Follow
VLDeformer: Learning Visual-Semantic Embeddings by Vision-Language Transformer Decomposing. (arXiv:2110.11338v1 [cs.CV]) http://arxiv.org/abs/2110.11338
VLDeformer: Learning Visual-Semantic Embeddings by Vision-Language Transformer Decomposing. (arXiv:2110.11338v1 [cs.CV]) http://arxiv.org/abs/2110.11338