AI Paper Atlas

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

CVPR 2021 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 8 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use VDSM rather than S3VAE for consistency evaluationSprites · Spritesaccuracy consistency: 99.49 -> 99.53Improved
Use VDSM rather than S3VAE for consistency evaluationMUG · MUGaccuracy consistency: 70.51 -> 93.33Improved
Use VDSM rather than G3AN for unconditional generationMUG · MUGFID: 67.12 -> 44.12Improved
Use VDSM rather than S3VAE for identity classification consistencySprites · Spritesidentity accuracy: 99.49 -> 99.53Improved
Use separate identity and dynamics embeddingsVDSM on Sprites · Spritesfactor classification accuracy: 98.67; 99.33; 45.00; 52.67Mixed
Use separate identity and dynamics embeddingsVDSM on MUG · MUGfactor classification accuracy: 99.00; 83.33; 57.33; 65.67Mixed
Replace the decoder bank with one decoder (ablation)VDSM · Identity-pose swappingidentity-pose disentanglementHurt
Add inverse autoregressive flows to the approximate posterior (ablation)VDSM · Experimentsoverall performanceNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy