Research map / Video / Video-language understanding
Event Video Mashup: From Hundreds of Videos to Minutes of Skeleton
Lianli Gao, Peng Wang, Jingkuan Song, Zi Huang, Jie Shao, Heng Shen
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 |
|---|---|---|---|
| EVM instead of Near-Duplicate detection (ND) | shot clique selection · Average over 8 events | precision: 0.73 -> 0.86 | Improved |
| EVM instead of ND | shot clique selection · Average over 8 events | recall: 0.59 -> 0.82 | Improved |
| EVM instead of Sparse Dictionary Selection (DS) | shot clique selection · Average over 8 events | precision: 0.48 -> 0.86 | Improved |
| EVM instead of DS | shot clique selection · Average over 8 events | recall: 0.42 -> 0.82 | Improved |
| ND instead of DS | baseline selection · Average over 8 events | precision: 0.48 -> 0.73 | Improved |
| EVM instead of DS | shot clique selection · Event #4 Michael Jackson Death | precision: 0.76 -> 0.90 | Mixed |
| combine semantic meaning and frequency (EVM vs ND) in mashup | video mashup · User study | Q1 information coverage: 0.74 -> 0.85 | Improved |
| EVM instead of ND | video mashup · User study | Q2 conciseness: 0.68 -> 0.81 | Improved |
| EVM instead of ND | video mashup · User study | Q3 subevent discovery: 0.42 -> 0.70 | Improved |
| EVM instead of ND | video mashup · User study | Q4 visualization pleasing: 0.69 -> 0.81 | Improved |
| abstract event facets such as hoax or truth | EVM · Michael Jackson Death / September 11 | summary quality | Hurt |
| longer, more complex events | semantic inference · Boston Marathon Bombings vs Academy Awards | # shot cliques with semantic meaning: 81 -> 204 | Improved |
Closest papers by meaning
- VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation (NeurIPS 2025 · similarity 0.85)
- Beyond Grounding: Extracting Fine-Grained Event Hierarchies across Modalities (AAAI 2024 · similarity 0.85)
- MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval (CVPR 2025 · similarity 0.84)
- VidEvent: A Large Dataset for Understanding Dynamic Evolution of Events in Videos (AAAI 2025 · similarity 0.84)
- Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark (AAAI 2025 · similarity 0.84)
- Mind the Time: Temporally-Controlled Multi-Event Video Generation (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.
