Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding
Paper recorded by Signals 4 on 2026-09-10 in cs.CV. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-10 on arXiv · recorded by Signals 4 on 2026-09-11
Category: cs.CV · 计算机视觉 · first seen 2026-09-11
Abstract
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-le
Read on arXiv →
Cite this page: Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding: the #80 most recent of 237 cs.CV papers we have recorded (as of 2026-09-10). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/caption-once-frames-on-demand-visual-need-routing-for-budget-aware-agentic-long-.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free