US Patent 11373055 Bidirectional attention-based image-text cross-modal retrieval method

The present disclosure provides a bidirectional attention-based image-text cross-modal retrieval method, applicable for cross-modal retrieval between natural image and electronic text. The present disclosure extracts initial image and text features by using a neural network, and builds a bidirectional attention module to reconstruct the initial image and text features extracted by the neural network, the reconstructed features containing richer semantic information. By using the bidirectional attention module, the present disclosure improves the conventional feature extraction process, obtaining higher-order features with richer image and text semantics, thereby realizing image-text cross-modal retrieval.