AI Paper Atlas

Research map / Video / Video-language understanding

Telepresence Video Quality Assessment

Zhenqiang Ying, Deepti Ghadiyaram, Alan Bovik

ECCV 2022 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 4 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 audio features to the visual model (ablation)TeleVQA (p+f+c) · Telepresence video databaseSRCC: 0.633 -> 0.663Improved
add patch-level features to image and clip features (ablation)TeleVQA (f+c) · Telepresence video databaseSRCC: 0.621 -> 0.633Improved
add patch-level features to image and clip features (ablation)TeleVQA (f+c) · LIVE-VQCSRCC: 0.811 -> 0.811No clear effect
add clip-level features to image features (ablation)TeleVQA (f) · Telepresence video databaseSRCC: 0.609 -> 0.621Improved
add clip-level features to image features (ablation)TeleVQA (f) · LIVE-VQCSRCC: 0.710 -> 0.811Improved
add audio to image features (ablation)TeleVQA (f) · Telepresence video databaseSRCC: 0.609 -> 0.622Improved
add audio to image and clip features (ablation)TeleVQA (f+c) · Telepresence video databaseSRCC: 0.621 -> 0.639Improved
add patch-level features to image, clip and audio features (ablation)TeleVQA (f+c+a) · Telepresence video databaseSRCC: 0.639 -> 0.663Improved
use image-level instead of patch-level features alone (ablation)TeleVQA unimodal · Telepresence video databaseSRCC: 0.476 -> 0.609Improved
use clip-level instead of image-level features alone (ablation)TeleVQA unimodal · Telepresence video databaseSRCC: 0.609 -> 0.475Hurt
multimodal Tele-VQA versus best baselineTele-VQA (p+f+c+a) · Telepresence video databaseSRCC: 0.601 -> 0.663Improved
Tele-IQA versus P2P-FM in cross-database test on KonIQTele-IQA · KonIQ (cross-database, no fine-tuning)SRCC: 0.788 -> 0.772Hurt

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