AI Paper Atlas

Research map / Video / Video-language understanding

Context Guided Transformer Entropy Modeling for Video Compression

Junlong Tong, Wei Zhang, Yaohui Jin, Xiaoyu Shen

ICCV 2025 · Video › Video-language understanding · approach: Long video understanding · 1 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 temporal context resampler (TCR) to CGT (ablation)CGT · Entropy modeling timetime (ms): 1,305 -> 488Improved
add TCR to CGT (ablation)CGT · BD-rateBD-rate (%): +1.8Hurt
add TCR to MIMT with random mask (ablation)MIMT(random) · Entropy modeling timetime (ms): 1,226 -> 427Improved
add TCR to MIMT with random mask (ablation)MIMT(random) · BD-rateBD-rate (%): +2.2Hurt
add TCR to CGT (ablation)CGT · Encoding/decoding timetime (ms): 1,682 -> 1,073 encoding; 1,576 -> 984 decodingImproved
use dependency-weighted spatial context assigner instead of min-entropy decoding (ablation)CGT · MCL-JCV, UVG, HEVC-B averageBD-rate (%): 0 -> -11.2Improved
use checkerboard decoding instead of min-entropy decoding (ablation)CGT · average of 3 datasetsBD-rate (%): 0 -> 17.3Hurt
use block-autoregressive decoding instead of min-entropy decoding (ablation)CGT · average of 3 datasetsBD-rate (%): 0 -> 19.5Hurt
set alpha=0 (importance only) instead of alpha=1 (certainty only) (ablation)CGT · MCL-JCV lambda=256PSNR: PSNR 35.3 -> 35.88, Bpp 0.017 -> 0.019Mixed
use explicit teacher-student modeling instead of random-mask proxy task (ablation)CGT · MCL-JCV alpha=0.5PSNR: 35.58 -> 35.82Improved
use explicit modeling instead of proxy task (ablation)CGT · MCL-JCV alpha=0Bpp: 0.021 -> 0.019Improved
replace DMC frame codec with DCVC-DCCGT · entropy codingBD-rateNo clear effect

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