Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers
Hendricks, Lisa Anne, Mellor, John, Schneider, Rosalia, Alayrac, Jean-Baptiste, Nematzadeh, Aida·2021·Transactions of the Association for Computational Linguistics
Cited by (101)
Items 101–101 of 101
- Cross-modal dual-branch parallel hybrid matching for text-to-image person retrievalMian Hu, Jie Xu, Haoran Li, Chen Xu, Yuan Yan Tang · 2026 · Neurocomputing