@article{240802272, title = {COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark}, author = {Koki Maeda and Tosho Hirasawa and Atsushi Hashimoto and Jun Harashima and Leszek Rybicki and Yusuke Fukasawa and Yoshitaka Ushiku}, year = {2024}, eprint = {2408.02272}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.02272v1}, }