AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Leveraging Motion Priors in Videos for Improving Human Segmentation

Yu-Ting Chen, Wen-Yen Chang, Hai-Lun Lu, Tingfan Wu, Min Sun

ECCV 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 2 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
select motion priors with the learned policy instead of random (ablation)U-Net segmenter · Gym-RGB->Gym-IRIoU: 52.5% -> 55.6%Improved
fine-tune on policy-selected motion priors from target videoU-Net segmenter · Gym-RGB->Gym-IRIoU: 48.6% -> 55.6%Improved
fine-tune on policy-selected motion priorsU-Net segmenter · Gym-RGB->UrbanStreetIoU: 48.5% -> 51.2%Improved
fine-tune on policy-selected motion priorsU-Net segmenter · Store-RGB->UrbanStreetIoU: 61.7% -> 64.8%Improved
learned policy instead of random selection (ablation)U-Net segmenter · Gym-RGB->Multi-Scene-IRIoU: 26.5% -> 30.5%Improved
learned policy instead of random selection (ablation)SegNet segmenter · Gym-RGB->Multi-Scene-IRIoU: 37.2% -> 38.4%Improved
learned policy instead of random selection (ablation)SegNet segmenter · Store-RGB->Gym-IRIoU: 24.8% -> 26.9%Improved
learned policy instead of random selection (ablation)U-Net segmenter · Store-RGB->Multi-Scene-IRIoU: 30.2% -> 34.3%Improved
learned policy instead of human selection of priorsU-Net segmenter · Store-RGB->Gym-IRIoU: 32.5% -> 32.3%No clear effect
add PAL on top of DSNDSN · Gym-RGB->Multi-Scene-IRIoU: 25.9% -> 35.8%Improved
add PAL on top of DSNDSN · Store-RGB->Gym-IRIoU: 31.8% -> 36.4%Improved
add PAL on top of DSNDSN · Gym-RGB->Gym-IRIoU: 54.3% -> 55.8%Improved

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