Research map / Video / Video generation
VideoAuteur: Towards Long Narrative Video Generation
Junfei Xiao, Feng Cheng, Lu Qi, Liangke Gui, Yang Zhao, Shanchuan Lin, Jiepeng Cen, Zhibei Ma, Alan Yuille, Lu Jiang
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 |
|---|---|---|---|
| add cosine-similarity loss to MSE loss for visual embedding regression (ablation) | VideoAuteur director · CookGen validation | CLIP-T: 23.6 -> 25.1 | Improved |
| add cosine-similarity loss to MSE loss for visual embedding regression (ablation) | VideoAuteur director · CookGen validation | FID: 31.9 -> 30.1 | Improved |
| add MSE loss to cosine loss (ablation) | VideoAuteur director · CookGen validation | CLIP-T: 24.1 -> 25.1 | Improved |
| add the caption stage between actions and visual embeddings (ablation) | VideoAuteur director · HowTo100M subset validation | FID: 27.9 -> 25.3 | Improved |
| add the caption stage between actions and visual embeddings (ablation) | VideoAuteur director · HowTo100M subset validation | CLIP-T: 22.7 -> 26.1 | Improved |
| add the action stage before caption for the director (ablation) | VideoAuteur director · HowTo100M subset validation | FID: 26.1 -> 25.3 | Improved |
| add random masking to visual-condition training (ablation) | VideoAuteur video model · HowTo100M | FVD: 554.3 -> 539.7 | Improved |
| add Gaussian noise to the embeddings during training (ablation) | VideoAuteur video model · HowTo100M | FVD: 539.7 -> 522.1 | Improved |
| add random shuffling of embeddings (ablation) | VideoAuteur video model · HowTo100M | CLIP-T: 27.2 -> 27.3 | Improved |
| condition video generation on visual embeddings with regularization instead of keyframes | VideoAuteur video model · YouCook2 | FVD: 557.7 -> 512.6 | Improved |
| condition on visual embeddings without regularization instead of keyframes (ablation) | VideoAuteur video model · YouCook2 | CLIP-T: 25.9 -> 25.5 | Hurt |
| add rolling context conditioning to the keyframe renderer (ablation) | VideoAuteur · CookGen narrative keyframes | CLIP-T: 26.1 -> 28.0 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Vlogger — Vlogger: Make Your Dream A Vlog (CVPR 2024) · better on 3 of 3 shared results
- StoryDiffusion — StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation (NeurIPS 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation (CVPR 2025 · similarity 0.88)
- LVD-2M: A Long-take Video Dataset with Temporally Dense Captions (NeurIPS 2024 · similarity 0.88)
- MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation (CVPR 2025 · similarity 0.87)
- EvalCrafter: Benchmarking and Evaluating Large Video Generation Models (CVPR 2024 · similarity 0.87)
- Video-Bench: Human-Aligned Video Generation Benchmark (CVPR 2025 · similarity 0.86)
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · 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.
