Research map / Label-efficient and robust learning / Recognition and long-tail
TuningIQA: Fine-Grained Blind Image Quality Assessment for Livestreaming Camera Tuning
Xiangfei Sheng, Zhichao Duan, Xiaofeng Pan, Yipo Huang, Zhichao Yang, Pengfei Chen, Leida Li
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 human-aware feature extraction (HFE) (ablation) | baseline BIQA · FGLive-10K | SRCC: 0.8757 -> 0.8917 | Improved |
| add human-aware feature extraction (HFE) (ablation) | baseline BIQA · FGLive-10K | PLCC: 0.9201 -> 0.9267 | Improved |
| add human-aware feature extraction (HFE) (ablation) | baseline BIQA · FGLive-10K | FG-ACC: 0.7258 -> 0.7496 | Improved |
| add graph-based camera parameter fusion (GCPF) (ablation) | baseline BIQA · FGLive-p | SRCC: 0.8206 -> 0.8552 | Improved |
| add graph-based camera parameter fusion (GCPF) (ablation) | baseline BIQA · FGLive-p | FG-ACC: 0.7092 -> 0.7308 | Improved |
| add HFE on top of GCPF (ablation) | baseline + GCPF · FGLive-p | SRCC: 0.8552 -> 0.8613 | Improved |
| add HFE on top of GCPF (ablation) | baseline + GCPF · FGLive-p | FG-ACC: 0.7308 -> 0.7382 | Improved |
| add HFE on top of GCPF (ablation) | baseline + GCPF · FGLive-p | PLCC: 0.8963 -> 0.9009 | Improved |
| use ResNet-50 backbone instead of MobileNetV3-S | TuningIQA · FGLive-10K test | FG-ACC: 0.7065 -> 0.7284 | Improved |
| pairwise fine-grained ranking instead of score-based ranking | TuningIQA · camera tuning top-1 subjective test | win rate: 76% and 74% win rates against LIQE and MUSIQ | Improved |
Closest papers by meaning
- Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment (TPAMI 2021 · similarity 0.86)
- Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models (TPAMI 2024 · similarity 0.86)
- Scaling-up Perceptual Video Quality Assessment (AAAI 2026 · similarity 0.85)
- Semi-Supervised Blind Image Quality Assessment through Knowledge Distillation and Incremental Learning (AAAI 2024 · similarity 0.83)
- Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption (CVPR 2025 · similarity 0.83)
- Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare (NeurIPS 2024 · similarity 0.83)
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.
