Cross-Media Scientific Research Achievements Retrieval Based on Deep Language Model
This addresses the need for more effective cross-media retrieval in science and technology big data, but it appears incremental as it builds on existing deep learning approaches for multimodal tasks.
The paper tackles the problem of retrieving scientific research achievements across different media types (images and texts) by proposing a deep language model-based method (CARDL) that learns semantic associations between modalities, achieving better cross-modal retrieval performance than existing methods.
Science and technology big data contain a lot of cross-media information.There are images and texts in the scientific paper.The s ingle modal search method cannot well meet the needs of scientific researchers.This paper proposes a cross-media scientific research achievements retrieval method based on deep language model (CARDL).It achieves a unified cross-media semantic representation by learning the semantic association between different modal data, and is applied to the generation of text semantic vector of scientific research achievements, and then cross-media retrieval is realized through semantic similarity matching between different modal data.Experimental results show that the proposed CARDL method achieves better cross-modal retrieval performance than existing methods. Key words science and technology big data ; cross-media retrieval; cross-media semantic association learning; deep language model; semantic similarity