AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Sequential Representation Learning via Static-Dynamic Conditional Disentanglement

Mathieu Cyrille Simon, Pascal Frossard, Christophe De Vleeschouwer

ECCV 2024 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
model static/dynamic factors as dependent via conditional normalizing flowStatic-dynamic disentanglement model · MPI3D (dependent factors)shape accuracy (%): 43.81 -> 90.15Improved
model static/dynamic factors as dependent via conditional normalizing flowStatic-dynamic disentanglement model · c-dSprites (dependent factors)shape accuracy (%): 74.32 -> 98.98Improved
model static/dynamic factors as dependent via conditional normalizing flowStatic-dynamic disentanglement model · LPCSprites (dependent factors)body accuracy (%): 54.94 -> 99.97Improved
dependent factors vs independent factors for baseline methodsprior sequential disentanglement methods · c-dSprites, MPI3D, LPCSpritesaccuracyHurt
apply method with independent factors (no dependency)Static-dynamic disentanglement model · MUGaction accuracy (%): 85.71 -> 84.32No clear effect
apply method vs SPYL on MHADStatic-dynamic disentanglement model · MHADaction accuracy (%): 68.63 -> 67.65No clear effect
use shuffle constraint on static codes instead of extra lossesStatic-dynamic disentanglement model · all datasetsdisentanglementImproved

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