{"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/order-embeddings-of-images-and-language","title":"Order-Embeddings of Images and Language","arxiv_id":"1511.06361","date":"2015-11-19","proceeding":null,"authors":["Ivan Vendrov","Ryan Kiros","Sanja Fidler","Raquel Urtasun"],"abstract":"Hypernymy, textual entailment, and image captioning can be seen as special\ncases of a single visual-semantic hierarchy over words, sentences, and images.\nIn this paper we advocate for explicitly modeling the partial order structure\nof this hierarchy. Towards this goal, we introduce a general method for\nlearning ordered representations, and show how it can be applied to a variety\nof tasks involving images and language. We show that the resulting\nrepresentations improve performance over current approaches for hypernym\nprediction and image-caption retrieval.","url_abs":"http://arxiv.org/abs/1511.06361v6","url_pdf":"http://arxiv.org/pdf/1511.06361v6.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":"order-embeddings-of-images-and-language","repo_url":"https://github.com/iesl/geometric_graph_embedding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"order-embeddings-of-images-and-language","repo_url":"https://github.com/ivendrov/order-embedding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"1024D GRU encoders w/ unsupervised 'skip-thoughts' pre-training","rank_in_archive_order":88,"of":98,"metrics":{"% Test Accuracy":"81.4","% Train Accuracy":"98.8","Parameters":"15m"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1511.06361","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}