{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/image-and-encoded-text-fusion-for-multi-modal","title":"Image and Encoded Text Fusion for Multi-Modal Classification","arxiv_id":"1810.02001","date":"2018-10-03","proceeding":null,"authors":["Ignazio Gallo","Alessandro Calefati","Shah Nawaz","Muhammad Kamran Janjua"],"abstract":"Multi-modal approaches employ data from multiple input streams such as\ntextual and visual domains. Deep neural networks have been successfully\nemployed for these approaches. In this paper, we present a novel multi-modal\napproach that fuses images and text descriptions to improve multi-modal\nclassification performance in real-world scenarios. The proposed approach\nembeds an encoded text onto an image to obtain an information-enriched image.\nTo learn feature representations of resulting images, standard Convolutional\nNeural Networks (CNNs) are employed for the classification task. We demonstrate\nhow a CNN based pipeline can be used to learn representations of the novel\nfusion approach. We compare our approach with individual sources on two\nlarge-scale multi-modal classification datasets while obtaining encouraging\nresults. Furthermore, we evaluate our approach against two famous multi-modal\nstrategies namely early fusion and late fusion.","url_abs":"http://arxiv.org/abs/1810.02001v1","url_pdf":"http://arxiv.org/pdf/1810.02001v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"image-and-encoded-text-fusion-for-multi-modal","repo_url":"https://github.com/artelab/Multi-modal-classification","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-modal-classification","task_name":"Multi-modal Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}