Research map / Video / Video segmentation and tracking
Submodular Span, with Applications to Conditional Data Summarization
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 S3 instead of MixModSub | Conditional MDS · DUC 2005 | ROUGE-1 F: 38.17 -> 38.20 | No clear effect |
| Use S3 instead of MixModSub | Conditional MDS · DUC 2005 | ROUGE-2 F: 7.65 -> 7.52 | Hurt |
| Use S3 instead of MixModSub | Conditional MDS · DUC 2005 | ROUGE-SU4 F: 13.49 -> 13.37 | No clear effect |
| Use S3 instead of Dual-CES | Conditional MDS · DUC 2006 | ROUGE-1 F: 41.23 -> 40.95 | Hurt |
| Use S3 instead of Dual-CES | Conditional MDS · DUC 2006 | ROUGE-2 F: 9.47 -> 9.20 | Hurt |
| Use S3 instead of Dual-CES | Conditional MDS · DUC 2007 | ROUGE-1 F: 43.24 -> 42.32 | Hurt |
| Use S3 instead of Dual-CES | Conditional MDS · DUC 2007 | ROUGE-2 F: 11.78 -> 11.07 | Hurt |
| Use S3 instead of HVN | Query-focused video summarization · UT-Egocentric Video-1 | F1 score: 51.45 -> 52.18 | Helped |
| Use S3 instead of HVN | Query-focused video summarization · UT-Egocentric Video-2 | F1 score: 47.49 -> 46.71 | Hurt |
| Use S3 instead of HVN | Query-focused video summarization · UT-Egocentric Video-3 | F1 score: 61.08 -> 62.66 | Helped |
| Use S3 instead of HVN | Query-focused video summarization · UT-Egocentric Video-4 | F1 score: 35.47 -> 34.97 | Hurt |
| Use S3 instead of HVN | Query-focused video summarization · UT-Egocentric average | F1 score: 48.87 -> 49.13 | Helped |
Closest papers by meaning
- Data Summarization at Scale: A Two-Stage Submodular Approach (ICML 2018 · similarity 0.89)
- Fast Constrained Submodular Maximization: Personalized Data Summarization (ICML 2016 · similarity 0.85)
- Learning Sparse Combinatorial Representations via Two-stage Submodular Maximization (ICML 2016 · similarity 0.85)
- V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning (AAAI 2025 · similarity 0.83)
- Video Summarization Using Denoising Diffusion Probabilistic Model (AAAI 2025 · similarity 0.83)
- DIUSum: Dynamic Image Utilization for Multimodal Summarization (AAAI 2024 · similarity 0.83)
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.