Open access
Aug 2026
Context-aware image captioning using cosine transformer attention and optimal vision transformer with improved walrus optimization algorithm
A new encoder-decoder architecture, that utilizes optimal vision transformer + attention to the transformer by using cosine distance in order to get more context by providing better mapping and outputs with better contextual details and flow of natural language, semantic fidelity.
Madhvi Patel, Dhirendra Pratap Singh, Jaytrilok Choudhary et al.
· Scientific Reports · 0 citations