{"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/situation-recognition-with-graph-neural","title":"Situation Recognition with Graph Neural Networks","arxiv_id":"1708.04320","date":"2017-08-14","proceeding":"ICCV 2017 10","authors":["Ruiyu Li","Makarand Tapaswi","Renjie Liao","Jiaya Jia","Raquel Urtasun","Sanja Fidler"],"abstract":"We address the problem of recognizing situations in images. Given an image,\nthe task is to predict the most salient verb (action), and fill its semantic\nroles such as who is performing the action, what is the source and target of\nthe action, etc. Different verbs have different roles (e.g. attacking has\nweapon), and each role can take on many possible values (nouns). We propose a\nmodel based on Graph Neural Networks that allows us to efficiently capture\njoint dependencies between roles using neural networks defined on a graph.\nExperiments with different graph connectivities show that our approach that\npropagates information between roles significantly outperforms existing work,\nas well as multiple baselines. We obtain roughly 3-5% improvement over previous\nwork in predicting the full situation. We also provide a thorough qualitative\nanalysis of our model and influence of different roles in the verbs.","url_abs":"http://arxiv.org/abs/1708.04320v1","url_pdf":"http://arxiv.org/pdf/1708.04320v1.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":"situation-recognition-with-graph-neural","repo_url":"https://github.com/thilinicooray/context-aware-reasoning-for-sr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"grounded-situation-recognition","task_name":"Grounded Situation Recognition"},{"task_slug":"situation-recognition","task_name":"Situation Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/grounded-situation-recognition-on-swig","task":"Grounded Situation Recognition","dataset":"SWiG","model":"GraphNet","rank_in_archive_order":10,"of":13,"metrics":{"Top-1 Verb":"36.72","Top-1 Verb & Value":"27.52","Top-5 Verbs":"61.90","Top-5 Verbs & Value":"45.39"},"uses_additional_data":false},{"leaderboard":"/sota/situation-recognition-on-imsitu","task":"Situation Recognition","dataset":"imSitu","model":"GraphNet","rank_in_archive_order":10,"of":13,"metrics":{"Top-1 Verb":"36.72","Top-1 Verb & Value":"27.52","Top-5 Verbs":"61.90","Top-5 Verbs & Value":"45.39"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.04320","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}