@misc{lian2025describe, title={Describe Anything: Detailed Localized Image and Video Captioning}, author={Long Lian and Yifan Ding and Yunhao Ge and Sifei Liu and Hanzi Mao and Boyi Li and Marco Pavone and Ming-Yu Liu and Trevor Darrell and Adam Yala and Yin Cui}, year={2025}, eprint={2504.16072}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2504.16072} }