{"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/learning-deep-structure-preserving-image-text","title":"Learning Deep Structure-Preserving Image-Text Embeddings","arxiv_id":"1511.06078","date":"2015-11-19","proceeding":"CVPR 2016 6","authors":["Liwei Wang","Yin Li","Svetlana Lazebnik"],"abstract":"This paper proposes a method for learning joint embeddings of images and text\nusing a two-branch neural network with multiple layers of linear projections\nfollowed by nonlinearities. The network is trained using a large margin\nobjective that combines cross-view ranking constraints with within-view\nneighborhood structure preservation constraints inspired by metric learning\nliterature. Extensive experiments show that our approach gains significant\nimprovements in accuracy for image-to-text and text-to-image retrieval. Our\nmethod achieves new state-of-the-art results on the Flickr30K and MSCOCO\nimage-sentence datasets and shows promise on the new task of phrase\nlocalization on the Flickr30K Entities dataset.","url_abs":"http://arxiv.org/abs/1511.06078v2","url_pdf":"http://arxiv.org/pdf/1511.06078v2.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":[],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"phrase-grounding","task_name":"Phrase Grounding"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-flickr30k-1k-test","task":"Image Retrieval","dataset":"Flickr30K 1K test","model":"SPE","rank_in_archive_order":15,"of":18,"metrics":{"R@1":"29.7","R@10":"72.1","R@5":"60.1"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-grounding-on-flickr30k-entities-test","task":"Phrase Grounding","dataset":"Flickr30k Entities Test","model":"DSPE","rank_in_archive_order":14,"of":18,"metrics":{"R@1":"43.89","R@10":"68.66","R@5":"64.46"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.06078","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}