AI Paper Atlas

Research map / Video / Video segmentation and tracking

Efficient Meta-Tuning for Content-Aware Neural Video Delivery

Xiaoqi Li, Jiaming Liu, Shizun Wang, Cheng Lyu, Ming Lu, Yurong Chen, Anbang Yao, Yandong Guo, Shanghang Zhang

ECCV 2022 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 22 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 meta-tuning (meta-learned init, S setting) instead of per-chunk training from scratchESPCN content-aware SR · inter-45s x2PSNR / time: 38.95 -> 39.08; 11.2h -> 1.2mImproved
use meta-learned init instead of pretrained init (ablation)EMT · sport-45s x2 (S)training time: 4.2m -> 1.2mImproved
use meta-learned init instead of pretrained init (ablation)EMT · inter-45s x2 (S)training time: 18.4m -> 1.2mImproved
add challenging patch sampling (ablation)EMT · inter-45s x2 (S)training time: 9.7m -> 1.2mImproved
add challenging patch sampling (ablation)EMT · sport-45s x2 (S)training time: 2.7m -> 1.2mImproved
update all parameters for first chunk (p1 20 -> 100) (ablation)EMT Ours(S) · inter-45s x2PSNR: 39.08 -> 39.19Improved
raise p2 from 1 to 10 (ablation)EMT Ours(S) · sport-45s x2PSNR: 46.11 -> 46.23Improved
vary number of meta-learning tasks (10, 15, 20) (ablation)EMT Ours(S) · inter-45s x2PSNR: 39.06 / 39.08 / 39.07No clear effect
increase meta-learning frames from 10 to 150 (ablation)EMT Ours(S) · sport-45s x2PSNR: 45.94 -> 46.20Mixed
apply EMT to x4 scaling instead of C1-nESPCN · sport-45s x4PSNR: 37.21 -> 37.22No clear effect
apply EMT to x3 scalingESPCN · inter-45s x3PSNR: 32.19 -> 32.55Improved
apply EMT with SRCNN backboneSRCNN · game-45sPSNR: 35.37 -> 35.64Improved

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