Cite
Notes
Only stored in your browser.
Attribution
MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs
arXiv 2025
OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
arXiv 2024
InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption
CVPR 2025 1
from 3 papers
Jian Yang
Kepan Nan
Penghao Zhou
Rui Xie
Xiang Li
Ying Tai
Zhenheng Yang
Chaoyou Fu
Yipeng Du
Zhijie Chen