{"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/conditional-image-text-embedding-networks","title":"Conditional Image-Text Embedding Networks","arxiv_id":"1711.08389","date":"2017-11-22","proceeding":"ECCV 2018 9","authors":["Bryan A. Plummer","Paige Kordas","M. Hadi Kiapour","Shuai Zheng","Robinson Piramuthu","Svetlana Lazebnik"],"abstract":"This paper presents an approach for grounding phrases in images which jointly\nlearns multiple text-conditioned embeddings in a single end-to-end model. In\norder to differentiate text phrases into semantically distinct subspaces, we\npropose a concept weight branch that automatically assigns phrases to\nembeddings, whereas prior works predefine such assignments. Our proposed\nsolution simplifies the representation requirements for individual embeddings\nand allows the underrepresented concepts to take advantage of the shared\nrepresentations before feeding them into concept-specific layers. Comprehensive\nexperiments verify the effectiveness of our approach across three phrase\ngrounding datasets, Flickr30K Entities, ReferIt Game, and Visual Genome, where\nwe obtain a (resp.) 4%, 3%, and 4% improvement in grounding performance over a\nstrong region-phrase embedding baseline.","url_abs":"http://arxiv.org/abs/1711.08389v4","url_pdf":"http://arxiv.org/pdf/1711.08389v4.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":"conditional-image-text-embedding-networks","repo_url":"https://github.com/BryanPlummer/cite","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"phrase-grounding","task_name":"Phrase Grounding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.08389","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}