Search Results for author:
Found 3 papers, 2 papers with code
Cross-media Multi-level Alignment with Relation Attention Network
First, we propose visual-language relation attention model to explore both fine-grained patches and their relations of different media types.
CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning
They can not only exploit cross-modal correlation for learning common representation, but also preserve reconstruction information for capturing semantic consistency within each modality.
Modality-specific Cross-modal Similarity Measurement with Recurrent Attention Network
Effectively measuring the similarity between different modalities of data is the key of cross-modal retrieval.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
