AI Paper Atlas

Research map / Video / Video-language understanding

Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training

Dingquan Li, Tingting Jiang, Ming Feng Jiang

IJCV 2021 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 145 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 dataset-specific perceptual scale alignment instead of naive linear re-scaling (ablation)MDTVSFA mixed training · Four datasets mixedsize-weighted median SROCC: 0.7576 -> 0.7753Improved
use dataset-specific scale alignment over linear re-scaling (LS-VSFA vs MDTVSFA) (ablation)MDTVSFA · CVD2014+KoNViD-1k+LIVE-Qualcomm overallSROCC: 0.7603 -> 0.7860Improved
use dataset-specific scale alignment over linear re-scaling (LS-VSFA vs MDTVSFA) (ablation)MDTVSFA · CVD2014+KoNViD-1k+LIVE-Qualcomm overallPLCC: 0.7662 -> 0.7923Improved
combine monotonicity, linearity and error losses rather than fewer losses (ablation)MDTVSFA · Four datasets mixedsize-weighted median SROCCImproved
mix three datasets for training instead of training on KoNViD-1k only (ablation)Our model · CVD2014+KoNViD-1k+LIVE-Qualcomm overallmedian SROCC: 0.7483 -> 0.7829Improved
mix three datasets for training instead of training on CVD2014 only (ablation)Our model · CVD2014+KoNViD-1k+LIVE-Qualcomm overallmedian SROCC: 0.6165 -> 0.7829Improved
mix three datasets instead of LIVE-Qualcomm only (ablation)Our model · LIVE-Qualcomm testmedian SROCC: 0.7538 -> 0.8157Improved
add CVD2014 to KoNViD-1k training, test on KoNViD-1k (ablation)Our model · KoNViD-1k testmedian SROCC: drops 0.0067Hurt
add CVD2014 to training of KoNViD-1k, test on CVD2014 (ablation)Our model · CVD2014 testmedian SROCC: 0.6474 -> +0.2078Improved
add LIVE-Qualcomm to LIVE-VQC training, test on unseen CVD2014 and KoNViD-1k (ablation)Our model · unseen test setsmedian SROCCMixed
add KoNViD-1k to training, test on unseen full datasets (ablation)Our model · CVD2014 (full), LIVE-Qualcomm (full), LIVE-VQC (full)median SROCC: 0.3390 +0.2579 (CVD2014 train, LIVE-Qualcomm test)Improved
increase proportion of training data (ablation)MDTVSFA · Four datasetsmean SROCCImproved

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