{"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/recovering-hidden-components-in-multimodal","title":"Recovering Hidden Components in Multimodal Data with Composite Diffusion Operators","arxiv_id":"1808.07312","date":"2018-08-22","proceeding":null,"authors":[],"abstract":"Finding appropriate low dimensional representations of high-dimensional\nmulti-modal data can be challenging, since each modality embodies unique\ndeformations and interferences. In this paper, we address the problem using\nmanifold learning, where the data from each modality is assumed to lie on some\nmanifold. In this context, the goal is to characterize the relations between\nthe different modalities by studying their underlying manifolds. We propose two\nnew diffusion operators that allow to isolate, enhance and attenuate the hidden\ncomponents of multi-modal data in a data-driven manner. Based on these new\noperators, efficient low-dimensional representations can be constructed for\nsuch data, which characterize the common structures and the differences between\nthe manifolds underlying the different modalities. The capabilities of the\nproposed operators are demonstrated on 3D shapes and on a fetal heart rate\nmonitoring application.","url_abs":"http://arxiv.org/abs/1808.07312v1","url_pdf":"http://arxiv.org/pdf/1808.07312v1.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":"recovering-hidden-components-in-multimodal","repo_url":"https://github.com/shnitzer/Recovering-hidden-components-in-multimodal-data","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.07312","atlas_url":"https://app.syntology.ai/?focus=1808.07312","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}