Research map / Video / Video segmentation and tracking
Highlight Detection With Pairwise Deep Ranking for First-Person 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 |
|---|---|---|---|
| Use pairwise deep ranking with two-stream late fusion instead of LR+IDT | First-person video highlight detection · First-person video test set | mAP: 10.5% | Helped |
| Fuse spatial and temporal DCNN scores (ablation) | TS-DCNN · First-person sports videos | mAP | Helped |
| Use temporal DCNN alone instead of spatial DCNN alone (ablation) | Highlight detection · First-person sports videos | mAP | Helped |
| Set late-fusion weight near ω = 0.3 (ablation) | TS-DCNN · First-person video test set | mAP | Helped |
| Generate a timelapse using highlight scores | First-person video summaries · User study vs UNI, IMP [21], and INT [6] | user preference for coverage and presentation: 91.4%; 80.1%; 74.3% (Coverage); 85.7%; 60.2%; 64.8% (Presentation) | Helped |
| Select highlight-scored segments for video skimming | First-person video summaries · User study vs UNI, IMP [21], and INT [6] | user preference for coverage and presentation: 87.2%; 77.1%; 71.4% (Coverage); 88.6%; 74.3%; 82.9% (Presentation) | Helped |
Closest papers by meaning
- Mr. HiSum: A Large-scale Dataset for Video Highlight Detection and Summarization (NeurIPS 2023 · similarity 0.89)
- Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection (AAAI 2025 · similarity 0.85)
- Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection (CVPR 2024 · similarity 0.85)
- ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries (AAAI 2025 · similarity 0.84)
- Exploring Domain Incremental Video Highlights Detection with the LiveFood Benchmark (AAAI 2024 · similarity 0.83)
- Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark (AAAI 2025 · 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.