Research map / Video / Video generation
Learning Dynamic Generator Model by Alternating Back-Propagation through Time
Read the paperCheck 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 the dynamic generator instead of MoCoGAN or TGAN | Video generation on UCF101 · UCF101, 9 selected classes | Inception score: 4.40±0.04 -> 8.21±0.09; 5.48±0.06 -> 8.21±0.09 | Helped |
| Use the dynamic generator instead of STGCN for single-region mask recovery | Video recovery · DynTex++ single-region masks, Avg. | recovery error: 5.7068 vs 6.2681 | Helped |
| Use the dynamic generator instead of MRF-ℓ1 or MRF-ℓ2 for single-region mask recovery | Video recovery · DynTex++ single-region masks, Avg. | recovery error: 5.7068 vs 11.7722; 5.7068 vs 12.6177 | Helped |
| Use the dynamic generator instead of STGCN for missing-frame recovery | Video recovery · DynTex++ 50% missing frames, Avg. | recovery error: 5.0454 vs 6.3791 | Helped |
| Use the dynamic generator instead of MRF-ℓ1 or MRF-ℓ2 for missing-frame recovery | Video recovery · DynTex++ 50% missing frames, Avg. | recovery error: 5.0454 vs 14.7272; 5.0454 vs 13.2065 | Helped |
| Use the dynamic generator instead of other baselines for dynamic texture synthesis | Dynamic texture generation · 12 dynamic texture videos | human fooling rate | Helped |
Closest papers by meaning
- Generative Image Dynamics (CVPR 2024 · similarity 0.87)
- Generative Pre-trained Autoregressive Diffusion Transformer (NeurIPS 2025 · similarity 0.85)
- Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series (NeurIPS 2024 · similarity 0.85)
- Autoregressive Video Generation without Vector Quantization (ICLR 2025 · similarity 0.85)
- Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation (CVPR 2024 · similarity 0.85)
- TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models (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.