Research map / Video / Video segmentation and tracking
Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization
Jungin Park, Jiyoung Lee, Kwanghoon Sohn
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 |
|---|---|---|---|
| add sentence-level language query to the temporal graph model (SumGraph) (ablation) | SumGraph · SumMe | F-score: 51.4 -> 55.8 | Improved |
| add sentence-level language query to the temporal graph model (SumGraph) (ablation) | SumGraph · TVSum | F-score: 63.9 -> 67.1 | Improved |
| add spatial object graph to temporal graph model (ablation) | VideoGraph without language · SumMe | F-score: 51.4 -> 54.7 | Improved |
| add spatial object graph to temporal graph model (ablation) | VideoGraph without language · TVSum | F-score: 63.9 -> 65.2 | Improved |
| add temporal graph to spatial-only model (ablation) | VideoGraph without language · SumMe | F-score: 45.2 -> 54.7 | Improved |
| add language query to full temporal+spatial graph (ablation) | VideoGraph · SumMe | F-score: 54.7 -> 58.1 | Improved |
| add language query to full temporal+spatial graph (ablation) | VideoGraph · TVSum | F-score: 65.2 -> 69.5 | Improved |
| add temporal graph to spatial+language model (ablation) | VideoGraph · QFVS | F-score avg: 57.33 -> 71.29 | Improved |
| add sparsity loss to classification loss (ablation) | VideoGraph · TVSum | F-score: 65.4 -> 67.8 | Improved |
| add diversity and reconstruction losses to classification loss (ablation) | VideoGraph · TVSum | F-score: 65.4 -> 67.5 | Improved |
| use all four losses instead of classification only (ablation) | VideoGraph · TVSum | F-score: 65.4 -> 69.5 | Improved |
| word-level query instead of sentence-level query | VideoGraph supervised · SumMe | F-score: 57.0 -> 58.1 | Improved |
Closest papers by meaning
- SumGraph: Video Summarization via Recursive Graph Modeling (ECCV 2020 · similarity 0.96)
- Language-Guided Graph Representation Learning for Video Summarization (TPAMI 2025 · similarity 0.93)
- Contextual Correspondence Matters: Bidirectional Graph Matching for Video Summarization (ECCV 2024 · similarity 0.91)
- Reconstructive Sequence-Graph Network for Video Summarization (TPAMI 2021 · similarity 0.90)
- Video Summarization with Large Language Models (CVPR 2025 · similarity 0.87)
- Fine-Grained Captioning of Long Videos through Scene Graph Consolidation (ICML 2025 · similarity 0.87)
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.
