{"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/qahoi-query-based-anchors-for-human-object","title":"QAHOI: Query-Based Anchors for Human-Object Interaction Detection","arxiv_id":"2112.08647","date":"2021-12-16","proceeding":null,"authors":["Junwen Chen","Keiji Yanai"],"abstract":"Human-object interaction (HOI) detection as a downstream of object detection tasks requires localizing pairs of humans and objects and extracting the semantic relationships between humans and objects from an image. Recently, one-stage approaches have become a new trend for this task due to their high efficiency. However, these approaches focus on detecting possible interaction points or filtering human-object pairs, ignoring the variability in the location and size of different objects at spatial scales. To address this problem, we propose a transformer-based method, QAHOI (Query-Based Anchors for Human-Object Interaction detection), which leverages a multi-scale architecture to extract features from different spatial scales and uses query-based anchors to predict all the elements of an HOI instance. We further investigate that a powerful backbone significantly increases accuracy for QAHOI, and QAHOI with a transformer-based backbone outperforms recent state-of-the-art methods by large margins on the HICO-DET benchmark. The source code is available at $\\href{https://github.com/cjw2021/QAHOI}{\\text{this https URL}}$.","url_abs":"https://arxiv.org/abs/2112.08647v1","url_pdf":"https://arxiv.org/pdf/2112.08647v1.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":"qahoi-query-based-anchors-for-human-object","repo_url":"https://github.com/cjw2021/QAHOI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-object-interaction-detection-on-hico","task":"Human-Object Interaction Detection","dataset":"HICO-DET","model":"QAHOI (Swin-L)","rank_in_archive_order":10,"of":55,"metrics":{"mAP":"35.78"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.08647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.08647"}},"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/cjw2021/QAHOI","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":2,"ran_violates":1,"ran":4,"ran_honours":1,"ran_draft_wrong":2,"unverified":5},"by_repo_kind":{"official":{"samples":15,"ran":10,"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":"144d10b49baeb8a6","entry":"window_partition","repo":"cjw2021/QAHOI","repo_kind":"official","path":"models/swin_transformer.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/models/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"3dc1dc492dbbbf13","entry":"clip_xyxy_to_image","repo":"cjw2021/QAHOI","repo_kind":"official","path":"vsrl_eval.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/vsrl_eval.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3dc1dc492dbbbf13"}},{"code_sha256_prefix":"74f3f5c1bab38c14","entry":"crop","repo":"cjw2021/QAHOI","repo_kind":"official","path":"datasets/transforms.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/datasets/transforms.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74f3f5c1bab38c14"}},{"code_sha256_prefix":"fd3666d3bd51e693","entry":"draw_umich_gaussian","repo":"cjw2021/QAHOI","repo_kind":"official","path":"datasets/hico.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/datasets/hico.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fd3666d3bd51e693"}},{"code_sha256_prefix":"f2a33236566ea043","entry":"gaussian_radius","repo":"cjw2021/QAHOI","repo_kind":"official","path":"datasets/hico.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/datasets/hico.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f2a33236566ea043"}},{"code_sha256_prefix":"d5a0b6aba0d66951","entry":"get_overlap","repo":"cjw2021/QAHOI","repo_kind":"official","path":"vsrl_eval.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/vsrl_eval.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d5a0b6aba0d66951"}},{"code_sha256_prefix":"9be9e658b5bd688a","entry":"hflip","repo":"cjw2021/QAHOI","repo_kind":"official","path":"datasets/transforms.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/datasets/transforms.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9be9e658b5bd688a"}},{"code_sha256_prefix":"5c0711aada67957e","entry":"sigmoid_focal_loss","repo":"cjw2021/QAHOI","repo_kind":"official","path":"models/QAHOI.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/models/QAHOI.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"code_sha256_prefix":"7c16bfea33d37328","entry":"voc_ap","repo":"cjw2021/QAHOI","repo_kind":"official","path":"vsrl_eval.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/vsrl_eval.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7c16bfea33d37328"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"cjw2021/QAHOI","repo_kind":"official","path":"models/swin_transformer.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/models/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"5f8551dd0fb2cf55","entry":"compute_area","repo":"cjw2021/QAHOI","repo_kind":"official","path":"datasets/hico_eval.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/datasets/hico_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5f8551dd0fb2cf55"}},{"code_sha256_prefix":"d00ab1027f478b6d","entry":"compute_iou","repo":"cjw2021/QAHOI","repo_kind":"official","path":"datasets/hico_eval.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/datasets/hico_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d00ab1027f478b6d"}},{"code_sha256_prefix":"86282b7f90be63f2","entry":"gaussian2D","repo":"cjw2021/QAHOI","repo_kind":"official","path":"datasets/hico.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/datasets/hico.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86282b7f90be63f2"}},{"code_sha256_prefix":"063310ab1ea2c2f4","entry":"load_checkpoint","repo":"cjw2021/QAHOI","repo_kind":"official","path":"models/swin_transformer.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/models/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"063310ab1ea2c2f4"}},{"code_sha256_prefix":"0c28a11db2ae313e","entry":"match_hoi","repo":"cjw2021/QAHOI","repo_kind":"official","path":"datasets/hico_eval.py","file_url":"https://github.com/cjw2021/QAHOI/blob/HEAD/datasets/hico_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0c28a11db2ae313e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}