Research map / Video / Video generation
LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation
Xiangqing Zheng, Chengyue Wu, Kehai Chen, Min Zhang
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 character removal (masking) to background consistency (ablation) | LoCoT2V-Eval BC · Human alignment | SRCC (%): 51.11 -> 30.98 | Hurt |
| use LoCoT2V-Eval instead of VBench-Long for overall alignment | human alignment · Human alignment, overall alignment | SRCC (%): 18.18 -> 67.23 | Improved |
| use LoCoT2V-Eval instead of VBench-Long for perceptual quality | human alignment · Human alignment, perceptual quality | SRCC (%): 50.69 -> 70.20 | Improved |
| use LoCoT2V-Eval instead of VBench-Long for character consistency | human alignment · Human alignment, character consistency | SRCC (%): 32.65 -> 49.90 | Improved |
| use LoCoT2V-Eval instead of VBench-Long for background consistency | human alignment · Human alignment, background consistency | SRCC (%): 35.38 -> 51.11 | Improved |
| use dual-agent Auditor-Evaluator HERD instead of QA-based or direct Qwen3-VL scoring (ablation) | HERD evaluation · Human alignment, HERD sub-dimensions | PLCC | Improved |
| use dual-agent HERD instead of QA-based evaluation for Visual Style (ablation) | HERD evaluation · Human alignment, Visual Style | PLCC | Hurt |
| prompt category Daily Life versus Virtual | evaluated LVG methods · LoCoT2V-Bench categories | overall score | Mixed |
Closest papers by meaning
- T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation (CVPR 2025 · similarity 0.91)
- StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text (CVPR 2025 · similarity 0.91)
- Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification (CVPR 2025 · similarity 0.90)
- Video-Bench: Human-Aligned Video Generation Benchmark (CVPR 2025 · similarity 0.90)
- EvalCrafter: Benchmarking and Evaluating Large Video Generation Models (CVPR 2024 · similarity 0.90)
- LVD-2M: A Long-take Video Dataset with Temporally Dense Captions (NeurIPS 2024 · similarity 0.89)
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.
