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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| fuse BM25 dialogue matching with CLIP visual similarity | CLIP · Script-to-Shot benchmark (50 films) | mSIoU: 0.252 -> 0.531 | Improved |
| fuse Qwen3-VL-Embedding with BM25 | BM25 · Script-to-Shot benchmark (50 films) | mSIoU: 0.399 -> 0.599 | Improved |
| fuse BM25 with CLIP, non-dialogue scenes | CLIP · Script-to-Shot benchmark (50 films) | IoU non-dialogue: 0.252 -> 0.403 | Improved |
| fuse CLIP with BM25, dialogue scenes | BM25 · Script-to-Shot benchmark (50 films) | IoU dialogue: 0.505 -> 0.597 | Improved |
| fuse Qwen3-VL-Embedding with BM25 over Qwen3-VL-Embedding alone | Qwen3-VL-Embedding · Script-to-Shot benchmark (50 films) | mSIoU: 0.500 -> 0.599 | Improved |
| increase fusion weight alpha from 0.5 to 0.7 for Qwen3-VL-Embedding | Fusion Qwen3-VL-Emb.+BM25 · Script-to-Shot benchmark (50 films) | mSIoU: 0.591 -> 0.599 | Improved |
| use Qwen3-VL-Embedding instead of CLIP as visual encoder | Visual retrieval · Script-to-Shot benchmark (50 films) | mSIoU: 0.252 -> 0.500 | Improved |
| use SigLIP as visual encoder instead of CLIP | Visual retrieval · Script-to-Shot benchmark (50 films) | mSIoU: 0.252 -> 0.023 | Hurt |
| use TAN or MATR temporal grounding instead of T-MASS | Temporal grounding · Script-to-Shot benchmark (50 films) | mSIoU: 0.130 -> 0.009 | Hurt |
| use BM25 instead of M/S dialogue matching | Dialogue retrieval · Script-to-Shot benchmark (50 films) | mSIoU: 0.324 -> 0.399 | Improved |
| use TF-IDF instead of BM25 | Dialogue retrieval · Script-to-Shot benchmark (50 films) | mSIoU: 0.399 -> 0.396 | No 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.
- DiffusionRet — DiffusionRet: Generative Text-Video Retrieval with Diffusion Model (ICCV 2023) · better on 2 of 2 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
- CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation (NeurIPS 2025 · similarity 0.87)
- ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models (NeurIPS 2025 · similarity 0.86)
- Unveiling the Value of Motion for Cinematic Camera Trajectories (NeurIPS 2026 · similarity 0.86)
- VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models (CVPR 2025 · similarity 0.85)
- ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing (NeurIPS 2026 · similarity 0.85)
- Progress-Aware Video Frame Captioning (CVPR 2025 · similarity 0.84)
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.
