{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T04:24:38Z","timestamp":1751430278293,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819666010","type":"print"},{"value":"9789819665990","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-6599-0_5","type":"book-chapter","created":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T22:19:31Z","timestamp":1751408371000},"page":"60-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained Transformer Encoder of\u00a0Image-Text Retrieval for\u00a0Streaming Data in\u00a0Cross-Modal Continual Learning"],"prefix":"10.1007","author":[{"given":"Hanlin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqiyu","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuesheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guibo","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,2]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., Tuytelaars, T.: Memory aware synapses: learning what (not) to forget. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 139\u2013154 (2018)","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Fini, E., Da\u00a0Costa, V.G.T., Alameda-Pineda, X., Ricci, E., Alahari, K., Mairal, J.: Self-supervised models are continual learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00940"},{"key":"5_CR4","unstructured":"Jian, Y., Gao, C., Vosoughi, S.: Bootstrapping vision-language learning with decoupled language pre-training. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"issue":"13","key":"5_CR5","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521\u20133526 (2017)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"12","key":"5_CR6","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","volume":"40","author":"Z Li","year":"2017","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935\u20132947 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR7","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Park, P., Jang, S., Cho, Y., Kim, Y.: Sam: cross-modal semantic alignments module for image-text retrieval. Multimedia Tools Appl. 83(4) (2024)","DOI":"10.1007\/s11042-023-15798-9"},{"issue":"4","key":"5_CR9","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1007\/s11263-020-01392-1","volume":"129","author":"Y Peng","year":"2021","unstructured":"Peng, Y., Qi, J., Ye, Z., Zhuo, Y.: Hierarchical visual-textual knowledge distillation for life-long correlation learning. Int. J. Comput. Vision 129(4), 921\u2013941 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: ICARL: incremental classifier and representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2001\u20132010 (2017)","DOI":"10.1109\/CVPR.2017.587"},{"key":"5_CR12","unstructured":"Tang, Y., et al.: Augmented shortcuts for vision transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 15316\u201315327 (2021)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Wan, T.S., Chen, J.C., Wu, T.Y., Chen, C.S.: Continual learning for visual search with backward consistent feature embedding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01620"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Wang, K., Herranz, L., van\u00a0de Weijer, J.: Continual learning in cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3628\u20133638 (2021)","DOI":"10.1109\/CVPRW53098.2021.00402"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Yang, J., Wang, X., Wang, Q.: TSFE: research on transformer and feature enhancement methods for image-text retrieval. In: 2024 27th International Conference on Computer Supported Cooperative Work in Design, pp. 2882\u20132887. IEEE (2024)","DOI":"10.1109\/CSCWD61410.2024.10580222"},{"key":"5_CR16","doi-asserted-by":"publisher","first-page":"110273","DOI":"10.1016\/j.patcog.2024.110273","volume":"149","author":"R Yang","year":"2024","unstructured":"Yang, R., et al.: Continual learning for cross-modal image-text retrieval based on domain-selective attention. Pattern Recogn. 149, 110273 (2024)","journal-title":"Pattern Recogn."},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Yang, R., et al.: Knowledge decomposition and replay: a novel cross-modal image-text retrieval continual learning method. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 6510\u20136519 (2023)","DOI":"10.1145\/3581783.3612207"},{"key":"5_CR18","unstructured":"Yildirim, M.O., Gok, E.C., Sokar, G., Mocanu, D.C., Vanschoren, J.: Continual learning with dynamic sparse training: exploring algorithms for effective model updates. In: Conference on Parsimony and Learning, pp. 94\u2013107. PMLR (2024)"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, H., Yang, Y., Qi, F., Qian, S., Xu, C.: C2MR: continual cross-modal retrieval for streaming multi-modal data. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 8963\u20138974 (2023)","DOI":"10.1145\/3581783.3611919"},{"key":"5_CR20","doi-asserted-by":"publisher","first-page":"121845","DOI":"10.1016\/j.eswa.2023.121845","volume":"238","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Fan, W., Liu, X.: Spiking generative networks empowered by multiple dynamic experts for lifelong learning. Expert Syst. Appl. 238, 121845 (2024)","journal-title":"Expert Syst. Appl."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6599-0_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T22:19:35Z","timestamp":1751408375000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6599-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819666010","9789819665990"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6599-0_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}