{"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/user-constrained-thumbnail-generation-using","title":"User Constrained Thumbnail Generation using Adaptive Convolutions","arxiv_id":"1810.13054","date":"2018-10-31","proceeding":null,"authors":["Perla Sai Raj Kishore","Ayan Kumar Bhunia","Shuvozit Ghose","Partha Pratim Roy"],"abstract":"Thumbnails are widely used all over the world as a preview for digital\nimages. In this work we propose a deep neural framework to generate thumbnails\nof any size and aspect ratio, even for unseen values during training, with high\naccuracy and precision. We use Global Context Aggregation (GCA) and a modified\nRegion Proposal Network (RPN) with adaptive convolutions to generate thumbnails\nin real time. GCA is used to selectively attend and aggregate the global\ncontext information from the entire image while the RPN is used to predict\ncandidate bounding boxes for the thumbnail image. Adaptive convolution\neliminates the problem of generating thumbnails of various aspect ratios by\nusing filter weights dynamically generated from the aspect ratio information.\nThe experimental results indicate the superior performance of the proposed\nmodel over existing state-of-the-art techniques.","url_abs":"http://arxiv.org/abs/1810.13054v3","url_pdf":"http://arxiv.org/pdf/1810.13054v3.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":"user-constrained-thumbnail-generation-using","repo_url":"https://github.com/sairajk/Thumbnail-Generation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"user-constrained-thumbnail-generation-using","repo_url":"https://github.com/Aiyoj/Thumbnail-Generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"user-constrained-thumbnail-generation","task_name":"User Constrained Thumbnail Generation"}],"methods":[{"method_slug":"rpn","method_name":"RPN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}