{"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/deep-cnn-frame-interpolation-with-lessons","title":"Deep CNN Frame Interpolation with Lessons Learned from Natural Language Processing","arxiv_id":"1809.05286","date":"2018-09-14","proceeding":null,"authors":["Kian Ghodoussi","Nihar Sheth","Zane Durante","Markie Wagner"],"abstract":"A major area of growth within deep learning has been the study and\nimplementation of convolutional neural networks. The general explanation within\nthe deep learning community of the robustness of convolutional neural networks\n(CNNs) within image recognition rests upon the idea that CNNs are able to\nextract localized features. However, recent developments in fields such as\nNatural Language Processing are demonstrating that this paradigm may be\nincorrect. In this paper, we analyze the current state of the field concerning\nCNN's and present a hypothesis that provides a novel explanation for the\nrobustness of CNN models. From there, we demonstrate the effectiveness of our\napproach by presenting novel deep CNN frame interpolation architecture that is\ncomparable to the state of the art interpolation models with a fraction of the\ncomplexity.","url_abs":"http://arxiv.org/abs/1809.05286v2","url_pdf":"http://arxiv.org/pdf/1809.05286v2.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":"deep-cnn-frame-interpolation-with-lessons","repo_url":"https://github.com/ghodouss/Aperio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}