{"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/vsgnet-spatial-attention-network-for","title":"VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions","arxiv_id":"2003.05541","date":"2020-03-11","proceeding":"CVPR 2020 6","authors":["Oytun Ulutan","A. S. M. Iftekhar","B. S. Manjunath"],"abstract":"Comprehensive visual understanding requires detection frameworks that can effectively learn and utilize object interactions while analyzing objects individually. This is the main objective in Human-Object Interaction (HOI) detection task. In particular, relative spatial reasoning and structural connections between objects are essential cues for analyzing interactions, which is addressed by the proposed Visual-Spatial-Graph Network (VSGNet) architecture. VSGNet extracts visual features from the human-object pairs, refines the features with spatial configurations of the pair, and utilizes the structural connections between the pair via graph convolutions. The performance of VSGNet is thoroughly evaluated using the Verbs in COCO (V-COCO) and HICO-DET datasets. Experimental results indicate that VSGNet outperforms state-of-the-art solutions by 8% or 4 mAP in V-COCO and 16% or 3 mAP in HICO-DET.","url_abs":"https://arxiv.org/abs/2003.05541v1","url_pdf":"https://arxiv.org/pdf/2003.05541v1.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":"vsgnet-spatial-attention-network-for","repo_url":"https://github.com/ASMIftekhar/VSGNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"vsgnet-spatial-attention-network-for","repo_url":"https://github.com/UCSB-VRL/GTNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"spatial-reasoning","task_name":"Spatial Reasoning"}],"methods":[{"method_slug":"vsgnet","method_name":"VSGNet"}],"datasets_introduced":[],"methods_introduced":[{"slug":"vsgnet","name":"VSGNet","full_name":"Visual-Spatial-Graph Network"}],"results":[{"leaderboard":"/sota/human-object-interaction-detection-on-hico","task":"Human-Object Interaction Detection","dataset":"HICO-DET","model":"VSGNet","rank_in_archive_order":50,"of":55,"metrics":{"mAP":"19.8"},"uses_additional_data":false},{"leaderboard":"/sota/human-object-interaction-detection-on-v-coco","task":"Human-Object Interaction Detection","dataset":"V-COCO","model":"VSGNet","rank_in_archive_order":24,"of":34,"metrics":{"AP(S1)":"51.76","AP(S2)":"57.0","Time Per Frame(ms)":"312"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.05541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05541"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/UCSB-VRL/GTNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ASMIftekhar/VSGNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c9b8d2d5da5a251d","entry":"compute_ap","repo":"ASMIftekhar/VSGNet","repo_kind":"official","path":"scripts_hico/HICO_eval/compute_map.py","file_url":"https://github.com/ASMIftekhar/VSGNet/blob/HEAD/scripts_hico/HICO_eval/compute_map.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9b8d2d5da5a251d"}},{"code_sha256_prefix":"5f8551dd0fb2cf55","entry":"compute_area","repo":"ASMIftekhar/VSGNet","repo_kind":"official","path":"scripts_hico/HICO_eval/bbox_utils.py","file_url":"https://github.com/ASMIftekhar/VSGNet/blob/HEAD/scripts_hico/HICO_eval/bbox_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f8551dd0fb2cf55"}},{"code_sha256_prefix":"5c81f0f6cf474579","entry":"compute_area_batch","repo":"ASMIftekhar/VSGNet","repo_kind":"official","path":"scripts_hico/HICO_eval/bbox_utils.py","file_url":"https://github.com/ASMIftekhar/VSGNet/blob/HEAD/scripts_hico/HICO_eval/bbox_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c81f0f6cf474579"}},{"code_sha256_prefix":"d342aa66e09cb8a9","entry":"compute_iou","repo":"ASMIftekhar/VSGNet","repo_kind":"official","path":"scripts_hico/HICO_eval/bbox_utils.py","file_url":"https://github.com/ASMIftekhar/VSGNet/blob/HEAD/scripts_hico/HICO_eval/bbox_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d342aa66e09cb8a9"}},{"code_sha256_prefix":"7eba67cf40d2079c","entry":"compute_pr","repo":"ASMIftekhar/VSGNet","repo_kind":"official","path":"scripts_hico/HICO_eval/compute_map.py","file_url":"https://github.com/ASMIftekhar/VSGNet/blob/HEAD/scripts_hico/HICO_eval/compute_map.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7eba67cf40d2079c"}},{"code_sha256_prefix":"6c82cba89895242a","entry":"dumps_json_object","repo":"ASMIftekhar/VSGNet","repo_kind":"official","path":"scripts_hico/HICO_eval/load.py","file_url":"https://github.com/ASMIftekhar/VSGNet/blob/HEAD/scripts_hico/HICO_eval/load.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c82cba89895242a"}},{"code_sha256_prefix":"fbb293b5e43e3fa4","entry":"load_json_object","repo":"ASMIftekhar/VSGNet","repo_kind":"official","path":"scripts_hico/HICO_eval/load.py","file_url":"https://github.com/ASMIftekhar/VSGNet/blob/HEAD/scripts_hico/HICO_eval/load.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbb293b5e43e3fa4"}},{"code_sha256_prefix":"f9531bd8a2f31c23","entry":"load_pickle_object","repo":"ASMIftekhar/VSGNet","repo_kind":"official","path":"scripts_hico/HICO_eval/load.py","file_url":"https://github.com/ASMIftekhar/VSGNet/blob/HEAD/scripts_hico/HICO_eval/load.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9531bd8a2f31c23"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}