VAA: Visual Aligning Attention Model for Remote Sensing Image Captioning

Owing to the effectiveness in selectively focusing on regions of interest of images, the attention mechanism has been widely used in image caption task, which can provide more accurate image information for training deep sequential models. Existing attention-based models typically rely on top-down a...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Zhengyuan Zhang, Wenkai Zhang, Wenhui Diao, Menglong Yan, Xin Gao, Xian Sun
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IEEE 2019-01-01
Edice:	IEEE Access
Témata:	Image captioning remote sensing image captioning attention mechanism visual aligning
On-line přístup:	https://ieeexplore.ieee.org/document/8843891/
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!