{"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/content-based-video-music-retrieval-using","title":"Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint","arxiv_id":"1704.06761","date":"2017-04-22","proceeding":null,"authors":["Sungeun Hong","Woobin Im","Hyun S. Yang"],"abstract":"Up to now, only limited research has been conducted on cross-modal retrieval\nof suitable music for a specified video or vice versa. Moreover, much of the\nexisting research relies on metadata such as keywords, tags, or associated\ndescription that must be individually produced and attached posterior. This\npaper introduces a new content-based, cross-modal retrieval method for video\nand music that is implemented through deep neural networks. We train the\nnetwork via inter-modal ranking loss such that videos and music with similar\nsemantics end up close together in the embedding space. However, if only the\ninter-modal ranking constraint is used for embedding, modality-specific\ncharacteristics can be lost. To address this problem, we propose a novel soft\nintra-modal structure loss that leverages the relative distance relationship\nbetween intra-modal samples before embedding. We also introduce reasonable\nquantitative and qualitative experimental protocols to solve the lack of\nstandard protocols for less-mature video-music related tasks. Finally, we\nconstruct a large-scale 200K video-music pair benchmark. All the datasets and\nsource code can be found in our online repository\n(https://github.com/csehong/VM-NET).","url_abs":"http://arxiv.org/abs/1704.06761v2","url_pdf":"http://arxiv.org/pdf/1704.06761v2.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":"content-based-video-music-retrieval-using","repo_url":"https://github.com/csehong/VM-NET","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"content-based-video-music-retrieval-using","repo_url":"https://github.com/morrisxu-driving/video-music_cross-modal_retrival","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.06761","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}