AI Paper Atlas

Research map / Video / Video segmentation and tracking

Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos

Yubin Hu, Yuze He, Yanghao Li, Jisheng Li, Yuxing Han, Jiangtao Wen, Yong-Jin Liu

CVPR 2023 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 17 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
Alter input resolution between HR keyframes and LR non-keyframes, with CReFF and FSTPSPNet18 and BiseNet18 · CamVid test and Cityscapes validmIoU (%): 69.43 -> 70.48; 71.57 -> 70.38; 69.00 -> 69.03; 70.09 -> 70.57Improved
Use AR-Seg with lower-resolution non-keyframesPSPNet18 and BiseNet18 · CamVid test and Cityscapes validGFLOPs: 309.02 -> 101.98; 58.83 -> 18.96; 560.97 -> 177.44; 178.96 -> 57.00Improved
Remove CReFF (ablation)AR-Seg with PSPNet18 · CamVid test; L=12mIoU (%): 70.48 -> 67.14Hurt
Use motion-vector warping without local attention (ablation)AR-Seg with PSPNet18 · CamVid test; L=12mIoU (%): 70.48 -> 57.64Hurt
Use local attention without motion-vector warping (ablation)AR-Seg with PSPNet18 · CamVid test; L=12mIoU (%): 70.48 -> 67.93Hurt
Replace 7x7 local attention with 3x3 local attention (ablation)AR-Seg with PSPNet18 · CamVid test; L=12mIoU (%): 70.48 -> 70.30Hurt
Replace 7x7 local attention with 11x11 local attention (ablation)AR-Seg with PSPNet18 · CamVid test; L=12GFLOPs: 101.98 -> 107.32Hurt
Replace grouped local-attention encoders with non-grouped encoders (ablation)AR-Seg with PSPNet18 · CamVid test; L=12GFLOPs: 101.98 -> 170.96Hurt
Replace local attention with global attention (ablation)AR-Seg with PSPNet18 · CamVid test; L=12mIoU (%): 70.48 -> 67.11Hurt
Replace local attention with a one-layer convolution (ablation)AR-Seg with PSPNet18 · CamVid test; L=12GFLOPs: 101.98 -> 143.63Hurt
Remove the direct-connection path from CReFF (ablation)AR-Seg with PSPNet18 · CamVid test; L=12mIoU (%): 70.48 -> 69.14Hurt
Move CReFF before the task sub-network instead of before the final 1x1 convolution (ablation)AR-Seg with PSPNet18 · CamVid test; L=12mIoU (%): 70.48 -> 68.60Hurt

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