{"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/st-hoi-a-spatial-temporal-baseline-for-human","title":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","arxiv_id":"2105.11731","date":"2021-05-25","proceeding":null,"authors":["Meng-Jiun Chiou","Chun-Yu Liao","Li-Wei Wang","Roger Zimmermann","Jiashi Feng"],"abstract":"Detecting human-object interactions (HOI) is an important step toward a comprehensive visual understanding of machines. While detecting non-temporal HOIs (e.g., sitting on a chair) from static images is feasible, it is unlikely even for humans to guess temporal-related HOIs (e.g., opening/closing a door) from a single video frame, where the neighboring frames play an essential role. However, conventional HOI methods operating on only static images have been used to predict temporal-related interactions, which is essentially guessing without temporal contexts and may lead to sub-optimal performance. In this paper, we bridge this gap by detecting video-based HOIs with explicit temporal information. We first show that a naive temporal-aware variant of a common action detection baseline does not work on video-based HOIs due to a feature-inconsistency issue. We then propose a simple yet effective architecture named Spatial-Temporal HOI Detection (ST-HOI) utilizing temporal information such as human and object trajectories, correctly-localized visual features, and spatial-temporal masking pose features. We construct a new video HOI benchmark dubbed VidHOI where our proposed approach serves as a solid baseline.","url_abs":"https://arxiv.org/abs/2105.11731v2","url_pdf":"https://arxiv.org/pdf/2105.11731v2.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":"st-hoi-a-spatial-temporal-baseline-for-human","repo_url":"https://github.com/coldmanck/VidHOI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"human-object-interaction-anticipation","task_name":"Human-Object Interaction Anticipation"},{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"spatio-temporal-action-localization","task_name":"Spatio-Temporal Action Localization"}],"methods":[],"datasets_introduced":[{"slug":"vidhoi","name":"VidHOI","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-object-interaction-anticipation-on","task":"Human-Object Interaction Anticipation","dataset":"VidHOI","model":"STTRAN","rank_in_archive_order":3,"of":3,"metrics":{"Person-wise Top5: t=1(mAP@0.5)":"29.09","Person-wise Top5: t=3(mAP@0.5)":"27.59","Person-wise Top5: t=5(mAP@0.5)":"27.32"},"uses_additional_data":false},{"leaderboard":"/sota/human-object-interaction-detection-on-vidhoi","task":"Human-Object Interaction Detection","dataset":"VidHOI","model":"STTRAN","rank_in_archive_order":3,"of":3,"metrics":{"Detection: Full (mAP@0.5)":"7.61","Detection: Non-Rare (mAP@0.5)":"13.18","Detection: Rare (mAP@0.5)":"3.33","Oracle: Full (mAP@0.5)":"28.32","Oracle: Non-Rare (mAP@0.5)":"42.08","Oracle: Rare (mAP@0.5)":"17.74"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.11731","atlas_url":"https://app.syntology.ai/?focus=2105.11731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11731"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/coldmanck/VidHOI","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"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":4,"samples":[{"code_sha256_prefix":"c90b5f606f54d4f7","entry":"get_loss_func","repo":"coldmanck/VidHOI","repo_kind":"official","path":"slowfast/models/losses.py","file_url":"https://github.com/coldmanck/VidHOI/blob/HEAD/slowfast/models/losses.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":false,"mcp_get_code":{"code_sha256":"c90b5f606f54d4f7"}},{"code_sha256_prefix":"75c62c582a31b362","entry":"construct_optimizer","repo":"coldmanck/VidHOI","repo_kind":"official","path":"slowfast/models/optimizer.py","file_url":"https://github.com/coldmanck/VidHOI/blob/HEAD/slowfast/models/optimizer.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":false,"mcp_get_code":{"code_sha256":"75c62c582a31b362"}},{"code_sha256_prefix":"4d6991202a8d6097","entry":"get_trans_func","repo":"coldmanck/VidHOI","repo_kind":"official","path":"slowfast/models/resnet_helper.py","file_url":"https://github.com/coldmanck/VidHOI/blob/HEAD/slowfast/models/resnet_helper.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":false,"mcp_get_code":{"code_sha256":"4d6991202a8d6097"}},{"code_sha256_prefix":"e702f7e23a23d4d5","entry":"interaction_inference_single_image","repo":"coldmanck/VidHOI","repo_kind":"official","path":"slowfast/models/fast_rcnn.py","file_url":"https://github.com/coldmanck/VidHOI/blob/HEAD/slowfast/models/fast_rcnn.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":false,"mcp_get_code":{"code_sha256":"e702f7e23a23d4d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}