{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:01Z","timestamp":1792786921659,"version":"4.5.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFC3305600"],"award-info":[{"award-number":["2023YFC3305600"]}]},{"name":"National Natural Science Foundation of China","award":["U25B2048"],"award-info":[{"award-number":["U25B2048"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3700158","type":"journal-article","created":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:40:23Z","timestamp":1780515623000},"page":"12244-12259","source":"Crossref","is-referenced-by-count":0,"title":["Deciphering Object Concepts: Hierarchical Cross-Modal Relational Reasoning for Mining Object-Attribute-Affordance Associations"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2767-2475","authenticated-orcid":false,"given":"Yuxuan","family":"Wang","sequence":"first","affiliation":[{"name":"Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muli","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), A*STAR"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiexi","family":"Yan","sequence":"additional","affiliation":[{"name":"Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fen","family":"Fang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), A*STAR"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xulei","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), A*STAR"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2620-3247","authenticated-orcid":false,"given":"Cheng","family":"Deng","sequence":"additional","affiliation":[{"name":"Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky","year":"2012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237935"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3421300"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01833"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30285-0_18"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115063"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.10.027"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2995805"},{"key":"ref11","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":"ref12","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3531452"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3573852"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3562534"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00776"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-025-02232-3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2015.08.015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2015.00420"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339980"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284038"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01648"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995543"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01133"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2023.3291558"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCSP.2017.7944094"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104617"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007465528199"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1206-1565"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2007.914848"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/1059712310370625"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-7998-9220-5.ch148"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3343736"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611873"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02243"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3568746"},{"key":"ref47","first-page":"49705","article-title":"Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3501714.3501736"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref51","first-page":"1779","article-title":"CLUB: A contrastive log-ratio upper bound of mutual information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cheng","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref55","article-title":"FastFCN: Rethinking dilated convolution in the backbone for semantic segmentation","author":"Wu","year":"2019"},{"key":"ref56","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00545"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01903"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00680"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02252"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02144-1"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1198\/016214504000001880"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01001"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01351"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754778"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref71","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00165"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11549962.pdf?arnumber=11549962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:50:11Z","timestamp":1790268611000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11549962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":74,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3700158","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}