[Elsevier] GTA: Geometric transform-attention network for enhanced spatial reasoning in image captioning |
|
This post will be closed automatically in 2026-10-25 19:18
Reward10points
|
post
reply
points
2060
10
Impact of Multiple Beams on the FLASH Effect in Soft Tissue and Skin in Mice
10
Optimization of dye-contaminated wastewater treatment by fungal Mycelial-light expanded clay aggregate composite
10
Targeting mitochondrial dysfunction in atopic dermatitis with trilinolein: A triacylglycerol from the medicinal plant Cannabis fructus
30
Impact of circular economy information on sensory acceptability, purchase intention and perceived value of upcycled foods by young consumers
10
Higher-order object relation network with triple attention transformer decoder for image captioning
