Research map / Video / Video generation
Video2GIF: Automatic Generation of Animated GIFs From Video
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 within-video ranking instead of classification (ablation) | Video2GIF RankNet · Video2GIF test set | nMSD: 61.37% -> 44.19% | Helped |
| Use within-video rather than video-agnostic comparisons (ablation) | Video2GIF RankNet · Video2GIF test set | nMSD: 53.71% -> 44.19% | Helped |
| Use a Huber ranking loss rather than l1 loss (ablation) | Video2GIF RankNet · Video2GIF test set | mAP: 16.09% -> 16.22% | Helped |
| Use a Huber ranking loss rather than l2 loss (ablation) | Video2GIF RankNet · Video2GIF test set | mAP: 16.10% -> 16.22% | Helped |
| Make the Huber threshold adaptive to GIF popularity (ablation) | Video2GIF RankNet · Video2GIF test set | nMSD: 44.43% -> 44.58% | Hurt |
| Add contextual category, tag and positional features (ablation) | Video2GIF RankNet · Video2GIF test set | nMSD: 44.58% -> 44.19% | Helped |
| Add contextual category, tag and positional features (ablation) | Video2GIF RankNet · Video2GIF test set | mAP: 16.21% -> 16.18% | No clear effect |
| Add model averaging (ablation) | Video2GIF RankNet · Video2GIF test set | nMSD: 44.19% -> 44.08% | Helped |
| Train the global GIF-suitability model and transfer it to highlight detection | Video2GIF · Highlight dataset, total | mAP: 37.9% -> 46.4% | Helped |
| Train one global GIF-suitability model rather than category-specific models directly on the target data | Video2GIF · Highlight dataset, total | mAP: 46.4% -> 53.6% | Hurt |
Closest papers by meaning
- StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text (CVPR 2025 · similarity 0.85)
- VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation (NeurIPS 2025 · similarity 0.84)
- SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction (ICLR 2024 · similarity 0.84)
- Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark (AAAI 2025 · similarity 0.83)
- Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis (CVPR 2024 · similarity 0.83)
- LongDiff: Training-Free Long Video Generation in One Go (CVPR 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.