AI Paper Atlas

Research map / Video / Video segmentation and tracking

VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision

Xihua Sheng, Li Li, Dong Liu, Houqiang Li

TPAMI 2024 · Video › Video segmentation and tracking · approach: Learned video compression · 41 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
use intermediate feature instead of reconstructed frame for temporal context (ablation)VNVC · HEVC Class BBD-rate (%): 2.2 -> 0.0Improved
use intermediate feature instead of last feature for temporal context (ablation)VNVC · HEVC (average)BD-rate (%): 0.74% BD-rate reductionImproved
use intermediate feature instead of last feature for temporal context (ablation)VNVC · HEVC Class EBD-rate (%): 3.3 -> 0.0Improved
use intermediate feature instead of last feature for temporal context (ablation)VNVC · decoding GFLOPsGFLOPs: 6745.61 -> 4709.17Improved
use cross-domain motion coding instead of pixel-domain (ablation)VNVC · encoding GFLOPsGFLOPs: 7909.90 -> 4606.08Improved
use cross-domain motion coding instead of feature-domain (ablation)VNVC · encoding timeseconds: 1.871 -> 1.336Improved
use cross-domain motion coding instead of pixel-domain (ablation)VNVC · HEVC Class BBD-rate (%): -1.6 -> 0.0Mixed
use 2 U-Net reconstruction network instead of 1 U-Net (ablation)VNVC · HEVC Class EBD-rate (%): 2.1 -> 0.0Improved
use 2 U-Net instead of 1 residual block (ablation)VNVC · HEVC Class EBD-rate (%): 6.5 -> 0.0Improved
decode intermediate features for the task (Ours(fea)) instead of decoded images (ablation)VNVC · DAVIS 2017 segmentationBD-performance: 0.00 vs -1.18Improved
decode intermediate features for the task (Ours(fea)) instead of decoded images (ablation)VNVC · DAVIS decoding GFLOPsGFLOPs: 1482.97 -> 1034.17Improved
decode intermediate features for the task instead of decoded images (ablation)VNVC · DAVIS non-blind denoising (delta=20)PSNR dB: 0.03No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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