Research map / Video / Video-language understanding
Score2Instruct: Scaling Up Video Quality-Centric Instructions via Automated Dimension Scoring
Qizhi Xie, Kun Yuan, Yunpeng Qu, Jiachao Gong, Mingda Wu, Ming Sun, Chao Zhou, Jihong Zhu
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 |
|---|---|---|---|
| instruction tune on S2I | LLaVA-OneVision · S2I-Bench | VCG sum: 7.96 -> 9.88 | Improved |
| instruction tune on S2I | six video LMMs · S2I-Bench | VCG sum: average +1.39 | Improved |
| instruction tune on S2I | LLaVA-OneVision · LSVQ-1080p | SRCC: 0.337 -> 0.671 | Improved |
| instruction tune on S2I | LLaVA-Next-Video · LIVE-VQC | SRCC: 0.406 -> 0.526 | Improved |
| add labeled VQA videos to unlabeled videos (ablation) | S2I · S2I-Bench | CI: 2.44 -> 3.02 | Improved |
| add unlabeled general videos to labeled videos (ablation) | S2I · Maxwell | SRCC: 0.506 -> 0.795 | Improved |
| add hierarchical CoT design (ablation) | S2I · S2I-Bench | VCG total: total decline of 0.27 without it | Improved |
| add high-level caption refinement (ablation) | S2I · S2I-Bench | CI: 2.54 -> 3.02 | Improved |
| add prompt keeping rating levels unchanged (ablation) | S2I · Maxwell | SRCC: 0.604 -> 0.795 | Improved |
| add stage I pretraining on dimension ratings (ablation) | S2I tuning · Maxwell | SRCC: 0.638 -> 0.795 | Improved |
| scale S2I training data from 20% to 100% (ablation) | S2I · Maxwell | SRCC: 0.623 -> 0.795 | Improved |
Closest papers by meaning
- Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs (CVPR 2025 · similarity 0.89)
- AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM (CVPR 2025 · similarity 0.88)
- VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment (AAAI 2025 · similarity 0.88)
- PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild (CVPR 2024 · similarity 0.87)
- Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels (ICML 2024 · similarity 0.87)
- Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare (NeurIPS 2024 · similarity 0.87)
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.
