A survey of attention-based transformer image captioning models with a multilingual focus, compiling prior methods, datasets, and metrics without new experiments.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Attention-based transformer models for image captioning across languages: An in-depth survey and evaluation
A survey of attention-based transformer image captioning models with a multilingual focus, compiling prior methods, datasets, and metrics without new experiments.