Participant selection bias for a video conferencing display layout based on gaze tracking

One or more non-transitory tangible media that includes code for execution and when executed by a processor is operable to perform operations comprising:

• presenting to a user a display layout associated with a video conferencing session, the display layout comprising a plurality of images of participants in the video conferencing session, wherein each of the participants is assigned to a layout category, wherein the display layout comprises at least one primary pane and an M number of secondary panes in which the images are presented;
• accumulating gaze tracking information indicative of an amount of time the user has spent looking at the image of a first one of the participants relative to the images of other ones of the participants;
• assigning a measure of interest (“MOI”) to the first one of the participants based on the accumulated gaze tracking information;
• determining whether the assigned MOI meets a first threshold value;
• if the assigned MOI meets the first threshold value, updating the layout category to which the first one of the participants is assigned;
• and
• updating the display layout using the updated layout category to which the first one of the participants is assigned, wherein each of the participants has an MOI associated therewith, the updating the display layout further comprising:
• presenting in the at least one primary pane an image of a current speaker in the video conferencing session;
• presenting in the secondary panes images of participants who are the most recent N speakers in the video conferencing session, where N<M, and (M-N) images of participants in the video conferencing session who have MOIs meeting the first threshold value and who are prior speakers and are not the most recent N speakers;
• and
• removing from the display layout an image of a participant in the video conferencing session who has an MOI that does not meet the first threshold value and who is not one of the most recent N speakers.

An apparatus comprising:

• a memory element configured to store data;
• and
• a processor operable to execute instructions associated with the data, wherein the processor is configured to:
• present to a user a display layout associated with a video conferencing session, the display layout comprising a plurality of images of participants in the video conferencing session, wherein each of the participants is assigned to a layout category, wherein the display layout comprises at least one primary pane and an M number of secondary panes in which the images are presented;
• accumulate gaze tracking information indicative of an amount of time the user has spent looking at the image of a first one of the participants relative to the images of other ones of the participants;
• assign a measure of interest (“MOI”) to the first one of the participants based on the accumulated gaze tracking information;
• determine whether the assigned MOI meets a first threshold value;
• if the assigned MOI meets the first threshold value, update the layout category to which the first one of the participants is assigned;
• and
• update the display layout using the updated layout category to which the first one of the participants is assigned, wherein each of the participants has an MOI associated therewith, by:
• presenting in the at least one primary pane an image of a current speaker in the video conferencing session;
• presenting in the secondary panes images of participants who are the most recent N speakers in the video conferencing session, where N<M, and (M-N) images of participants in the video conferencing session who have MOIs meeting the first threshold value and who are prior speakers and are not the most recent N speakers;
• and
• removing from the display layout an image of a participant in the video conferencing session who has an MOI that does not meet the first threshold value and who is not one of the most recent N speakers.