Research map / Video / Video generation
SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation
Ryosuke Matsuda, Keito Kudo, Haruto Yoshida, Nobuyuki Shimizu, Jun Suzuki
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 |
|---|---|---|---|
| Use human judges instead of automatic systems | long-video evaluation · SLVMEval (10 aspects) | accuracy: 84.7%-96.8% human | Improved |
| Compare GPT-5 video-based judge with humans on dynamics degree | GPT-5 · SLVMEval Dynamics degree | accuracy: 35.3 vs 95.9 | Hurt |
| Use text-based (caption) evaluation instead of video-based (ablation) | Qwen3-VL-235B · SLVMEval Background consistency | accuracy: 49.7 -> 73.0 | Improved |
| Use text-based (caption) evaluation instead of video-based (ablation) | Qwen3-VL-235B · SLVMEval Appearance style | accuracy: 55.3 -> 72.4 | Improved |
| Use text-based instead of video-based evaluation (ablation) | GPT-5 · SLVMEval Aesthetics | accuracy: 90.1 -> 74.8 | Hurt |
| Increase video duration | automatic evaluation systems · SLVMEval | accuracy | Mixed |
| Skip manual crowd filtering of degraded pairs (ablation) | SLVMEval construction · SLVMEval | system accuracy | No clear effect |
Closest papers by meaning
- Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability, Reproducibility, and Practicality (NeurIPS 2024 · similarity 0.89)
- EvalCrafter: Benchmarking and Evaluating Large Video Generation Models (CVPR 2024 · similarity 0.89)
- Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification (CVPR 2025 · similarity 0.89)
- Video-Bench: Human-Aligned Video Generation Benchmark (CVPR 2025 · similarity 0.88)
- ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation (NeurIPS 2024 · similarity 0.88)
- LVD-2M: A Long-take Video Dataset with Temporally Dense Captions (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.
