The present disclosure relates to a system and method for monitoring audio-video (AV) streams transported over a network. The system may include at least one AV probe configured for installation at a network node. The at least one AV probe may be configured to receive an incoming AV stream at a native frame rate and to capture at least one thumbnail of the incoming AV stream at a sampling rate which is less than the native frame rate to form a thumbnail stream. The at least one AV probe may be further configured to timestamp and transmit the thumbnail stream, and to forward the incoming AV stream substantially in real-time. The system may further include at least one monitoring engine operatively connected with the at least one AV probe, the at least one monitoring engine configured to receive the thumbnail stream, capture AV data from the thumbnail stream, and transform the AV data into a visual representation of AV stream quality of experience (QoE).