{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:03:59Z","timestamp":1775595839205,"version":"3.50.1"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222213"],"award-info":[{"award-number":["62222213"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2059"],"award-info":[{"award-number":["U22B2059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tnnls.2025.3623197","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:11:04Z","timestamp":1762539064000},"page":"1645-1659","source":"Crossref","is-referenced-by-count":0,"title":["From a Social Cognitive Perspective: Context-Aware Visual Social Relationship Recognition"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3206-6827","authenticated-orcid":false,"given":"Shiwei","family":"Wu","sequence":"first","affiliation":[{"name":"Anhui Province Key Laboratory of Big Data Analysis and Application, School of Data Science and School of Computer Science, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2579-8783","authenticated-orcid":false,"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Anhui Province Key Laboratory of Big Data Analysis and Application, School of Data Science and School of Computer Science, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joya","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Design and Engineering, National University of Singapore, Queenstown, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4246-5386","authenticated-orcid":false,"given":"Tong","family":"Xu","sequence":"additional","affiliation":[{"name":"Anhui Province Key Laboratory of Big Data Analysis and Application, School of Data Science and School of Computer Science, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2575-4779","authenticated-orcid":false,"given":"Likang","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Management and Economics, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qimeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Gao","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Hu","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-4102","authenticated-orcid":false,"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"Anhui Province Key Laboratory of Big Data Analysis and Application, School of Data Science and School of Computer Science, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/aphw.12000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1000316"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0022146510383501"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1037\/h0047511"},{"key":"ref5","first-page":"1008","article-title":"From local actions to global tasks: Stigmergy and collective robotics","author":"Beckers","year":"2000","journal-title":"Prerational Intelligence: Adaptive Behavior and Intelligent Systems Without Symbols and Logic, Volume 1, Volume 2 Prerational Intelligence: Interdisciplinary Perspectives on the Behavior of Natural and Artificial Systems, Volume 3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3115.003.0048"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(02)00372-X"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9976"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3016659"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121027"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.4324\/9780203781159"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.99.4.689"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.289"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/142"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00987"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00582688"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.ps.33.020182.000245"},{"key":"ref21","volume-title":"Theories of Cognitive Consistency: A Sourcebook","author":"Abelson","year":"1968"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2466\/PMS.8.7.279-286"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1037\/h0045430"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1037\/h0022492"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1037\/h0044867"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01295-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00368"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475684"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.54"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00895"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250485"},{"issue":"6","key":"ref32","first-page":"660","article-title":"The anatomy of dependence by takeo doi, M.D","volume":"40","author":"Tabbat","year":"1976","journal-title":"Bull. Menninger Clinic"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2307\/2571738"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3196831"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3416493"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00279"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00198"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02244-w"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01144"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.414"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD54268.2022.9776270"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3096553"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/rs13112038"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00444"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3337838"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3110682"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3344359"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3543054"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3592551"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299113"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25151"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027575"},{"key":"ref53","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. ICLR","author":"Gu"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref55","article-title":"CLIP2Video: Mastering video-text retrieval via image CLIP","author":"Fang","year":"2021","journal-title":"arXiv:2106.11097"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref58","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.421"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3416701"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3269789"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029181"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3443394"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"ref66","first-page":"9125","article-title":"DetCLIP: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume-title":"Proc. NeurIPS","author":"Yao"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01462"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_41"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0944"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref72","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. NeurIPS","volume":"28","author":"Ren"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.2991\/itids-19.2019.52"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.126.2.187"},{"key":"ref77","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref78","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref81","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref82","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NaacL-HLT","author":"Kenton"},{"key":"ref83","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.","author":"Li"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref85","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463634"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3181849"},{"key":"ref88","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11475606\/11232485.pdf?arnumber=11232485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:01:01Z","timestamp":1775592061000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11232485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":88,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3623197","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}