{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:25:45Z","timestamp":1778171145141,"version":"3.51.4"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448108","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"3680-3684","source":"Crossref","is-referenced-by-count":2,"title":["Implicit-Knowledge-Guided Align Before Understanding for KB-VQA"],"prefix":"10.1109","author":[{"given":"Mao","family":"Feng","sequence":"first","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Eigineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Liao","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Eigineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Yang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Eigineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00070"},{"key":"ref3","first-page":"17021","article-title":"Proto: Program-guided transformer for program-guided tasks","volume":"34","author":"Zhao","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547870"},{"key":"ref5","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref7","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Devlin"},{"key":"ref8","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref11","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref13","article-title":"Bilinear attention networks","volume":"31","author":"Kim","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.44"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20174"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.10.007"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413943"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.169"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107563"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448108.pdf?arnumber=10448108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:46:40Z","timestamp":1722581200000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448108\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448108","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}