AI Paper Atlas

Research map / Video / Video segmentation and tracking

Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence

Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon

CVPR 2019 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 27 citations (OpenAlex)

Check 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 a 3D encoder with a 2D decoder rather than a 2D encoder-2D decoder (ablation)BVDNet · ChaLearn 2018 LAP Inpainting Track2 validationPSNR: 33.6803 -> 34.1029Improved
Use a 3D encoder-2D decoder rather than a 3D encoder-3D decoder (ablation)BVDNet · ChaLearn 2018 LAP Inpainting Track2 validationPSNR: 28.4590 -> 34.1029Improved
Add gradient L1 loss (ablation)3D encoder-2D decoder with L1 loss · ChaLearn 2018 LAP Inpainting Track2 validationPSNR: 34.1029 -> 34.2251Improved
Add SSIM loss alongside L1 and gradient L1 (ablation)3D encoder-2D decoder · ChaLearn 2018 LAP Inpainting Track2 validationPSNR: 34.2251 -> 34.6544Improved
Add recurrence stream and temporal consistency constraints (ablation)BVDNet · ChaLearn 2018 LAP Inpainting Track2 validation, 500 clipsTemporal error: 0.00117 -> 0.00090Improved
Add recurrence stream (ablation)BVDNet · ChaLearn 2018 LAP Inpainting Track2 validationPSNR: 34.6544 -> 34.7055Improved
Add GAN loss (ablation)BVDNet · ChaLearn 2018 LAP Inpainting Track2 validationPSNR: 34.7055 -> 31.2257Hurt
Remove residual image shortcut (ablation)BVDNet · ChaLearn 2018 LAP Inpainting Track2 validationPSNR: 34.7055 -> 34.3892Hurt
Use 3 input frames instead of 5 (ablation)BVDNet · ChaLearn 2018 LAP Inpainting Track2 validationPSNR: 34.7055 -> 33.7895Hurt
Use 7 input frames instead of 5 (ablation)BVDNet · ChaLearn 2018 LAP Inpainting Track2 validationPSNR: 34.7055 -> 34.5063Hurt
Use 9 input frames instead of 5 (ablation)BVDNet · ChaLearn 2018 LAP Inpainting Track2 validationPSNR: 34.7055 -> 34.6260Hurt

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