… We focus specifically on object detection in videos (applicable in many video analytics
scenarios) and show that the fused edge-cloud predictions can outperform the accuracy of edge-…

… They were largely derived from our experience in deploying a pilot video analytics
system in collaboration with two major US cities (one per coast), for road traffic monitoring. …

… video analytics system, which optimizes the workload between edge and cloud by taking into
account the characteristics of the video … and temporal events occurring in video streams (eg…

… , including tasks such as object detection, scene classification, and event recognition. … video
analytics, including the development of new algorithms and the integration of video analytics …

… these obstacles in current approaches, this paper introduces CONVINCE, a new approach
to look at the network cameras as a collective entity that enables collaborative video analytics …

… video analytics are two categories with very distinct requirements. In this paper, we focus on
online video analytics … , offline video analytics can also benefit from an online analysis to pre-…

… an efficient and scalable video-analytics approach to measure … -analysis techniques, to
analyze data gathered from in-store … event-specific hazard function as the probability that event A …

… We adopt a hybrid live video analytics architecture comprised of smart cameras, edge
servers and cloud (Figure 1), and primarily focus on video surveillance applications, eg, traffic …

… Video analytics plays a key role in smart cities and connected applications such as crowd
counting, activity detection, event classification, traffic counting, etc. With recent advances in …

… of the generic event model above), we adopt an event image (in short, emage) representation
approach. We consider user interest pattern regarding any topic or event of interest to be a …