works on
audio description 1multimodal QA 1narrative grounding 1training-free methods 1video-language models 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CV2026

StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description

Seung Hyun Hahm, Minh T. Dinh, SouYoung Jin

StoryTeller is a training‑free framework that adds a persistent narrative memory to video‑language models so they can generate coherent, story‑aware audio descriptions for long vid…