{"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/deeply-supervised-multimodal-attentional","title":"Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection","arxiv_id":"1902.05829","date":"2019-02-15","proceeding":null,"authors":["Nikolaos Gkanatsios","Vassilis Pitsikalis","Petros Koutras","Athanasia Zlatintsi","Petros Maragos"],"abstract":"Detecting visual relationships, i.e. <Subject, Predicate, Object> triplets,\nis a challenging Scene Understanding task approached in the past via linguistic\npriors or spatial information in a single feature branch. We introduce a new\ndeeply supervised two-branch architecture, the Multimodal Attentional\nTranslation Embeddings, where the visual features of each branch are driven by\na multimodal attentional mechanism that exploits spatio-linguistic similarities\nin a low-dimensional space. We present a variety of experiments comparing\nagainst all related approaches in the literature, as well as by re-implementing\nand fine-tuning several of them. Results on the commonly employed VRD dataset\n[1] show that the proposed method clearly outperforms all others, while we also\njustify our claims both quantitatively and qualitatively.","url_abs":"http://arxiv.org/abs/1902.05829v1","url_pdf":"http://arxiv.org/pdf/1902.05829v1.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":"deeply-supervised-multimodal-attentional","repo_url":"https://bitbucket.org/deeplabai/vrd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"relationship-detection","task_name":"Relationship Detection"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"visual-relationship-detection","task_name":"Visual Relationship Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.05829","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}