AI Paper Atlas

Research map / Video / Video segmentation and tracking

VCT: A Video Compression Transformer

Fabian Mentzer, George Toderici, David Minnen, Sergi Caelles, Sung Jin Hwang, Mario Lucic, Eirikur Agustsson

NeurIPS 2022 · Video › Video segmentation and tracking · approach: Learned video compression · 37 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
condition entropy model on 1 previous frame instead of none (ablation)VCT · MCL-JCVbpp: 0.218 -> 0.0907Improved
use 2 previous frames instead of 1 (ablation)VCT · MCL-JCVbpp: 0.0907 -> 0.0775Improved
add latent residual predictor (LRP) (ablation)VCT · MCL-JCVPSNR: 36.1 -> 36.8Improved
use more than 2 previous frames of context (ablation)VCT · MCL-JCVbppNo clear effect
replace flow/warping with transformer temporal entropy modelSSF-style video codec · Synthetic Shift videosR-D loss: approx 45% lower R-D lossImproved
transformer instead of built-in motion priors, static videoVCT · Synthetic static video (x=0)R-D lossHurt
increase training set size to 50k+ clips (ablation)VCT vs SSF · MCL-JCVevaluation lossImproved

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