{"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/towards-bridging-the-cross-modal-semantic-gap","title":"Towards Bridging the Cross-modal Semantic Gap for Multi-modal Recommendation","arxiv_id":"2407.05420","date":"2024-07-07","proceeding":null,"authors":["Xinglong Wu","Anfeng Huang","HongWei Yang","Hui He","Yu Tai","Weizhe Zhang"],"abstract":"Multi-modal recommendation greatly enhances the performance of recommender systems by modeling the auxiliary information from multi-modality contents. Most existing multi-modal recommendation models primarily exploit multimedia information propagation processes to enrich item representations and directly utilize modal-specific embedding vectors independently obtained from upstream pre-trained models. However, this might be inappropriate since the abundant task-specific semantics remain unexplored, and the cross-modality semantic gap hinders the recommendation performance. Inspired by the recent progress of the cross-modal alignment model CLIP, in this paper, we propose a novel \\textbf{CLIP} \\textbf{E}nhanced \\textbf{R}ecommender (\\textbf{CLIPER}) framework to bridge the semantic gap between modalities and extract fine-grained multi-view semantic information. Specifically, we introduce a multi-view modality-alignment approach for representation extraction and measure the semantic similarity between modalities. Furthermore, we integrate the multi-view multimedia representations into downstream recommendation models. Extensive experiments conducted on three public datasets demonstrate the consistent superiority of our model over state-of-the-art multi-modal recommendation models.","url_abs":"https://arxiv.org/abs/2407.05420v1","url_pdf":"https://arxiv.org/pdf/2407.05420v1.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":"towards-bridging-the-cross-modal-semantic-gap","repo_url":"https://github.com/WuXinglong-HIT/CLIPER","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-modal-recommendation","task_name":"Multi-modal Recommendation"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}