Research map / Video / Video segmentation and tracking
Learning to Decompose and Disentangle Representations for Video Prediction
Jun-Ting Hsieh, Bingbin Liu, De-An Huang, Li F Fei-Fei, Juan Carlos Niebles
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 automatic component decomposition and disentangled content/pose representations | DDPAE · Moving MNIST | BCE and MSE | Improved |
| Remove component decomposition (ablation) | DDPAE · Moving MNIST | BCE and MSE | Hurt |
| Remove content/pose disentanglement (ablation) | DDPAE · Moving MNIST | BCE and MSE | Hurt |
| Add interdependent pose prediction across components | DDPAE · Bouncing Balls | velocity relative error and cosine similarity | Improved |
| Remove interdependent component prediction (ablation) | DDPAE · Bouncing Balls | velocity relative error and cosine similarity | Hurt |
| Train with reconstruction and prediction losses throughout instead of switching to prediction loss only halfway (ablation) | DDPAE · Video prediction experiments | prediction results | No clear effect |
Closest papers by meaning
- Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders (ECCV 2020 · similarity 0.89)
- DFDNet: Disentangling and Filtering Dynamics for Enhanced Video Prediction (AAAI 2025 · similarity 0.86)
- Deep Hierarchical Video Compression (AAAI 2024 · similarity 0.86)
- Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations (NeurIPS 2025 · similarity 0.86)
- Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement (CVPR 2024 · similarity 0.85)
- EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens (ICML 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.
