AI Paper Atlas

Research map / Video / Video segmentation and tracking

Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction

Efstathios Karypidis, Spyros Gidaris, Nikos Komodakis

ECCV 2026 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 0 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 hierarchical semantic forecasting stage (Re2Pix)video diffusion baseline · Cityscapes (single-dataset training)FID: 12.86 -> 9.90Improved
add hierarchical semantic forecasting stage (Re2Pix)video diffusion baseline · Cityscapes (single-dataset training)mIoU(A): 60.55 -> 63.53Improved
add REPA alignment lossvideo diffusion baseline · Cityscapes (single-dataset training)FID: 12.86 -> 12.34Improved
add VideoREPA alignment lossvideo diffusion baseline · Cityscapes (single-dataset training)FID: 12.86 -> 12.95No clear effect
increase parameters to 1.5B (Baseline-Large)video diffusion baseline · Cityscapes (single-dataset training)mIoU(A): 60.55 -> 61.69Improved
add nested dropout of semantic channels (ablation)Re2Pix · Cityscapes (single-dataset training)FID: 12.63 -> 9.90Improved
add nested dropout of semantic channels (ablation)Re2Pix · Cityscapes (single-dataset training)FVD: 58.91 -> 52.66Improved
add 10% predicted features to ground-truth training (mixed supervision) (ablation)Re2Pix · Cityscapes (single-dataset training)FVD: 80.85 -> 52.66Improved
add 10% predicted features to ground-truth training (mixed supervision) (ablation)Re2Pix · Cityscapes (single-dataset training)mIoU(A): 64.42 -> 63.53Hurt
add 90% ground-truth features to predicted-only training (mixed supervision) (ablation)Re2Pix · Cityscapes (single-dataset training)FID: 10.21 -> 9.90Improved
add 90% ground-truth features to predicted-only training (mixed supervision) (ablation)Re2Pix · Cityscapes (single-dataset training)mIoU(A): 62.77 -> 63.53Improved
use DINOv2 instead of SigLIP-2 as VFM (ablation)Re2Pix · Cityscapes (single-dataset training)mIoU(A): 63.02 -> 63.53Improved

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