QR Code

Visual Question Answering Model Based on Spatial Relation and Frequency Feature

As an important task in multimodal data processing, Visual Question Answering(VQA) needs to associate and represent information from different modalities.However, existing VQA models can not effectively distinguish similar target objects and can not accurately express the spatial relationship betwee...

Whakaahuatanga katoa

I tiakina i:
Kaituhi matua: FU Pengcheng, YANG Guan, LIU Xiaoming, LIU Yang, ZHANG Ziming, CHENG Xi
Hōputu: Artigo
Reo:Inglês
I whakaputaina: Editorial Office of Computer Engineering 2022-09-01
Rangatū:Jisuanji gongcheng
Ngā marau:
discrete cosine transform(dct)|fine-grained identification|relation network(rn)|attention mechanism|feature fusion
Urunga tuihono:https://www.ecice06.com/fileup/1000-3428/PDF/20220912.pdf
Ngā Tūtohu: Tāpirihia he Tūtohu
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!

Ngā tūemi rite