{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T04:46:25Z","timestamp":1769921185068,"version":"3.49.0"},"reference-count":93,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&amp;D Program of China","award":["2021YFB1600501"],"award-info":[{"award-number":["2021YFB1600501"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906038"],"award-info":[{"award-number":["61906038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2242021R41184"],"award-info":[{"award-number":["2242021R41184"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tcds.2024.3496566","type":"journal-article","created":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T13:45:27Z","timestamp":1731332727000},"page":"631-643","source":"Crossref","is-referenced-by-count":1,"title":["Interaction Is Worth More Explanations: Improving Human\u2013Object Interaction Representation With\u00a0Propositional Knowledge"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3495-5257","authenticated-orcid":false,"given":"Feng","family":"Yang","sequence":"first","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2997-4012","authenticated-orcid":false,"given":"Yichao","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9320-0658","authenticated-orcid":false,"given":"Xuanpeng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8626-2233","authenticated-orcid":false,"given":"Weigong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3205168"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3275217"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02147"},{"key":"ref7","article-title":"Searching for better spatio-temporal alignment in few-shot action recognition","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Cao","year":"2022"},{"key":"ref8","article-title":"Detecting any human-object interaction relationship: Universal HOI detector with spatial prompt learning on foundation models","author":"Cao","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083112"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/65"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3334302"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00889"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.042"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547948"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547943"},{"key":"ref19","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"},{"key":"ref22","article-title":"Instance-centric attention network for human-object interaction detection","author":"Gao","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3226301"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.05.052"},{"key":"ref26","article-title":"Visual semantic role labeling","author":"Gupta","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2851569"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.118"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3367493"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2787196"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01441"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00528"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2023.100026"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_30"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01897"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_43"},{"key":"ref41","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref43","article-title":"Human-aware vision-and-language navigation: Bridging simulation to reality with dynamic human interactions","author":"Li","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109234"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01018"},{"key":"ref46","first-page":"5011","article-title":"HOI analysis: Integrating and decomposing human-object interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Li","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00370"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20041"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3231528"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612368"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2015.2504919"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01948"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_15"},{"key":"ref56","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413600"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2019.2919702"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199654864.003.0013"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00207"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01895"},{"key":"ref64","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref67","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00895"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00956"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3357618"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3283406"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28376"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3238181"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3167331"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2023.3240087"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3375620"},{"key":"ref80","article-title":"RLIP: Relational language-image pre-training for human-object interaction detection","author":"Yuan","year":"2022"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20229"},{"key":"ref82","first-page":"17209","article-title":"Mining the benefits of two-stage and one-stage HOI detection","volume":"34","author":"Zhang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3410371"},{"key":"ref86","article-title":"GLIPV2: Unifying localization and vision-language understanding","author":"Zhang","year":"2022"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01458-8"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01303"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01896"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531367"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00200"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11023974\/10750402.pdf?arnumber=10750402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T18:32:58Z","timestamp":1765909978000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10750402\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":93,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2024.3496566","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}