{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:17:52Z","timestamp":1742912272494,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533044"},{"type":"electronic","value":"9783031533051"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-53305-1_25","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"327-341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Structure-Aware Adaptive Hybrid Interaction Modeling for\u00a0Image-Text Matching"],"prefix":"10.1007","author":[{"given":"Wei","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaorong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Cao, M., Li, S., Li, J., Nie, L., Zhang, M.: Image-text retrieval: a survey on recent research and development. arXiv preprint arXiv:2203.14713 (2022)","DOI":"10.24963\/ijcai.2022\/759"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Chen, H., Ding, G., Liu, X., Lin, Z., Liu, J., Han, J.: IMRAM: iterative matching with recurrent attention memory for cross-modal image-text retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12655\u201312663 (2020)","DOI":"10.1109\/CVPR42600.2020.01267"},{"issue":"4","key":"25_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3499027","volume":"18","author":"Y Cheng","year":"2022","unstructured":"Cheng, Y., Zhu, X., Qian, J., Wen, F., Liu, P.: Cross-modal graph matching network for image-text retrieval. ACM Trans. Multimedia Comput. Commun. Appl. 18(4), 1\u201323 (2022)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"25_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zeng, Z., Huang, Y., Liu, B., Fu, D., Fu, J.: Seeing out of the box: end-to-end pre-training for vision-language representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12976\u201312985 (2021)","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Ji, Z., Chen, K., Wang, H.: Step-wise hierarchical alignment network for image-text matching. In: IJCAI International Joint Conference on Artificial Intelligence, pp. 765\u2013771 (2021)","DOI":"10.24963\/ijcai.2021\/106"},{"key":"25_CR7","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"25_CR8","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Visual semantic reasoning for image-text matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4654\u20134662 (2019)","DOI":"10.1109\/ICCV.2019.00475"},{"issue":"1","key":"25_CR11","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1109\/TPAMI.2022.3148470","volume":"45","author":"K Li","year":"2022","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Image-text embedding learning via visual and textual semantic reasoning. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 641\u2013656 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"25_CR12","doi-asserted-by":"publisher","first-page":"102432","DOI":"10.1016\/j.ipm.2020.102432","volume":"58","author":"WH Li","year":"2021","unstructured":"Li, W.H., Yang, S., Wang, Y., Song, D., Li, X.Y.: Multi-level similarity learning for image-text retrieval. Inf. Process. Manage. 58(1), 102432 (2021)","journal-title":"Inf. Process. Manage."},{"key":"25_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","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"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Miyawaki, S., Hasegawa, T., Nishida, K., Kato, T., Suzuki, J.: Scene-text aware image and text retrieval with dual-encoder. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pp. 422\u2013433 (2022)","DOI":"10.18653\/v1\/2022.acl-srw.34"},{"key":"25_CR15","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":"25_CR16","doi-asserted-by":"crossref","unstructured":"Qu, L., Liu, M., Wu, J., Gao, Z., Nie, L.: Dynamic modality interaction modeling for image-text retrieval. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1104\u20131113 (2021)","DOI":"10.1145\/3404835.3462829"},{"key":"25_CR17","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"25_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR19","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.1109\/TMM.2022.3142420","volume":"24","author":"G Wang","year":"2022","unstructured":"Wang, G., Xu, X., Shen, F., Lu, H., Ji, Y., Shen, H.T.: Cross-modal dynamic networks for video moment retrieval with text query. IEEE Trans. Multimedia 24, 1221\u20131232 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"25_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-58586-0_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhang, Y., Ji, Z., Pang, Y., Ma, L.: Consensus-aware visual-semantic embedding for image-text matching. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 18\u201334. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_2"},{"issue":"3","key":"25_CR21","doi-asserted-by":"publisher","first-page":"103280","DOI":"10.1016\/j.ipm.2023.103280","volume":"60","author":"Y Wang","year":"2023","unstructured":"Wang, Y., et al.: Rare-aware attention network for image-text matching. Inf. Process. Manage. 60(3), 103280 (2023)","journal-title":"Inf. Process. Manage."},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Wasserstein coupled graph learning for cross-modal retrieval. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1793\u20131802. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.00183"},{"issue":"1","key":"25_CR23","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1109\/TCSVT.2021.3060713","volume":"32","author":"J Wu","year":"2021","unstructured":"Wu, J., Wu, C., Lu, J., Wang, L., Cui, X.: Region reinforcement network with topic constraint for image-text matching. IEEE Trans. Circuits Syst. Video Technol. 32(1), 388\u2013397 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"You, S., et al.: What image do you need? A two-stage framework for image selection in e-commerce. In: Companion Proceedings of the ACM Web Conference 2023, pp. 452\u2013456 (2023)","DOI":"10.1145\/3543873.3584646"},{"key":"25_CR25","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.future.2023.01.004","volume":"142","author":"R Yu","year":"2023","unstructured":"Yu, R., Jin, F., Qiao, Z., Yuan, Y., Wang, G.: Multi-scale image-text matching network for scene and spatio-temporal images. Future Gener. Comput. Syst. 142, 292\u2013300 (2023)","journal-title":"Future Gener. Comput. Syst."},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, J., He, X., Qing, L., Liu, L., Luo, X.: Cross-modal multi-relationship aware reasoning for image-text matching. Multimedia Tools Appl. 81, 12005\u201312027 (2022)","DOI":"10.1007\/s11042-020-10466-8"},{"key":"25_CR27","doi-asserted-by":"publisher","first-page":"110280","DOI":"10.1016\/j.knosys.2023.110280","volume":"263","author":"G Zhao","year":"2023","unstructured":"Zhao, G., Zhang, C., Shang, H., Wang, Y., Zhu, L., Qian, X.: Generative label fused network for image-text matching. Knowl.-Based Syst. 263, 110280 (2023)","journal-title":"Knowl.-Based Syst."},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, J., Li, Z., Zeng, Y., Wei, J., Ma, H.: Image-text matching with fine-grained relational dependency and bidirectional attention-based generative networks. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 395\u2013403 (2022)","DOI":"10.1145\/3503161.3548058"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53305-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:03:14Z","timestamp":1710331394000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53305-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533044","9783031533051"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53305-1_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"112","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}