The system of claim 9 , wherein the control circuitry configured to determine an order to display the video streams is further configured to:
determine an entropy value for each video of the plurality of video streams; and
base the order in which to display the plurality of video streams on the entropy values.
14. The system of claim 9 , wherein the control circuitry configured to determine an order to display the video streams is further configured to:
determine, with a model trained to filter out non-human actions, an entropy value that reflects the actions of people in the video for each video of the plurality of video streams; and
base the order in which to display the plurality of video streams on the entropy values.
15. The system of claim 9 , wherein:
the control circuitry configured to determine an order in which to display the video streams is further configured to base the order in which to display the plurality of video streams on the order in which participants in the videoconference join the videoconference.
16. The system of claim 9 , wherein:
the control circuitry configured to receive a plurality of video streams is further configured to receive video streams from a video conference comprising a plurality of participants; and
the control circuitry configured to determine an order in which to display the video streams is further configured to base the order in which to display the plurality of video streams on a label that participants in the videoconference have been assigned.