Abstract

Hybrid meeting platforms give remote attendees structured side-channel mechanisms—virtual hand raises, emoji reactions, poll responses—that are entirely absent for in-room participants, whose non-verbal behaviour remains visible only inside the physical room. This paper describes a bridging system that observes in-room participants through a shared room camera, detects a defined vocabulary of natural non-verbal signals (nodding, head-shaking, raised hands, and postural cues), and translates each qualified signal into a corresponding structured reaction event within the conferencing platform’s existing reaction model. The result is a unified reaction channel in which in-room and remote participants are represented with equivalent expressive bandwidth, without requiring any deliberate action by in-room attendees.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.

Download

Share

COinS