{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:12:45Z","timestamp":1774419165357,"version":"3.50.1"},"reference-count":28,"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"}],"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889423","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Retention Enhanced Cross-modal Attention for Multi-Hop VQA"],"prefix":"10.1109","author":[{"given":"Zijie","family":"Zhu","sequence":"first","affiliation":[{"name":"Dalian University of Technology,School of Software Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Ding","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglong","family":"Chu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangming","family":"Zhong","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref5","first-page":"1097","article-title":"Mucko: Multi-layer cross-modal knowledge reasoning for fact-based visual question answering","volume-title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020","author":"Zhu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.29"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01459"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref9","article-title":"Retentive network: A successor to transformer for large language models","volume-title":"CoRR","author":"Sun","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref14","first-page":"2010","article-title":"An interpretable reasoning network for multi-relation question answering","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"Zhou"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"ref16","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"5th International Conference on Learning Representations, ICLR 2017","author":"Kipf"},{"key":"ref17","article-title":"Gated graph sequence neural networks","volume-title":"4th International Conference on Learning Representations, ICLR 2016","author":"Li"},{"key":"ref18","article-title":"Memory networks","volume-title":"3rd International Conference on Learning Representations, ICLR 2015","author":"Weston"},{"key":"ref19","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018","author":"Kim"},{"key":"ref20","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014","author":"Sutskever"},{"key":"ref21","first-page":"2440","article-title":"End-to-end memory networks","volume-title":"Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","author":"Sukhbaatar"},{"key":"ref22","first-page":"1400","article-title":"Key-value memory networks for directly reading documents","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Miller"},{"key":"ref23","first-page":"2010","article-title":"An interpretable reasoning network for multi-relation question answering","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"Zhou"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44848-9_11"},{"key":"ref25","first-page":"615","article-title":"Question answering with subgraph embeddings","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Bordes"},{"key":"ref26","article-title":"Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning","volume-title":"6th International Conference on Learning Representations, ICLR 2018","author":"Das"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371812"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"}],"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\/10889423.pdf?arnumber=10889423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:00Z","timestamp":1774416060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889423","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}