During a video conference (VC), users often want to share information with other participants in the VC. For example, a user may refer verbally to concepts or show objects to the other participants. For example, a teacher in a video conference may hold up a book and request students to turn to a particular page. Currently, such actions interrupt the flow of presentation, since the presenting user is required to provide information such as URLs for the students to access. This disclosure describes techniques to automatically share within a video conference (VC) expanded information about concepts or objects referenced by a user within the VC. With specific user permission, image recognition is performed on the video stream of the VC to identify objects and/or speech recognition is performed to identify concepts in the user’s voice stream. Additional information about the recognized objects/concepts is made available to other participants in the VC.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Lewis, Peter; Lewis, Stephen; and Lewis, Andrew, "Automatically Augmenting Video Conference With Related Content Overlays", Technical Disclosure Commons, (August 28, 2020)