{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T07:42:33Z","timestamp":1774942953217,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650044","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T13:35:05Z","timestamp":1725888905000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Hierarchical Fusion Framework for Multimodal Dialogue Response Generation"],"prefix":"10.1109","author":[{"given":"Qi","family":"Deng","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China"}]},{"given":"Lijun","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China"}]},{"given":"Kaile","family":"Su","sequence":"additional","affiliation":[{"name":"Griffith University,School of Information and Communication Technology,Brisbane,Australia"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[{"name":"Central South University,School of Computer Science and Engineering,Changsha,China"}]},{"given":"Zhiyuan","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China"}]},{"given":"Weiwei","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,Chengdu,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01124"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.375"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.204"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2798607"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.479"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00506"},{"key":"ref9","article-title":"Multi-task learning as multi-objective optimization","volume":"31","author":"Sener","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2012.03.014"},{"issue":"1","key":"ref11","first-page":"427","article-title":"Revisiting Frank-Wolfe: Projection-free sparse convex optimization","volume-title":"Proceedings of the 30th International Conference on Machine Learning","volume":"28","author":"Jaggi"},{"key":"ref12","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref14","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.70"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International conference on Machine Learning, ICML 2021, 18 - 24 July 2021, Virtual Event","volume":"139","author":"Radford"},{"key":"ref18","article-title":"Coca: Contrastive captioners are image-text foundation models","volume":"2022","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01757"},{"key":"ref20","article-title":"Dialog without dialog data: Learning visual dialog agents from VQA data","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6 - 12, 2020, virtual","author":"Cogswell"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01117"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00566"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3061479"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487381"},{"key":"ref26","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18 - 22, 2018","author":"Kendall"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.749"},{"key":"ref30","article-title":"One-peace: Exploring one general representation model toward unlimited modalities","author":"Wang","year":"2023"},{"key":"ref31","article-title":"Compositional attention networks for machine reasoning","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings","author":"Hudson"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650044.pdf?arnumber=10650044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:33:13Z","timestamp":1759858393000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650044\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650044","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}