AI Paper Atlas

Research map / Video / Video segmentation and tracking

Deep Video Quality Assessor: From Spatio-temporal Visual Sensitivity to A Convolutional Neural Aggregation Network

Woojae Kim, Jongyoo Kim, Sewoong Ahn, Jinwoo Kim, Sanghoon Lee

ECCV 2018 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 127 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 frame difference map as temporal input (ablation)DeepQA (2 spatial inputs) · LIVE VQASROCC: .8678 -> .8723Improved
add temporal error map in addition to frame difference (ablation)DeepVQA-3ch · LIVE VQASROCC: .8723 -> .8913Improved
add temporal error map in addition to frame difference (ablation)DeepVQA-3ch · CSIQ VQASROCC: .8854 -> .9043Improved
add frame difference map as temporal input (ablation)DeepQA · CSIQ VQASROCC: .8752 -> .8854Improved
add CNAN attention temporal pooling instead of average pooling (ablation)DeepVQA-4ch · LIVE VQASROCC: .8913 -> .9152Improved
add CNAN attention temporal pooling instead of average pooling (ablation)DeepVQA-4ch · LIVE VQAPLCC: .8813 -> .8952Improved
add CNAN attention temporal pooling instead of average pooling (ablation)DeepVQA-4ch · CSIQ VQASROCC: .9043 -> .9123Improved
add CNAN attention temporal pooling instead of average pooling (ablation)DeepVQA-4ch · CSIQ VQAPLCC: .9013 -> .9135Improved
use VQPooling instead of average pooling (ablation)DeepVQA-4ch · LIVE VQASROCC: .8913 -> .8987Improved
use CNAN instead of VQPooling (ablation)DeepVQA-VQPooling · LIVE VQASROCC: .8987 -> .9152Improved
add CNAN attention temporal pooling (ablation)DeepVQA-4ch · LIVE VQA (cross-dataset)SROCC: .8322 -> .8437Improved
sample 12 frames per video instead of 6 (ablation)DeepVQA step 1 · LIVE VQAmedian SROCC: .8787 -> .8812Improved

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