Research map / Video / Video segmentation and tracking
Summary Transfer: Exemplar-Based Subset Selection for Video Summarization
Check 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 |
|---|---|---|---|
| Transfer summary structures nonparametrically from annotated videos | Ours · Kodak | F-score: 78.9 -> 82.3 | Helped |
| Transfer summary structures nonparametrically from annotated videos | Ours · OVP | F-score: 77.7 -> 76.5 | Hurt |
| Transfer summary structures nonparametrically from annotated videos | Ours · YouTube | F-score: 60.8 -> 61.8 | Helped |
| Transfer summary structures nonparametrically from annotated videos | Ours · MED | F-score: 28.9 -> 30.7 | Helped |
| Transfer summary structures nonparametrically from annotated videos | Ours · SumMe | F-score: 39.7 -> 40.9 | Helped |
| Add hard category-specific transfer (ablation) | Ours · YouTube | F-score: 60.0 -> 61.5 | Helped |
| Add soft category-specific transfer (ablation) | Ours · YouTube | F-score: 60.0 -> 60.6 | Helped |
| Add hard category-specific transfer (ablation) | Ours · MED | F-score: 28.9 -> 30.4 | Helped |
| Add soft category-specific transfer (ablation) | Ours · MED | F-score: 28.9 -> 30.7 | Helped |
| Add hard category-specific transfer (ablation) | Ours · SumMe | F-score: 39.2 -> 40.9 | Helped |
| Add soft category-specific transfer (ablation) | Ours · SumMe | F-score: 39.2 -> 40.2 | Helped |
| Use subshot-level rather than frame-level similarity (ablation) | Ours · YouTube, no category prior | F-score: 60.0 -> 60.7 (mean-feature); 60.0 -> 60.9 (max-similarity) | Helped |
Closest papers by meaning
- Video Summarization with Large Language Models (CVPR 2025 · similarity 0.88)
- Video Summarization Using Denoising Diffusion Probabilistic Model (AAAI 2025 · similarity 0.86)
- Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark (AAAI 2025 · similarity 0.86)
- V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning (AAAI 2025 · similarity 0.86)
- Scaling Up Video Summarization Pretraining with Large Language Models (CVPR 2024 · similarity 0.86)
- Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos (ICLR 2025 · similarity 0.85)
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.