StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description
Long-form audio description (AD) requires more than describing visible actions: it must preserve characters, events, relationships, and story context across scenes so that blind and low-vision (BLV) audiences can follow a film. Modern video-language models (VLMs) are effective on short clips, but they often treat each moment independently, producing descriptions that miss who characters are, why events matter, and how the current scene connects to earlier narrative context. We propose StoryTeller, a training-free framework for story-aware long-form AD. Instead of relying only on local visual c
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%VioletVision-3B →
- PossiblePossibly related (embedding) · 51%linyqh/NarratoAI →
- PossiblePossibly related (embedding) · 50%worldwonderer/video-recap-skills →
- PossiblePossibly related (embedding) · 49%modelscope/FunClip →
- PossiblePossibly related (embedding) · 48%HKUSTDial/DataMagic →
- FuzzyOverlapping authors or contributors · 62%HKUDS/LightRAG →
“Shared author/contributor keys: jin”
- FuzzyOverlapping authors or contributors · 62%keras-team/keras →
“Shared author/contributor keys: jin”
- LinkedLinked via arxiv author · 85%Seung Hyun Hahm →
“StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description”