Dual-Modal Transformer with Enhanced Inter- and Intra-Modality Interactions for Image Captioning

Image captioning is oriented towards describing an image with the best possible use of words that can provide a semantic, relatable meaning of the scenario inscribed. Different models can be used to accomplish this arduous task depending on the context and requirement of what needs to be achieved. A...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Deepika Kumar, Varun Srivastava, Daniela Elena Popescu, Jude D. Hemanth
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2022-07-01
Serija:	Applied Sciences
Teme:	attention model encoder–decoder model multi-modal transformer BLEU score beam search
Online dostop:	https://www.mdpi.com/2076-3417/12/13/6733
Oznake:	Označite Brez oznak, prvi označite!