AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders

Sarthak Bhagat, Shagun Uppal, Zhuyun Yin, Nengli Lim

ECCV 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Structured latent VAEs · 31 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
add geodesic loss (ablation)MGP-VAE prediction network · Moving MNIST (k=1)MSE: 25.4 -> 18.5Improved
add geodesic loss (ablation)MGP-VAE prediction network · Moving MNIST (k=2)MSE: 72.2 -> 69.2Improved
add geodesic loss (ablation)MGP-VAE prediction network · Coloured dSprites (k=1)MSE: 6.1 -> 4.5Improved
add geodesic loss (ablation)MGP-VAE prediction network · Sprites (k=1)MSE: 68.8 -> 61.6Improved
add geodesic loss (ablation)MGP-VAE prediction network · Coloured dSprites (k=1)BCE: 85.2 -> 70.3Improved
use MGP-VAE latent instead of DDPAEprediction MLP · Moving MNIST (k=1)MSE: 35.2 -> 25.4Improved
use MGP-VAE representation instead of DDPAEkNN attribute classification · Coloured dSpritesaverage mAP (%): 80.8 -> 83.4Improved
use MGP-VAE representation instead of DDPAEkNN attribute classification · Spritesaverage mAP (%): 76.9 -> 78.5Improved
set fBM Hurst H=0.9 rather than H=0.5 for motion channel (ablation)MGP-VAE · Moving MNISTmotion capture (qualitative)Improved
include more channels than factors of variation (ablation)MGP-VAE · Coloured dSprites and Spritesdisentanglement (qualitative)Improved
replace fBM mixtures with 4-5 Brownian bridge channels (ablation)MGP-VAE · Coloured dSprites and Spritesdisentanglement (qualitative)No clear effect
use Ornstein-Ulenbeck process as latent prior (ablation)MGP-VAE · video datasetsdisentanglement (qualitative)Hurt

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