R2E-VID uses temporal gating to predict routing patterns and robust optimization to allocate video inference between edge and cloud, reporting up to 60% cost reduction, 35-45% lower delay, and 2-7% higher accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.NI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
R2E-VID: Two-Stage Robust Routing via Temporal Gating for Elastic Edge-Cloud Video Inference
R2E-VID uses temporal gating to predict routing patterns and robust optimization to allocate video inference between edge and cloud, reporting up to 60% cost reduction, 35-45% lower delay, and 2-7% higher accuracy.