AI Paper Atlas

Research map / Video / Video-language understanding

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

Seung Hahm, Minh Dinh, SouYoung Jin

ECCV 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add structured fact extraction, identity, verification and memory over VLM-only narration (ablation)Qwen3-VL narration · MAD-EvalCIDEr: 11.4 -> 21.4Improved
use structured facts instead of scene summaries (ablation)StoryTeller · MAD-EvalCIDEr: 15.4 -> 21.4Improved
add cross-clip narrative memory (ablation)StoryTeller · MAD-EvalCIDEr: 18.0 -> 21.4Improved
add persistent identity graph (ablation)StoryTeller · MAD-EvalCIDEr: 17.9 -> 21.4Improved
add public IMDb metadata retrieval (ablation)StoryTeller · MAD-EvalSPICE: 4.8 -> 6.7Improved
add narrative memory on StoryAD-QA Track A 240s (ablation)StoryTeller · StoryAD-QA Track A (240)accuracy: 0.891 -> 0.972Improved
add components over VLM-only on short segments (Track A 30s) (ablation)StoryTeller · StoryAD-QA Track A (30)accuracy: 0.908 -> 0.892No clear effect
add identity graph on Track B 30+30 (ablation)StoryTeller · StoryAD-QA Track B (30+30)accuracy: 0.794 -> 0.754No clear effect
use StoryTeller instead of AutoAD-Zero on Track B 90+30AutoAD-Zero · StoryAD-QA Track B (90+30)accuracy: 0.673 -> 0.788Improved
use StoryTeller instead of AutoAD-Zero on Track A 30sAutoAD-Zero · StoryAD-QA Track A (30)accuracy: 0.840 -> 0.892Improved
use StoryTeller (VideoLLaMA2) instead of AutoAD-Zero on MAD-EvalAutoAD-Zero · MAD-EvalCIDEr: 22.4 -> 19.1 (CIDEr); SPICE 7.3 -> 9.0; ROUGE-L 14.4 -> 16.0Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy