A novel method for image captioning using multimodal feature fusion employing mask RNN and LSTM models.

Kumaravel ThangavelNatesan PalanisamySuresh MuthusamyOm Prava MishraSuma Christal Mary SundararajanHitesh PanchalAshok Kumar LoganathanPonarun Ramamoorthi
Published in: Soft Comput. (2023)
Keyphrases
  • multiscale
  • similarity measure
  • neural network
  • feature set
  • image representation
  • fusion method
  • image segmentation
  • preprocessing
  • pairwise
  • image features
  • nearest neighbor
  • image classification
  • model selection