Learning visual and textual representations for multimodal matching and classification

Yu Liu, Li Liu, Yanming Guo, Michael S. Lew

Abstract: Highlights•A unified network for image-text matching and classification.•Seamlessly incorporating the matching and classification components.•A multi-stage training algorithm by combining the matching and classification loss.•Comprehensive study on the effectiveness of the proposed approach.•Comparisons on four well-known multimodal benchmarks.