AI Paper Atlas

Research map / Video / Video generation

Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives

Haoning Wu, Erli Zhang, Liang Liao, Chaofeng Chen, Jingwen Hou, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin

ICCV 2023 · Video › Video generation · approach: Compositional text-to-video diffusion · 304 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 View Decomposition (separate aesthetic and technical views) (ablation)DOVER · LSVQ_testSROCC: 0.859 -> 0.888Improved
use separate branch supervision instead of feature aggregation (ablation)DOVER · LSVQ_testSROCC: 0.873 -> 0.888Improved
add subjectively-inspired weighted fusion (0.428/0.572) instead of unweighted sum (ablation)DOVER · LSVQ_testSROCC: 0.885 -> 0.888Improved
fuse both branches rather than using one (ablation)DOVER · LSVQ_testSROCC: 0.877 -> 0.885Improved
add direct perspective supervision L_DS to L_LVBS (ablation)DOVER++ · DIVIDE-3kSROCC: 0.8331 -> 0.8442Improved
use L_DS only instead of L_LVBS only (ablation)DOVER++ · DIVIDE-3kSROCC: 0.8331 -> 0.8357Improved
train with perspective labels MOS_A and MOS_T (DOVER++ vs DOVER)DOVER · DIVIDE-3kSROCC: 0.8331 -> 0.8442Improved
replace FAST-VQA with DOVERUGC-VQA models · KoNViD-1k (train on LSVQ)PLCC: 0.855 -> 0.883Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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