{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T21:36:51Z","timestamp":1771537011808,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["22H00548"],"award-info":[{"award-number":["22H00548"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Japan Science and Technology Agency (JST) Cutting-edge Research and Operationalization onNext-generation Open Sciences","award":["JPMJCS24K4"],"award-info":[{"award-number":["JPMJCS24K4"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3659132","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:25:27Z","timestamp":1769721927000},"page":"23299-23310","source":"Crossref","is-referenced-by-count":0,"title":["Bridging Detection Architectures With Foundation Models: A Unified Framework for Human\u2013Object Interaction Detection"],"prefix":"10.1109","volume":"14","author":[{"given":"Junwen","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Informatics, The University of Electro-Communications, Tokyo, Japan"}]},{"given":"Keiji","family":"Yanai","sequence":"additional","affiliation":[{"name":"Department of Informatics, The University of Electro-Communications, Tokyo, Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1117\/12.2671090"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00977"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00370"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref11","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"arXiv:1904.07850"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01053"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01303"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02663"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00286"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01895"},{"key":"ref23","first-page":"17209","article-title":"Mining the benefits of two-stage and one-stage HOI detection","volume-title":"Proc. Adv. Neural Inform. Process. Syst. (NIPS)","author":"Zhang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref25","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/MVA57639.2023.10215534"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref29","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref30","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref31","first-page":"45895","article-title":"CLIP4HOI: Towards adapting clip for practical zero-shot hoi detection","volume-title":"Proc. Adv. Neural Inform. Process. Syst. (NIPS)","author":"Mao"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref33","first-page":"739","article-title":"Detecting any human-object interaction relationship: Universal HOI detector with spatial prompt learning on foundation models","volume-title":"Proc. Adv. Neural Inform. Process. Syst. (NIPS)","author":"Cao"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00912"},{"key":"ref35","first-page":"1","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Liu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3335410"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref39","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Oquab"},{"key":"ref40","article-title":"DINOv3","author":"Sim\u00e9oni","year":"2025","journal-title":"arXiv:2508.10104"},{"key":"ref41","first-page":"1825","article-title":"HOLa: Zero-shot HOI detection with low-rank decomposed VLM feature adaptation","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"Lei"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02665"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3331738"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1002\/nav.20053"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3607828.3617790"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01897"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_26"},{"key":"ref48","article-title":"Boosting human-object interaction detection with text-to-image diffusion model","author":"Yang","year":"2023","journal-title":"arXiv:2305.12252"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00955"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01979"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015","journal-title":"arXiv:1505.04474"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11367687.pdf?arnumber=11367687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T20:59:46Z","timestamp":1771534786000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11367687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3659132","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}