{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:24:49Z","timestamp":1774419889891,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890095","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Multimodal Analogical Reasoning Through Triplet Interaction"],"prefix":"10.1109","author":[{"given":"Hua","family":"Cai","sequence":"first","affiliation":[{"name":"UniDT Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuli","family":"Shen","sequence":"additional","affiliation":[{"name":"UniDT Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaishuai","family":"Li","sequence":"additional","affiliation":[{"name":"UniDT Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weilin","family":"Shen","sequence":"additional","affiliation":[{"name":"UniDT Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Xu","sequence":"additional","affiliation":[{"name":"UniDT Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/09528130600558091"},{"key":"ref2","article-title":"Analogical reasoning for visually grounded language acquisition","author":"Wu","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3448250"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.311"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/tea.3660290603"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/64.590078"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-815952-1.00010-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1006\/jmla.1993.1036"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5926\/arepj1962.41.0_27"},{"key":"ref10","first-page":"746","article-title":"Linguistic regularities in continuous space word representations","volume-title":"Proceedings of the 2013 conference of the north american chapter of the association for computational linguistics: Human language technologies","author":"Mikolov"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-2002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1315"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0702_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/621"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16248"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3715093"},{"key":"ref18","article-title":"Learning to make analogies by contrasting abstract relational structure","volume-title":"International Conference on Learning Representations","author":"Hill"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00389"},{"key":"ref20","first-page":"356","article-title":"Semeval-2012 task 2: Measuring degrees of relational similarity","volume-title":"* SEM 2012: The First Joint Conference on Lexical and Computational Semantics\u2013Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012)","author":"Jurgens"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref23","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Devlin"},{"key":"ref24","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.280"},{"key":"ref26","article-title":"Multimodal analogical reasoning over knowledge graphs","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhang"},{"key":"ref27","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref28","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International conference on machine learning","author":"Kim"},{"key":"ref29","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531992"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890095.pdf?arnumber=10890095","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:15Z","timestamp":1774416315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890095\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890095","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}