{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:05:01Z","timestamp":1780495501315,"version":"3.54.1"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61966003"],"award-info":[{"award-number":["61966003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004607","name":"Guangxi Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113614","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T23:46:38Z","timestamp":1774395998000},"page":"113614","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Fine-grained mutual geometric features enhanced human-object interaction detection"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4585-4103","authenticated-orcid":false,"given":"Ri","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8311-1694","authenticated-orcid":false,"given":"Lin","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6492-6630","authenticated-orcid":false,"given":"Shengjie","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3919-2970","authenticated-orcid":false,"given":"Xiaoyu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113614_bib0001","series-title":"2018 IEEE Winter Conference on Applications of Computer Vision (WACV)","first-page":"381","article-title":"Learning to detect human-object interactions","author":"Chao","year":"2018"},{"key":"10.1016\/j.patcog.2026.113614_bib0002","series-title":"2023 IEEE International Conference on Image Processing (ICIP)","first-page":"271","article-title":"HOKEM: human and object keypoint-based extension module for human-object interaction detection","author":"Ito","year":"2023"},{"key":"10.1016\/j.patcog.2026.113614_bib0003","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"482","article-title":"PPDM: parallel point detection and matching for real-time human-object interaction detection","author":"Liao","year":"2020"},{"issue":"2","key":"10.1016\/j.patcog.2026.113614_bib0004","doi-asserted-by":"crossref","first-page":"635","DOI":"10.3390\/app14020635","article-title":"High-noise grayscale image denoising using an improved median filter for the adaptive selection of a threshold","volume":"14","author":"Cao","year":"2024","journal-title":"Appl. Sci."},{"issue":"7","key":"10.1016\/j.patcog.2026.113614_bib0005","first-page":"6675","article-title":"DiffusionEdge: diffusion probabilistic model for crisp edge detection","volume":"38","author":"Ye","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113614_bib0006","series-title":"2020 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"1","article-title":"Skeleton-based interactive graph network for human object interaction detection","author":"Zheng","year":"2020"},{"key":"10.1016\/j.patcog.2026.113614_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110021","article-title":"Parallel disentangling network for human\u2013object interaction detection","volume":"146","author":"Cheng","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113614_bib0008","series-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"9416","article-title":"Focusing on what to decode and what to train: SOV decoding with specific target guided DeNoising and vision language advisor","author":"Chen","year":"2025"},{"key":"10.1016\/j.patcog.2026.113614_bib0009","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4116","article-title":"Learning human-object interaction detection using interaction points","author":"Wang","year":"2020"},{"key":"10.1016\/j.patcog.2026.113614_bib0010","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"498","article-title":"UnionDet: union-level detector towards real-time human-object interaction detection","author":"Kim","year":"2020"},{"key":"10.1016\/j.patcog.2026.113614_bib0011","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.patcog.2026.113614_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10410","article-title":"QPIC: query-based pairwise human-object interaction detection with image-wide contextual information","author":"Tamura","year":"2021"},{"key":"10.1016\/j.patcog.2026.113614_bib0013","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11825","article-title":"End-to-end human object interaction detection with HOI transformer","author":"Zou","year":"2021"},{"issue":"4","key":"10.1016\/j.patcog.2026.113614_bib0014","doi-asserted-by":"crossref","first-page":"2415","DOI":"10.1109\/TPAMI.2023.3331738","article-title":"FGAHOI: fine-grained anchors for human-object interaction detection","volume":"46","author":"Ma","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113614_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"29161","article-title":"DiffVsgg: diffusion-driven online video scene graph generation","author":"Chen","year":"2025"},{"key":"10.1016\/j.patcog.2026.113614_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104091","article-title":"UAHOI: uncertainty-aware robust interaction learning for HOI detection","volume":"247","author":"Chen","year":"2024","journal-title":"Comput. Vis. Image Understanding"},{"key":"10.1016\/j.patcog.2026.113614_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"20123","article-title":"GEN-VLKT: simplify association and enhance interaction understanding for HOI detection","author":"Liao","year":"2022"},{"key":"10.1016\/j.patcog.2026.113614_bib0018","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia (ACMMM)","first-page":"1711","article-title":"Unseen no more: unlocking the potential of CLIP for generative zero-shot HOI detection","author":"Guo","year":"2024"},{"key":"10.1016\/j.patcog.2026.113614_bib0019","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"15275","article-title":"Category query learning for human-object interaction classification","author":"Xie","year":"2023"},{"key":"10.1016\/j.patcog.2026.113614_bib0020","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1109\/TIP.2022.3231528","article-title":"ERNet: an efficient and reliable human-object interaction detection network","volume":"32","author":"Lim","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113614_bib0021","unstructured":"C. Gao, Y. Zou, J.-B. Huang, iCAN: instance-centric attention network for human\u2013object interaction detection, (2018). arXiv: 1808.10437."},{"key":"10.1016\/j.patcog.2026.113614_bib0022","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"13299","article-title":"Spatially conditioned graphs for detecting human\u2013object interactions","author":"Zhang","year":"2021"},{"issue":"6","key":"10.1016\/j.patcog.2026.113614_bib0023","doi-asserted-by":"crossref","first-page":"2827","DOI":"10.1109\/TPAMI.2021.3049156","article-title":"Cascaded parsing of human-object interaction recognition","volume":"44","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.patcog.2026.113614_bib0024","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2009","journal-title":"IEEE Trans. Neural Netw."},{"key":"10.1016\/j.patcog.2026.113614_bib0025","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"20072","article-title":"Efficient two-stage detection of human-object interactions with a novel unary-pairwise transformer","author":"Zhang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113614_bib0026","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"19526","article-title":"Exploring structure-aware transformer over interaction proposals for human-object interaction detection","author":"Zhang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113614_bib0027","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"10377","article-title":"Exploring predicate visual context in detecting of human\u2013object interactions","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113614_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109110","article-title":"Automatically detecting human-object interaction by an instance part-level attention deep framework","volume":"134","author":"Bai","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113614_bib0029","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"1923","article-title":"Dense extreme inception network: towards a robust CNN model for edge detection","author":"Poma","year":"2020"},{"key":"10.1016\/j.patcog.2026.113614_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"23507","article-title":"HOICLIP: efficient knowledge transfer for HOI detection with vision-language models","author":"Ning","year":"2023"},{"key":"10.1016\/j.patcog.2026.113614_bib0031","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"3593","article-title":"Visual semantic role labeling: a benchmark for visual analysis of human-object interactions","author":"Gupta","year":"2015"},{"key":"10.1016\/j.patcog.2026.113614_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"74","article-title":"HOTR: end-to-end human-object interaction detection with transformers","author":"Kim","year":"2021"},{"key":"10.1016\/j.patcog.2026.113614_bib0033","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"9004","article-title":"Reformulating HOI detection as adaptive set prediction","author":"Chen","year":"2021"},{"key":"10.1016\/j.patcog.2026.113614_bib0034","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"407","article-title":"Learning human-object interactions by graph parsing neural networks","author":"Qi","year":"2018"},{"key":"10.1016\/j.patcog.2026.113614_bib0035","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"696","article-title":"DRG: dual relation graph for human-object interaction detection","author":"Gao","year":"2020"},{"key":"10.1016\/j.patcog.2026.113614_bib0036","unstructured":"J. Yang, B. Li, F. Yang, A. Zeng, L. Zhang, R. Zhang, Boosting human-object interaction detection with text-to-image diffusion model, (2023). arXiv: 2305.12252."},{"key":"10.1016\/j.patcog.2026.113614_bib0037","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"17152","article-title":"ViPLO: vision transformer based pose-conditioned self-loop graph for human-object interaction detection","author":"Park","year":"2023"},{"key":"10.1016\/j.patcog.2026.113614_bib0038","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"6480","article-title":"Efficient adaptive human-object interaction detection with concept-guided memory","author":"Lei","year":"2023"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326005790?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326005790?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:05:50Z","timestamp":1780491950000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326005790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":38,"alternative-id":["S0031320326005790"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113614","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Fine-grained mutual geometric features enhanced human-object interaction detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113614","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113614"}}