Litcius/Paper detail

MutualFormer: Multi-modal Representation Learning via Cross-Diffusion Attention

Xixi Wang, Xiao Wang, Bo Jiang, Jin Tang, Bin Luo

2024International Journal of Computer Vision11 citationsDOI

Topics & Concepts

Representation (politics)ModalPattern recognition (psychology)Artificial intelligenceComputer scienceDiffusionMaterials sciencePhysicsPoliticsThermodynamicsPolitical scienceLawPolymer chemistryMultimodal Machine Learning ApplicationsDomain Adaptation and Few-Shot LearningHuman Pose and Action Recognition
MutualFormer: Multi-modal Representation Learning via Cross-Diffusion Attention | Litcius