This research work proposes an enriched human perception-based distributed architecture for the multi-party video conferencing services. Rich theoretical models of the three different architectures: the proposed perception-based distributed architecture, the conventional centralized architecture and perception-based centralized architecture have been constructed by using queuing theory to reflect the traffic generated, transmitted and processed on all three architectures. The performance of these three different architectures has been considered in different aspects from the total waiting time, the point- to-point delay and the required service rates to the total throughput. Together, the modelling tools, the analysis, and the numerical results help to answer the common concern about advantages and disadvantages between the centralized and distributed architectures for the video conferencing service architecture