MMCAMulti-Modality Cross AttentionCross-modal Attention ModelsLanguage Is Not All You NeedViLBERTAsCL openaccess.thecvf.comhttps://openaccess.thecvf.com/content_CVPR_2020/papers/Wei_Multi-Modality_Cross_Attention_Network_for_Image_and_Sentence_Matching_CVPR_2020_paper.pdf