{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:17:57Z","timestamp":1763191077744,"version":"3.45.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228736","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["MAMR: Modality-Aligned Multi-modal Retrieval"],"prefix":"10.1109","author":[{"given":"YangZhen","family":"Xu","sequence":"first","affiliation":[{"name":"South China Normal University,School of Artificial Intelligence,Foshan,China"}]},{"given":"JiaWei","family":"Mo","sequence":"additional","affiliation":[{"name":"South China Normal University,School of Artificial Intelligence,Foshan,China"}]},{"given":"FangZhen","family":"Lin","sequence":"additional","affiliation":[{"name":"Dongguan NVT Technology Co.,Ltd,Manufacture Research&Development,DongGuan,China"}]},{"given":"ZeBiao","family":"Chen","sequence":"additional","affiliation":[{"name":"South China Normal University,School of Artificial Intelligence,Foshan,China"}]},{"given":"ChengFeng","family":"Chen","sequence":"additional","affiliation":[{"name":"South China Normal University,School of Artificial Intelligence,Foshan,China"}]},{"given":"ShouQiang","family":"Liu","sequence":"additional","affiliation":[{"name":"South China Normal University,School of Artificial Intelligence,Foshan,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00289"},{"article-title":"Retrieval-augmented generation for AI-generated content: A survey","year":"2024","author":"Zhao","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.314"},{"article-title":"Retrieval-augmented generation for large language models: A survey","year":"2023","author":"Gao","key":"ref5"},{"article-title":"Benchmarking multi-modal retrieval augmented generation with dynamic VQA dataset and self-adaptive planning agent","year":"2024","author":"Li","key":"ref6"},{"article-title":"Fine-grained late-interaction multi-modal retrieval for retrieval augmented visual question answering","volume-title":"Proceedings of the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS)","author":"Lin","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.478"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.289"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00301"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01587"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793752"},{"article-title":"DINOv2: Learning robust visual features without supervision","year":"2023","author":"Oquab","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.133"},{"article-title":"Learning transferable visual models from natural language supervision","year":"2021","author":"Radford","key":"ref19"},{"article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Yao","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613848"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02238"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00501"},{"article-title":"Fine-grained late-interaction multi-modal retrieval for retrieval augmented visual question answering","volume-title":"Proceedings of the Thirty-Seventh Conference on Neural Information Processing Systems","author":"Lin","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref30","article-title":"REVIVE: Regional visual representation matters in knowledge-based visual question answering","author":"Lin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"ref33","first-page":"6769","article-title":"Dense passage retrieval for open-domain question answering","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Karpukhin"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557325"},{"article-title":"WikiWeb2M: A page-level multimodal Wikipedia dataset","year":"2023","author":"Burns","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00501"},{"key":"ref37","first-page":"5583","article-title":"VILT: Vision-and-language transformer without convolution or region supervision","volume-title":"International Conference on Machine Learning","author":"Kim"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228736.pdf?arnumber=11228736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:13:37Z","timestamp":1763190817000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228736","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}