作者位次 #4/7ACL 2026Poster· Natural Language Processing
OSCB ench: Benchmarking Object State Change in Text-to-Video Generation
Xianjing Han · Bin Zhu · Shiqi Hu · Franklin Mingzhe Li · Patrick Carrington · Roger Zimmermann · Jingjing Chen
摘要
Text-to-video (T2V) generation models have made rapid progress in producing visually high-quality and temporally coherent videos. However, existing benchmarks primarily focus on perceptual quality, text–video alignment, or physical plausibility, leaving a critical aspect of action understanding l...