AI Paper Atlas

Research map / Video / Video-language understanding

Long Story Short: Story-level Video Understanding from 20K Short Films

Ridouane Ghermi, Xi Wang, Vicky S. Kalogeiton, Ivan Laptev

IJCV 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 25 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
give the movie title to the LLM (ablation)GPT-4 title-only · MovieQAaccuracy: 53.9 -> 71.3Improved
add character names (no anonymization) on top of title (ablation)GPT-4 title-only · MovieQAaccuracy: 31.4 -> 53.9Improved
give the movie title to the LLM (ablation)GPT-4 title-only · SF20K-Testaccuracy: 17.1 -> 18.3No clear effect
add character names to the question (ablation)GPT-4 title-only · SF20K-Testaccuracy: 15.9 -> 17.1No clear effect
replace the title with a random commercial titleLLM title-only · MovieQAaccuracy: 36.3 -> 20.3Hurt
replace the title with a random commercial titleLLM title-only · SF20K-Testaccuracy: 17.1 -> 8.5Hurt
replace the title with a random amateur titleLLM title-only · MovieQAaccuracy: 36.3 -> 32.0Hurt
replace the title with a random amateur titleLLM title-only · SF20K-Testaccuracy: 17.1 -> 16.7No clear effect
add subtitles and video frames to a single modality (ablation)GPT-5 · SF20K-Testaccuracy: 28.6 -> 56.2Improved
add video frames to language-only input (ablation)GPT-5 · SF20K-Testaccuracy: 37.7 -> 56.2Improved
increase frames from one to 128 (ablation)GPT-5 · SF20K-Testaccuracy: 39.6 -> 58.6Improved
enlarge temporal window from shot to scene (ablation)Qwen3-VL-8B · SF20K-Testaccuracy: 22.3 -> 25.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 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