Follow
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts. (arXiv:2102.08981v1 [cs.CV]) http://arxiv.org/abs/2102.08981
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts. (arXiv:2102.08981v1 [cs.CV]) http://arxiv.org/abs/2102.08981