{"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/recurrent-convolutional-fusion-for-rgb-d","title":"Recurrent Convolutional Fusion for RGB-D Object Recognition","arxiv_id":"1806.01673","date":"2018-06-05","proceeding":null,"authors":["Mohammad Reza Loghmani","Mirco Planamente","Barbara Caputo","Markus Vincze"],"abstract":"Providing machines with the ability to recognize objects like humans has\nalways been one of the primary goals of machine vision. The introduction of\nRGB-D cameras has paved the way for a significant leap forward in this\ndirection thanks to the rich information provided by these sensors. However,\nthe machine vision community still lacks an effective method to synergically\nuse the RGB and depth data to improve object recognition. In order to take a\nstep in this direction, we introduce a novel end-to-end architecture for RGB-D\nobject recognition called recurrent convolutional fusion (RCFusion). Our method\ngenerates compact and highly discriminative multi-modal features by combining\ncomplementary RGB and depth information representing different levels of\nabstraction. Extensive experiments on two popular datasets, RGB-D Object\nDataset and JHUIT-50, show that RCFusion significantly outperforms\nstate-of-the-art approaches in both the object categorization and instance\nrecognition tasks.","url_abs":"http://arxiv.org/abs/1806.01673v3","url_pdf":"http://arxiv.org/pdf/1806.01673v3.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":"recurrent-convolutional-fusion-for-rgb-d","repo_url":"https://github.com/MRLoghmani/rcfusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-categorization","task_name":"Object Categorization"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.01673","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}