atlas

Research map / Video / Video segmentation and tracking

Structure Preserving Video Prediction

CVPR 2018 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 49 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 the two-branch frequency framework (ablation)ConvLSTM · CityScapePSNR: 22.8 -> 25.2Helped
Add the two-branch frequency framework (ablation)ConvLSTM · Human3.6MPSNR: 36.2 -> 37.2Helped
Add the two-branch frequency framework (ablation)ConvLSTM · Clean-JerkPSNR: 23.4 -> 25.3Helped
Add Fus-4 hidden-state fusion (ablation)Two-B · CityScapePSNR: 25.2 -> 25.7Helped
Add Fus-4 hidden-state fusion (ablation)Two-B · Human3.6MPSNR: 37.2 -> 37.5No clear effect
Add Fus-4 hidden-state fusion (ablation)Two-B · Clean-JerkPSNR: 25.3 -> 25.7No clear effect
Add Tem-K temporal-adaptive kernels (ablation)Two-B+Fus-4 · CityScapePSNR: 25.7 -> 26.6Helped
Add Tem-K temporal-adaptive kernels (ablation)Two-B+Fus-4 · Human3.6MPSNR: 37.5 -> 39.7Helped
Add Tem-K temporal-adaptive kernels (ablation)Two-B+Fus-4 · Clean-JerkPSNR: 25.7 -> 27.5Helped

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