Research map / Probabilistic and scientific modeling / Causal discovery
Sequential Representation Learning via Static-Dynamic Conditional Disentanglement
Mathieu Cyrille Simon, Pascal Frossard, Christophe De Vleeschouwer
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 |
|---|---|---|---|
| model static/dynamic factors as dependent via conditional normalizing flow | Static-dynamic disentanglement model · MPI3D (dependent factors) | shape accuracy (%): 43.81 -> 90.15 | Improved |
| model static/dynamic factors as dependent via conditional normalizing flow | Static-dynamic disentanglement model · c-dSprites (dependent factors) | shape accuracy (%): 74.32 -> 98.98 | Improved |
| model static/dynamic factors as dependent via conditional normalizing flow | Static-dynamic disentanglement model · LPCSprites (dependent factors) | body accuracy (%): 54.94 -> 99.97 | Improved |
| dependent factors vs independent factors for baseline methods | prior sequential disentanglement methods · c-dSprites, MPI3D, LPCSprites | accuracy | Hurt |
| apply method with independent factors (no dependency) | Static-dynamic disentanglement model · MUG | action accuracy (%): 85.71 -> 84.32 | No clear effect |
| apply method vs SPYL on MHAD | Static-dynamic disentanglement model · MHAD | action accuracy (%): 68.63 -> 67.65 | No clear effect |
| use shuffle constraint on static codes instead of extra losses | Static-dynamic disentanglement model · all datasets | disentanglement | Improved |
Closest papers by meaning
- Sequential Disentanglement by Extracting Static Information From A Single Sequence Element (ICML 2024 · similarity 0.91)
- Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations (NeurIPS 2025 · similarity 0.89)
- Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation (ICML 2023 · similarity 0.89)
- Transferring disentangled representations: bridging the gap between synthetic and real images (NeurIPS 2024 · similarity 0.87)
- Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement (CVPR 2024 · similarity 0.87)
- Object centric architectures enable efficient causal representation learning (ICLR 2024 · similarity 0.86)
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.
