AI Paper Atlas

Research map / Video / Video segmentation and tracking

Conditional Entropy Coding for Efficient Video Compression

Jerry Liu, Shenlong Wang, Wei-Chiu Ma, Meet Shah, Rui Hu, Pranaab Dhawan, Raquel Urtasun

ECCV 2020 · Video › Video segmentation and tracking · approach: Learned video compression · 76 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 internal learning of latent codes at inference (ablation)conditional entropy video compressor · UVG rate-distortionbitrate: ~10% additional bitrate savingsImproved
add the conditional entropy model on top of single-image compression (ablation)single-image Liu model · NorthAmericabitrate: bitrate improvements of 20-50%Improved
add internal learning on NorthAmerica (ablation)conditional entropy video compressor · NorthAmericabitrate: additional ~10% improvementImproved
add conditional entropy model at lower framerates (ablation)single-image model · UVG and CDVL, framerates 1/3, 1/6, 1/10bitrate: 20%-50% reduction of bitrateImproved
add internal learning at lower framerates (ablation)conditional entropy video compressor · UVG and CDVL, framerates 1/3, 1/6, 1/10bitrate: additional 10-20% reduction in bitrateImproved
increase internal learning gradient steps from 1 to 100 (ablation)conditional entropy video compressor · UVG ShakeNDry (first 50 frames)rate-distortion: saturates after 30 gradient stepsMixed
increase H.265/H.264 GoP size from 12 to full video length (ablation)H.265 / H.264 · UVGrate-distortion: marginal gap between GoP 12 and default; thin gap to max GoPNo clear effect
use single-image compression instead of H.265 veryslow at lower frameratessingle-image compressor · UVG lower frameratesrate-distortion: matches H.265 veryslowNo clear effect
independent frame encoder lacks high-frequency capture on VTLconditional entropy video compressor · VTLrate-distortion vs video codecsHurt

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