Research map / Video / Video generation
CelebV-Text: A Large-Scale Facial Text-Video Dataset
Jianhui Yu, Hao Zhu, Liming Jiang, Chen Change Loy, Weidong Cai, Wayne Wu
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 |
|---|---|---|---|
| Use test-time text interpolation | MMVID · CelebV-Text, App.+Emo. | FVD: 82.78 ± 1.47 -> 72.87 ± 1.23 | Improved |
| Use test-time text interpolation | MMVID · CelebV-Text, App.+Emo. | FID: 61.58 ± 3.99 -> 41.57 ± 3.56 | Improved |
| Use test-time text interpolation | MMVID · CelebV-Text, App.+Emo. | CLIPSIM: 0.176 ± 0.008 -> 0.182 ± 0.010 | Improved |
| Use test-time text interpolation | MMVID · CelebV-Text, App.+Act. | FVD: 109.25 ± 2.11 -> 80.81 ± 2.55 | Improved |
| Use test-time text interpolation | MMVID · CelebV-Text, App.+Act. | FID: 82.55 ± 4.37 -> 70.88 ± 4.77 | Improved |
| Use test-time text interpolation | MMVID · CelebV-Text, App.+Act. | CLIPSIM: 0.174 ± 0.019 -> 0.176 ± 0.020 | Improved |
| Add dynamic-state descriptions to appearance descriptions | MMVID trained on CelebV-Text · CelebV-Text, dynamic descriptions | video quality | Hurt |
Closest papers by meaning
- OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation (ICLR 2025 · similarity 0.85)
- T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation (CVPR 2025 · similarity 0.84)
- A Recipe for Scaling up Text-to-Video Generation with Text-free Videos (CVPR 2024 · similarity 0.84)
- Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers (CVPR 2024 · similarity 0.84)
- VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation (NeurIPS 2025 · similarity 0.84)
- MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation (CVPR 2024 · 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.
