AI Paper Atlas

Research map / Video / Video segmentation and tracking

VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation

Manoj Kumar, Mohammad Babaeizadeh, Dumitru Erhan, Chelsea Finn, Sergey Levine, Laurent Dinh, Durk Kingma

ICLR 2020 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 30 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
Use VideoFlow instead of SAVP-VAEstochastic video generation · Stochastic Movement Datasetfooling rate: 16.4 % -> 31.8 %Improved
Use VideoFlow instead of SV2Pstochastic video generation · Stochastic Movement Datasetfooling rate: 17.5 % -> 31.8 %Improved
Use VideoFlow instead of SAVP-VAEconditional video prediction · BAIR action-freebits-per-pixel: ≤ 6.73 -> 1.87Improved
Use VideoFlow instead of SV2Pconditional video prediction · BAIR action-freebits-per-pixel: ≤ 6.78 -> 1.87Improved
Lower sampling temperature from T=1.0 to T=0.8VideoFlow · BAIR action-free, training 13 frames; evaluation 13 framesFVD: 149$\pm$6 -> 95$\pm$4Improved
Lower sampling temperature from T=1.0 to T=0.8VideoFlow · BAIR action-free, training 13 frames; evaluation 16 framesFVD: 221$\pm$8 -> 127$\pm$3Improved
Lower sampling temperature from T=1.0 to T=0.8VideoFlow · BAIR action-free, training 13 frames; 2 conditioning frames; evaluation 16 framesFVD: 251$\pm$7 -> 131$\pm$5Improved
Add temporal skip connections (ablation)VideoFlow latent dynamics network · BAIR action-freebits-per-pixelImproved
Use dilated convolutions and GATU instead of the baseline components (ablation)VideoFlow latent dynamics network · BAIR action-freebits-per-pixelImproved
Add dilated convolutions and temporal skip connections (ablation)VideoFlow latent dynamics network · BAIR action-freebits-per-pixelImproved
Use dilated convolutions alone, without temporal skip connections or GATU (ablation)VideoFlow latent dynamics network · BAIR action-freetraining stabilityHurt
Lower temperature from 1.0 toward 0.0 (ablation)SAVP-VAE and SV2P latent Gaussian priors · BAIR action-freeperformanceHurt

Later papers that compared with this method

2 later accepted papers report VideoFlow as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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