Research map / Video / Video segmentation and tracking
Video Prediction via Example Guidance
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 VPEG instead of SVG-LP | MovingMnist deterministic prediction · MovingMnist deterministic, T=17 | PSNR: 17.4 -> 19.3 | Helped |
| Use VPEG instead of DFN | MovingMnist stochastic prediction · MovingMnist stochastic, T=17 | PSNR: 14.3 -> 19.2 | Helped |
| Use VPEG instead of the strongest listed prior method | PennAction prediction · PennAction | Action Acc: 68.89 -> 73.23 | Helped |
| Use VPEG instead of the strongest listed prior method | PennAction prediction · PennAction | FVD: 1509.0 -> 1283.5 | Helped |
| Increase the retrieved example count from K=2 to K=5 (ablation) | VPEG · RobotPush | PSNR: 17.81 -> 18.35 | Helped |
| Increase the retrieved example count from K=2 to K=5 (ablation) | VPEG · RobotPush | SSIM: 0.78 -> 0.84 | Helped |
| Increase the retrieved example count beyond K=5 (ablation) | VPEG · RobotPush | PSNR: 18.35 -> 18.31 -> 18.25 | Hurt |
| Increase the retrieved example count from K=5 to K=7 (ablation) | VPEG · RobotPush | SSIM: 0.84 -> 0.83 | Hurt |
Closest papers by meaning
- Learning the Predictability of the Future (CVPR 2021 · similarity 0.88)
- Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations (ICML 2025 · similarity 0.86)
- PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning (ICML 2025 · similarity 0.86)
- Visual Representation Learning with Stochastic Frame Prediction (ICML 2024 · similarity 0.85)
- E-Motion: Future Motion Simulation via Event Sequence Diffusion (NeurIPS 2024 · similarity 0.85)
- Towards Understanding Future: Consistency Guided Probabilistic Modeling for Action Anticipation (AAAI 2024 · similarity 0.85)
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.