AI Paper Atlas

Research map / Video / Video-language understanding

From Script to Shot: A Benchmark for Grounding Screenplays in Movies

jungu cho, Young-Jae Park, Seong Jong Ha, Siyeol Kim, Seungho Park, Jisu Shin, Junmyeong Lee, Chaemin Hwang, Hyunjun Jung, Sangeyl Lee, Hae-Gon Jeon

ECCV 2026 · Video › Video-language understanding · approach: Video-language pretraining · 0 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
fuse BM25 dialogue matching with CLIP visual similarityCLIP · Script-to-Shot benchmark (50 films)mSIoU: 0.252 -> 0.531Improved
fuse Qwen3-VL-Embedding with BM25BM25 · Script-to-Shot benchmark (50 films)mSIoU: 0.399 -> 0.599Improved
fuse BM25 with CLIP, non-dialogue scenesCLIP · Script-to-Shot benchmark (50 films)IoU non-dialogue: 0.252 -> 0.403Improved
fuse CLIP with BM25, dialogue scenesBM25 · Script-to-Shot benchmark (50 films)IoU dialogue: 0.505 -> 0.597Improved
fuse Qwen3-VL-Embedding with BM25 over Qwen3-VL-Embedding aloneQwen3-VL-Embedding · Script-to-Shot benchmark (50 films)mSIoU: 0.500 -> 0.599Improved
increase fusion weight alpha from 0.5 to 0.7 for Qwen3-VL-EmbeddingFusion Qwen3-VL-Emb.+BM25 · Script-to-Shot benchmark (50 films)mSIoU: 0.591 -> 0.599Improved
use Qwen3-VL-Embedding instead of CLIP as visual encoderVisual retrieval · Script-to-Shot benchmark (50 films)mSIoU: 0.252 -> 0.500Improved
use SigLIP as visual encoder instead of CLIPVisual retrieval · Script-to-Shot benchmark (50 films)mSIoU: 0.252 -> 0.023Hurt
use TAN or MATR temporal grounding instead of T-MASSTemporal grounding · Script-to-Shot benchmark (50 films)mSIoU: 0.130 -> 0.009Hurt
use BM25 instead of M/S dialogue matchingDialogue retrieval · Script-to-Shot benchmark (50 films)mSIoU: 0.324 -> 0.399Improved
use TF-IDF instead of BM25Dialogue retrieval · Script-to-Shot benchmark (50 films)mSIoU: 0.399 -> 0.396No clear effect

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