{"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/spatio-attentive-graphs-for-human-object","title":"Spatially Conditioned Graphs for Detecting Human-Object Interactions","arxiv_id":"2012.06060","date":"2020-12-11","proceeding":"ICCV 2021 10","authors":["Frederic Z. Zhang","Dylan Campbell","Stephen Gould"],"abstract":"We address the problem of detecting human-object interactions in images using graphical neural networks. Unlike conventional methods, where nodes send scaled but otherwise identical messages to each of their neighbours, we propose to condition messages between pairs of nodes on their spatial relationships, resulting in different messages going to neighbours of the same node. To this end, we explore various ways of applying spatial conditioning under a multi-branch structure. Through extensive experimentation we demonstrate the advantages of spatial conditioning for the computation of the adjacency structure, messages and the refined graph features. In particular, we empirically show that as the quality of the bounding boxes increases, their coarse appearance features contribute relatively less to the disambiguation of interactions compared to the spatial information. Our method achieves an mAP of 31.33% on HICO-DET and 54.2% on V-COCO, significantly outperforming state-of-the-art on fine-tuned detections.","url_abs":"https://arxiv.org/abs/2012.06060v3","url_pdf":"https://arxiv.org/pdf/2012.06060v3.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":"spatio-attentive-graphs-for-human-object","repo_url":"https://github.com/fredzzhang/spatially-conditioned-graphs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"spatio-attentive-graphs-for-human-object","repo_url":"https://github.com/fredzzhang/hicodet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-object-interaction-detection-on-hico","task":"Human-Object Interaction Detection","dataset":"HICO-DET","model":"SCG (DETR-R101)","rank_in_archive_order":29,"of":55,"metrics":{"mAP":"29.26"},"uses_additional_data":false},{"leaderboard":"/sota/human-object-interaction-detection-on-v-coco","task":"Human-Object Interaction Detection","dataset":"V-COCO","model":"SCG","rank_in_archive_order":18,"of":34,"metrics":{"AP(S1)":"54.2","AP(S2)":"60.9","Time Per Frame(ms)":"500"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.06060","atlas_url":"https://app.syntology.ai/?focus=2012.06060","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}