Research map / Graph learning / Graph algorithms and clustering
Movie Summarization via Sparse Graph Construction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use GraphTP with audiovisual information instead of text-only GraphTP (ablation) | GraphTP · TRIPOD | TA: 6.76 -> 9.12 | Helped |
| Use GraphTP with audiovisual information instead of text-only GraphTP (ablation) | GraphTP · TRIPOD | PA: 10.00 -> 12.63 | Helped |
| Use GraphTP with audiovisual information instead of text-only GraphTP (ablation) | GraphTP · TRIPOD | D: 9.62 -> 9.77 | Hurt |
| Replace the learned sparse graph with a fully connected graph (ablation) | GraphTP · TRIPOD | TA: 9.12 -> 5.00 | Hurt |
| Remove graph interactions and use scene content only (ablation) | GraphTP · TRIPOD | TA: 9.12 -> 5.59 | Hurt |
| Remove scene content and retain neighborhood interactions plus position (ablation) | GraphTP · TRIPOD | TA: 6.76 -> 9.71 | Helped |
| Remove scene content and retain neighborhood interactions plus position (ablation) | GraphTP · TRIPOD | D: 9.62 -> 10.98 | Hurt |
| Add visual features alone (ablation) | GraphTP · TRIPOD | TA: 6.76 -> 6.18 | Hurt |
| Add audio features alone (ablation) | GraphTP · TRIPOD | TA: 6.76 -> 7.06 | Helped |
| Use GraphTP rather than TAM with audiovisual information | TP identification · TRIPOD | TA: 7.36 -> 9.12 | Helped |
| Use GraphTP rather than TextRank | TP identification · TRIPOD | D: 17.77 -> 9.62 | Helped |
Closest papers by meaning
- A Closer Look at Dynamic Scene Graph Generation in the Era of Multimodal Large Language Models (NeurIPS 2026 · similarity 0.84)
- MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation (CVPR 2025 · similarity 0.83)
- Video Summarization with Large Language Models (CVPR 2025 · similarity 0.83)
- Previously on ... From Recaps to Story Summarization (CVPR 2024 · similarity 0.83)
- Fine-Grained Captioning of Long Videos through Scene Graph Consolidation (ICML 2025 · similarity 0.83)
- CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation (NeurIPS 2025 · similarity 0.82)
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.