{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:17:42Z","timestamp":1759331862399,"version":"3.37.3"},"reference-count":25,"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\/icassp48485.2024.10448302","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"2775-2779","source":"Crossref","is-referenced-by-count":2,"title":["Human Guided Cross-Modal Reasoning with Semantic Attention Learning for Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Lei","family":"Liao","sequence":"first","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}]},{"given":"Mao","family":"Feng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}]},{"given":"Meng","family":"Yang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","first-page":"8465","article-title":"Found a reason for me? weakly-supervised grounded visual question answering using capsules","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Urooj"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00070"},{"article-title":"Compositional attention networks for machine reasoning","volume-title":"International Conference on Learning Representations","author":"Hudson","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108980"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859591"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897563"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859639"},{"article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","year":"2022","author":"Li","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref15","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Advances in neural information processing systems","volume":"34","author":"Li"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref19","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Ming-Wei Chang Kenton"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01464"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00189"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref23","first-page":"18256","article-title":"Supervising the transfer of reasoning patterns in vqa","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Kervadec"},{"key":"ref24","first-page":"17021","article-title":"Proto: Program-guided transformer for program-guided tasks","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Zhao"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10448302.pdf?arnumber=10448302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:51:52Z","timestamp":1722660712000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448302","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}