Research map / Video / Video segmentation and tracking
Contrastive Learning for Unsupervised Video Highlight Detection
Taivanbat Badamdorj, Mrigank Rochan, Yang Wang, Li Cheng
Check 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 dropout perturbations to the contrastive learning framework (ablation) | video highlight selector · YouTube Highlights | mAP: 0.6287 -> 0.6539 | Improved |
| add dropout perturbations to the contrastive learning framework (ablation) | video highlight selector · TVSum | top-5 mAP: 0.4887 -> 0.5276 | Improved |
| add dropout perturbations to the contrastive learning framework (ablation) | video highlight selector · VTW | mAP: 0.5606 -> 0.6090 | Improved |
| select highlight clips rather than non-highlight clips for video embeddings (ablation) | contrastive video representation · YouTube Highlights | intra-cluster distance: 0.0954 -> 0.0888 | Improved |
| select highlight clips rather than non-highlight clips for video embeddings (ablation) | contrastive video representation · YouTube Highlights | inter-cluster distance: 0.2325 -> 0.2597 | Improved |
Closest papers by meaning
- Less Is More: Learning Highlight Detection From Video Duration (CVPR 2019 · similarity 0.92)
- Cross-Category Video Highlight Detection via Set-Based Learning (ICCV 2021 · similarity 0.92)
- Adaptive Video Highlight Detection by Learning from User History (ECCV 2020 · similarity 0.91)
- Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection (CVPR 2024 · similarity 0.89)
- Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection (AAAI 2025 · similarity 0.87)
- Exploring Domain Incremental Video Highlights Detection with the LiveFood Benchmark (AAAI 2024 · similarity 0.86)
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.
