{"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/qpic-query-based-pairwise-human-object","title":"QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information","arxiv_id":"2103.05399","date":"2021-03-09","proceeding":"CVPR 2021 1","authors":["Masato Tamura","Hiroki Ohashi","Tomoaki Yoshinaga"],"abstract":"We propose a simple, intuitive yet powerful method for human-object interaction (HOI) detection. HOIs are so diverse in spatial distribution in an image that existing CNN-based methods face the following three major drawbacks; they cannot leverage image-wide features due to CNN's locality, they rely on a manually defined location-of-interest for the feature aggregation, which sometimes does not cover contextually important regions, and they cannot help but mix up the features for multiple HOI instances if they are located closely. To overcome these drawbacks, we propose a transformer-based feature extractor, in which an attention mechanism and query-based detection play key roles. The attention mechanism is effective in aggregating contextually important information image-wide, while the queries, which we design in such a way that each query captures at most one human-object pair, can avoid mixing up the features from multiple instances. This transformer-based feature extractor produces so effective embeddings that the subsequent detection heads may be fairly simple and intuitive. The extensive analysis reveals that the proposed method successfully extracts contextually important features, and thus outperforms existing methods by large margins (5.37 mAP on HICO-DET, and 5.7 mAP on V-COCO). The source codes are available at $\\href{https://github.com/hitachi-rd-cv/qpic}{\\text{this https URL}}$.","url_abs":"https://arxiv.org/abs/2103.05399v1","url_pdf":"https://arxiv.org/pdf/2103.05399v1.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":"qpic-query-based-pairwise-human-object","repo_url":"https://github.com/hitachi-rd-cv/qpic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"human-object-interaction-concept-discovery","task_name":"Human-Object Interaction Concept Discovery"},{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-object-interaction-concept-discovery-on","task":"Human-Object Interaction Concept Discovery","dataset":"HICO-DET","model":"Qpic","rank_in_archive_order":2,"of":3,"metrics":{"Unknown (AP)":"27.42"},"uses_additional_data":false},{"leaderboard":"/sota/human-object-interaction-detection-on-hico","task":"Human-Object Interaction Detection","dataset":"HICO-DET","model":"QPIC (ResNet101)","rank_in_archive_order":27,"of":55,"metrics":{"Time Per Frame (ms)":"63","mAP":"29.90"},"uses_additional_data":true},{"leaderboard":"/sota/human-object-interaction-detection-on-hico","task":"Human-Object Interaction Detection","dataset":"HICO-DET","model":"QPIC (ResNet50)","rank_in_archive_order":30,"of":55,"metrics":{"Time Per Frame (ms)":"46","mAP":"29.07"},"uses_additional_data":true},{"leaderboard":"/sota/human-object-interaction-detection-on-v-coco","task":"Human-Object Interaction Detection","dataset":"V-COCO","model":"QPIC (ResNet50)","rank_in_archive_order":13,"of":34,"metrics":{"AP(S1)":"58.8","AP(S2)":"61.0","Time Per Frame(ms)":"46"},"uses_additional_data":false},{"leaderboard":"/sota/human-object-interaction-detection-on-v-coco","task":"Human-Object Interaction Detection","dataset":"V-COCO","model":"QPIC (ResNet101)","rank_in_archive_order":14,"of":34,"metrics":{"AP(S1)":"58.3","AP(S2)":"60.7","Time Per Frame(ms)":"63"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.05399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.05399"}},"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":"deterministic:regex_extraction","url":"https://github.com/hitachi-rd-cv/qpic","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"111b2ff51d39b77d","entry":"DETRHOI","repo":"hitachi-rd-cv/qpic","repo_kind":"official","path":"models/hoi.py","file_url":"https://github.com/hitachi-rd-cv/qpic/blob/HEAD/models/hoi.py","link_basis":"first_harvest_node","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":"111b2ff51d39b77d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}