Research map / Video / Video segmentation and tracking
Hierarchical Long-term Video Prediction without Supervision
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 EPVA instead of CDNA | Long-term prediction on bouncing shapes · Bouncing shapes, frames 1012–1022 | shape has correct color: 24.6% -> 96.9% | Helped |
| Use EPVA instead of CDNA | Long-term prediction on bouncing shapes · Bouncing shapes, frames 1012–1022 | shape disappeared: 69.7% -> 0% | Helped |
| Add adversarial loss in feature space | EPVA · Human3.6M, frames 1–127 | human preference: ours is better: 46.4% -> 73.9% | Helped |
| Add adversarial loss in feature space | EPVA · Human3.6M, long-term prediction | prediction realism | Helped |
| Replace VAN with a decoder that only receives the encoding (ablation) | EPVA · Human3.6M, prediction beyond frame 32 | foreground removal and long-term prediction quality | Hurt |
| Combine E2E and EPVA losses (ablation) | EPVA · Human3.6M | prediction sharpness | Hurt |
| Increase context from 5 to 10 frames (ablation) | EPVA · Human3.6M, long-term prediction | long-term prediction quality | No clear effect |
| Use EPVA learned features instead of VGG object-recognition features | Pose regression MLP · Human3.6M, pose regression | pose regression error: 0.0758 -> 0.0687 | Helped |
Closest papers by meaning
- Learning to Generate Long-term Future via Hierarchical Prediction (ICML 2017 · similarity 0.91)
- Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction (ICLR 2021 · similarity 0.90)
- FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations (CVPR 2024 · similarity 0.85)
- Visual Representation Learning with Stochastic Frame Prediction (ICML 2024 · similarity 0.84)
- Video Prediction by Modeling Videos as Continuous Multi-Dimensional Processes (CVPR 2024 · similarity 0.84)
- WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception (NeurIPS 2025 · 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.