Jul 2026
Task-specialized multi-modal fusion network for food nutrition estimation
This work designs a dual-backbone feature extraction architecture for food nutrition estimation, and introduces the Adaptive Spatial Feature Fusion (ASFF), which fuse ingredient semantic features with visual features through Softmax weighted interaction to enhance feature fusion.
Shu-Ying Hong, Dong-Lin Zhang, Xiao-Jun Wu
· Multimedia Systems · 0 citations