AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Conditional Recurrent Flow: Conditional Generation of Longitudinal Samples With Applications to Neuroimaging

Seong Jae Hwang, Zirui Tao, Won Hwa Kim, Vikas Singh

ICCV 2019 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers · 13 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 temporal context gating (TCG) to CRow (ablation)CRow · TADPOLE Diagnosis, Control vs Progressionsignificant ROIs: 11 -> 12Improved
add temporal context gating (TCG) to CRow (ablation)CRow · TADPOLE ADAS13, Control vs Progressionsignificant ROIs: 12 -> 14Improved
add temporal context gating (TCG) to CRow (ablation)CRow · TADPOLE CDR-SB, Control vs Progressionsignificant ROIs: 7 -> 9Improved
add temporal context gating (TCG) to CRow (ablation)CRow · TADPOLE MMSE and RAVLT-I, Control vs Progressionsignificant ROIs: 2 -> 2No clear effect
add temporal context gating (TCG) to CRow (ablation)CRow · TADPOLE Diagnosis, Control vs Early-progressionsignificant ROIs: 2 -> 4Improved
add temporal context gating (TCG) to CRow (ablation)CRow · TADPOLE ADAS13, Control vs Early-progressionsignificant ROIs: 4 -> 5Improved
replace cINN with recurrent flow CRowconditional invertible network · TADPOLE Diagnosis, Control vs Progressionsignificant ROIs: 4 -> 11Improved
replace cINN with recurrent flow CRowconditional invertible network · TADPOLE CDR-SB, Control vs Progressionsignificant ROIs: 0 -> 7Improved
replace cINN with recurrent flow CRowconditional invertible network · TADPOLE Diagnosis, Control vs Early-progressionsignificant ROIs: 0 -> 2Improved
generate synthetic samples instead of using raw training datagroup statistical analysis · TADPOLE Control vs Progressionsignificant ROIs: no significant ROIs with raw dataImproved
increase generated samples from 100 to 150 per groupControl vs Early-progression analysis · TADPOLE Early-progressionsignificant ROIs: no significant ROIs at N=100 -> several at N=150Improved

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