Research map / Video / Video-language understanding
Telepresence Video Quality Assessment
Zhenqiang Ying, Deepti Ghadiyaram, Alan Bovik
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add audio features to the visual model (ablation) | TeleVQA (p+f+c) · Telepresence video database | SRCC: 0.633 -> 0.663 | Improved |
| add patch-level features to image and clip features (ablation) | TeleVQA (f+c) · Telepresence video database | SRCC: 0.621 -> 0.633 | Improved |
| add patch-level features to image and clip features (ablation) | TeleVQA (f+c) · LIVE-VQC | SRCC: 0.811 -> 0.811 | No clear effect |
| add clip-level features to image features (ablation) | TeleVQA (f) · Telepresence video database | SRCC: 0.609 -> 0.621 | Improved |
| add clip-level features to image features (ablation) | TeleVQA (f) · LIVE-VQC | SRCC: 0.710 -> 0.811 | Improved |
| add audio to image features (ablation) | TeleVQA (f) · Telepresence video database | SRCC: 0.609 -> 0.622 | Improved |
| add audio to image and clip features (ablation) | TeleVQA (f+c) · Telepresence video database | SRCC: 0.621 -> 0.639 | Improved |
| add patch-level features to image, clip and audio features (ablation) | TeleVQA (f+c+a) · Telepresence video database | SRCC: 0.639 -> 0.663 | Improved |
| use image-level instead of patch-level features alone (ablation) | TeleVQA unimodal · Telepresence video database | SRCC: 0.476 -> 0.609 | Improved |
| use clip-level instead of image-level features alone (ablation) | TeleVQA unimodal · Telepresence video database | SRCC: 0.609 -> 0.475 | Hurt |
| multimodal Tele-VQA versus best baseline | Tele-VQA (p+f+c+a) · Telepresence video database | SRCC: 0.601 -> 0.663 | Improved |
| Tele-IQA versus P2P-FM in cross-database test on KonIQ | Tele-IQA · KonIQ (cross-database, no fine-tuning) | SRCC: 0.788 -> 0.772 | Hurt |
Closest papers by meaning
- Patch-VQ: 'Patching Up' the Video Quality Problem (CVPR 2021 · similarity 0.86)
- Modular Blind Video Quality Assessment (CVPR 2024 · similarity 0.84)
- FineVQ: Fine-Grained User Generated Content Video Quality Assessment (CVPR 2025 · similarity 0.82)
- KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception (CVPR 2025 · similarity 0.81)
- AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM (CVPR 2025 · similarity 0.81)
- PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild (CVPR 2024 · similarity 0.81)
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.
