@inproceedings{groundingeverythingemerginglocalization, title = {Grounding Everything: Emerging Localization Properties in Vision-Language Transformers}, author = {Walid Bousselham and Felix Petersen and Vittorio Ferrari and Hilde Kuehne}, year = {2023}, booktitle = {CVPR 2024 1}, eprint = {2312.00878}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.00878v3}, }