{"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/picture-it-in-your-mind-generating-high-level","title":"Picture It In Your Mind: Generating High Level Visual Representations From Textual Descriptions","arxiv_id":"1606.07287","date":"2016-06-23","proceeding":null,"authors":["Fabio Carrara","Andrea Esuli","Tiziano Fagni","Fabrizio Falchi","Alejandro Moreo Fernández"],"abstract":"In this paper we tackle the problem of image search when the query is a short\ntextual description of the image the user is looking for. We choose to\nimplement the actual search process as a similarity search in a visual feature\nspace, by learning to translate a textual query into a visual representation.\nSearching in the visual feature space has the advantage that any update to the\ntranslation model does not require to reprocess the, typically huge, image\ncollection on which the search is performed. We propose Text2Vis, a neural\nnetwork that generates a visual representation, in the visual feature space of\nthe fc6-fc7 layers of ImageNet, from a short descriptive text. Text2Vis\noptimizes two loss functions, using a stochastic loss-selection method. A\nvisual-focused loss is aimed at learning the actual text-to-visual feature\nmapping, while a text-focused loss is aimed at modeling the higher-level\nsemantic concepts expressed in language and countering the overfit on\nnon-relevant visual components of the visual loss. We report preliminary\nresults on the MS-COCO dataset.","url_abs":"http://arxiv.org/abs/1606.07287v1","url_pdf":"http://arxiv.org/pdf/1606.07287v1.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":"picture-it-in-your-mind-generating-high-level","repo_url":"https://github.com/AlexMoreo/tensorflow-Tex2Vis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"picture-it-in-your-mind-generating-high-level","repo_url":"https://github.com/AlexMoreo/tensorflow-Text2Vis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"cross-modal-information-retrieval","task_name":"Cross-Modal Information Retrieval"},{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}