AI Paper Atlas

Research map / Video / Video segmentation and tracking

Non-Semantics Suppressed Mask Learning for Unsupervised Video Semantic Compression

Yuan Tian, Guo Lu, Guangtao Zhai, Zhiyong Gao

ICCV 2023 · 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
add semantic compensation (residual semantic stream) to VVC (ablation)SMC · UCF101 TSM @0.02bppTop1 accuracy (%): 16% Top1 drop without compensationImproved
use video enhancement BasicVSR++ instead of semantic compensation (ablation)SMC · UCF101 TSM @0.02bppTop1 accuracy (%): -14.23%@0.02bppHurt
add NSS entropy suppression loss to MAE objective (ablation)SMC · UCF101 TSM (VVC CRF 51)Top1 accuracy (%): 69.57 -> 72.96Improved
add NSS entropy suppression loss to MAE objective (ablation)SMC · UCF101 TSM (VVC CRF 51)residual bitrate (bpp): 0.0074 -> 0.0028Improved
condition GMM on mined semantic feature S instead of a plain learnable variable (ablation)NSS · UCF101 TSM (VVC CRF 51)Top1 accuracy (%): 71.38 -> 72.96Improved
use GMM entropy regularization instead of VQ codebook for token discretization (ablation)NSS · UCF101 TSM (VVC CRF 51)Top1 accuracy (%): 71.22 vs 71.38 (VQ vs woSem)No clear effect
use NSS-MAE objective instead of MoCoV3 contrastive objective (ablation)SMC · MOT17 ByteTrack @0.01bppMOTA (%): 67.62 -> 70.84Improved
use NSS-MAE objective instead of MoCoV3 (ablation)SMC · UCF101 TSM @0.02bppTop1 accuracy (%): 75.20 -> 76.48Improved
fine-tune downstream TSM on videos from each codecVVC · UCF101 TSM @0.04bppTop1 accuracy (%): 76.97 -> 82.35Improved
fine-tune downstream TSM on SMC-decoded videosSMC · UCF101 TSM @0.04bppTop1 accuracy (%): 86.46 -> 89.83Improved
replace NSS-MAE semantic objective with hand-crafted SegMap loss (ablation)SMC · UCF101 TSMTop1 accuracy (%): about 3% gap at 0.05bppHurt
set NSS weight beta to 0.01 or 1 instead of 0.1 (ablation)SMC · UCF101 TSMTop1 accuracy (%)Hurt

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