Research map / Video / Video segmentation and tracking
VDSM: Unsupervised Video Disentanglement With State-Space Modeling and Deep Mixtures of Experts
Matthew J. Vowels, Necati Cihan Camgoz, Richard Bowden
Check 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 |
|---|---|---|---|
| Use VDSM rather than S3VAE for consistency evaluation | Sprites · Sprites | accuracy consistency: 99.49 -> 99.53 | Improved |
| Use VDSM rather than S3VAE for consistency evaluation | MUG · MUG | accuracy consistency: 70.51 -> 93.33 | Improved |
| Use VDSM rather than G3AN for unconditional generation | MUG · MUG | FID: 67.12 -> 44.12 | Improved |
| Use VDSM rather than S3VAE for identity classification consistency | Sprites · Sprites | identity accuracy: 99.49 -> 99.53 | Improved |
| Use separate identity and dynamics embeddings | VDSM on Sprites · Sprites | factor classification accuracy: 98.67; 99.33; 45.00; 52.67 | Mixed |
| Use separate identity and dynamics embeddings | VDSM on MUG · MUG | factor classification accuracy: 99.00; 83.33; 57.33; 65.67 | Mixed |
| Replace the decoder bank with one decoder (ablation) | VDSM · Identity-pose swapping | identity-pose disentanglement | Hurt |
| Add inverse autoregressive flows to the approximate posterior (ablation) | VDSM · Experiments | overall performance | No clear effect |
Closest papers by meaning
- Unsupervised Learning of Disentangled Representations from Video (NeurIPS 2017 · similarity 0.90)
- Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations (NeurIPS 2025 · similarity 0.88)
- Sequential Representation Learning via Static-Dynamic Conditional Disentanglement (ECCV 2024 · similarity 0.88)
- A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation (JMLR 2020 · similarity 0.88)
- Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective (NeurIPS 2023 · similarity 0.87)
- Sequential Disentanglement by Extracting Static Information From A Single Sequence Element (ICML 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.
