AI Paper Atlas

Research map / Video / Video segmentation and tracking

Video Compression With Rate-Distortion Autoencoders

Amirhossein Habibian, Ties van Rozendaal, Jakub M. Tomczak, Taco S. Cohen

ICCV 2019 · Video › Video segmentation and tracking · approach: Learned video compression · 236 citations (OpenAlex)

Read the paper

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 the autoregressive prior on the previous latent frame (ablation)frame-based prior · SDV (trained on Kinetics)rate-distortionImproved
add a Conv-GRU to the prior instead of last-frame conditioning (ablation)video prior (last frame) · SDV (trained on Kinetics)rate-distortionNo clear effect
use a 3D spatio-temporal autoencoder instead of a 2D frame autoencoder (ablation)frame AE · SDV (trained on Kinetics)rate-distortionImproved
weight rate and distortion losses toward person regions (alpha 0.95)non-semantic model · Human ActivityMS-SSIM foreground vs backgroundMixed
finetune generic model on the target driving domaingeneric Kinetics model · Dynamicsrate-distortionImproved
train on channel-wise concatenation of four camera streams instead of single streamsunimodal model · MHADbits per pixel: 0.035 -> 0.007 bpp vs HEVCImproved

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