SOURCE-LINKED INTELLIGENCE

Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Long-video understanding on edge devices must reason over hours of content under tight compute and bandwidth budgets. Subsampling visual tokens loses temporal structure, while text-only video memories lose fine-grained visual attributes. We observe a visual-textual duality: language memories carry long-range temporal structure better than dense frames, while pixels remain decisive for attribute-level perception. Building on this insight, we propose Caption-once, Frames-onDemand (CFD), a budget-aware edge-cloud agentic framework. The edge runs a single offline captioning pass that builds a dual

Read original source ↗ Open in workspace

recordType

paper

region

Global