Participant sorting in video conferencing
An example non-transitory machine-readable storage medium comprising instructions executable by a processing resource of a computing device to cause the computing device to: receive a video feed of a participant in a video conference; identify the participants within the video feed; determine a probability that a characteristic is being experienced by the participant; determine a relevancy score of the participant based on the probability that the characteristic is being experienced by the participant; and display the participant relative to other participants in the video conference based on the relevancy score.
1. A non-transitory machine-readable storage medium comprising instructions executable by a processing resource of a computing device to cause the computing device to:
receive a video feed of a participant in a video conference;
identify the participant within the video feed;
determine a probability that a characteristic is being experienced by the participant;
determine, for each frame of the video feed, a frame relevancy score of the participant based on the probability that the characteristic is being experienced by the participant;
determine an average relevancy score for the participant based on a combination of the probability that the characteristic is being experienced by the participant, a sorting criterion, and a weighted average of the frame relevancy scores over a predetermined interval; and
display the participant relative to other participants in the video conference based on the average relevancy score.
2. The non-transitory machine-readable storage medium of claim 1 , wherein the instructions further cause the computing device to identify the participant using a multi-cascaded convolutional neural network (MTCNN).
3. The non-transitory machine-readable storage medium of claim 1 , wherein the instructions further cause the computing device to determine the probability using a convolutional neural network (CNN).
4. The non-transitory machine-readable storage medium of claim 1 , wherein the characteristic is selected from the group consisting of: an emotion and a level of engagement.
5. The non-transitory machine-readable storage medium of claim 1 , wherein the characteristic is an emotion corresponding to a state of boredom, tiredness, excitement, interest, anger, disgust, fear, happiness, sadness, surprise, or apathy, of the participant.
6. The non-transitory machine-readable storage medium of claim 1 , wherein the instructions cause the computing device to determine the probability using facial emotional analysis.
7. The non-transitory machine-readable storage medium of claim 1 , wherein the instructions cause the computing device to determine the probability using hand gesture recognition.
8. The non-transitory machine-readable storage medium of claim 1 , wherein the instructions further cause the computing device to determine the probability using head motion recognition.
9. The non-transitory machine-readable storage medium of claim 1 , wherein the sorting criterion corresponds to a similar characteristic experienced by the other participants in the video conference.
10. A non-transitory machine-readable storage medium comprising instructions executable by a processing resource of a computing device to cause the computing device to:
receive a probability that a characteristic is being experienced by a participant present in a video feed of a video conference;
receive a sorting criterion associated with the characteristic;
determine, for each frame of the video feed, a frame relevancy score of the participant using the probability and the sorting criterion;
determine an average relevancy score for the participant based on the probability that the characteristic is being expressed by the participant, the sorting criterion, and the a weighted average of the frame relevancy scores over a predetermined interval;
rank the participant relative to other participants in the video conference based on the relevancy score; and
display the video feed of the participant relative to the other participants in the video conference based on the average relevancy score.
11. The non-transitory machine-readable storage medium of claim 10 , wherein the characteristic is selected from the group consisting of: an emotion and a level of engagement.
12. The non-transitory machine-readable storage medium of claim 10 , wherein the characteristic is an emotion corresponding to a state of boredom, tiredness, excitement, interest, anger, disgust, fear, happiness, sadness, surprise, or apathy, of the participant.
13. A non-transitory machine-readable storage medium comprising instructions executable by a processing resource of a computing device to cause the computing device to:
receive a video feed for each of a set of participants in a video conference;
determine probabilities of characteristics being experienced by the set of participants in the video conference, wherein a distinct probability is determined for each participant of the set of participants;
determine a list of characteristics based on the probabilities and a threshold value;
determine a relevancy score for each of the set of participants in the video conference based on the probabilities and the threshold value;
sort the list of characteristics and the set of participants based on the probabilities and the relevancy scores; and
display a set of characteristics and the set of participants based on the sorted list of characteristics.
14. The non-transitory machine-readable storage medium of claim 13 , wherein the characteristic is selected from the group consisting of: an emotion and a level of engagement.
15. The non-transitory machine-readable storage medium of claim 13 , wherein the characteristic is an emotion corresponding to a state of boredom, tiredness, excitement, interest, anger, disgust, fear, happiness, sadness, surprise, or apathy, of a participant.
16. The non-transitory machine-readable storage medium of claim 13 , wherein the instructions further cause the computing device to receive a selection of a characteristic from the set of characteristics.
17. The non-transitory machine-readable storage medium of claim 16 , wherein the instructions further cause the computing device to display the set of participants in an order based upon the selection.
18. The non-transitory machine-readable storage medium of claim 13 , wherein the instructions further cause the computing device to display a characteristic of the sorted list corresponding to a characteristic most likely being experienced by the largest number of participants in the video conference.
19. The non-transitory machine-readable storage medium of claim 13 , wherein the instructions further cause the computing device to display a characteristic occurring most frequently in the sorted list.