Research map / Video / Video segmentation and tracking
Video Prediction with Appearance and Motion Conditions
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 appearance and motion conditions with AMC-GAN instead of the compared video-prediction baselines | Video prediction · MUG | accuracy: 43.22 -> 99.79 | Helped |
| Use appearance and motion conditions with AMC-GAN instead of the compared video-prediction baselines | Video prediction · NATOPS | accuracy: 12.76 -> 91.12 | Helped |
| Add an appearance condition (ablation) | AMC-GAN · NATOPS | accuracy: 4.75 -> 91.12 | Helped |
| Add a motion condition (ablation) | AMC-GAN · NATOPS | accuracy: 7.62 -> 91.12 | Helped |
| Use appearance and motion conditions instead of random noise alone (ablation) | AMC-GAN · NATOPS | accuracy: 5.52 -> 91.12 | Helped |
| Add mismatched conditions y' to the conditioning scheme (ablation) | AMC-GAN · NATOPS | accuracy: 86.80 -> 91.12 | Helped |
| Add the appearance discriminator (ablation) | AMC-GAN · NATOPS | accuracy: 85.97 -> 91.12 | Helped |
| Add the motion discriminator (ablation) | AMC-GAN · NATOPS | accuracy: 79.23 -> 91.12 | Helped |
| Add the discriminator auxiliary loss (ablation) | AMC-GAN · NATOPS | accuracy: 81.05 -> 91.12 | Helped |
| Add the generator auxiliary loss (ablation) | AMC-GAN · NATOPS | accuracy: 88.29 -> 91.12 | Helped |
| Add the perceptual ranking loss (ablation) | AMC-GAN · NATOPS | accuracy: 90.83 -> 91.12 | Helped |
| Add the perceptual ranking loss (ablation) | AMC-GAN · Video generation | visual quality | Helped |
Closest papers by meaning
- Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency (CVPR 2021 · similarity 0.90)
- Anticipating Visual Representations From Unlabeled Video (CVPR 2016 · similarity 0.87)
- G3AN: Disentangling Appearance and Motion for Video Generation (CVPR 2020 · similarity 0.86)
- Predicting Future Frames Using Retrospective Cycle GAN (CVPR 2019 · similarity 0.86)
- VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models (ICML 2025 · similarity 0.85)
- FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations (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.