Dataset Groups Activity Stream DINOv2 The dataset used in the paper is DINOv2, a vision foundation model trained on a large-scale dataset. BibTex: @dataset{M_Oquab_and_T_Darcet_and_T_Moutakanni_and_H_Vo_and_M_Szafraniec_and_V_Khalidov_and_P_Fernandez_and_D_Haziza_and_F_Massa_and_A_El-Nouby_2024, abstract = {The dataset used in the paper is DINOv2, a vision foundation model trained on a large-scale dataset.}, author = {M. Oquab and T. Darcet and T. Moutakanni and H. Vo and M. Szafraniec and V. Khalidov and P. Fernandez and D. Haziza and F. Massa and A. El-Nouby}, doi = {10.57702/c7dxp393}, institution = {No Organization}, keyword = {'Computer Vision', 'DINOv2', 'Deep Learning', 'Self-supervised Vision Backbone', 'Vision Transformers', 'large-scale dataset', 'vision foundation model'}, month = {dec}, publisher = {TIB}, title = {DINOv2}, url = {https://service.tib.eu/ldmservice/dataset/dinov2}, year = {2024} }
