{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:06:07Z","timestamp":1743120367405,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030923099"},{"type":"electronic","value":"9783030923105"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-92310-5_48","type":"book-chapter","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T14:04:20Z","timestamp":1638799460000},"page":"417-424","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bottom-Up Progressive Semantic Alignment for\u00a0Image-Text Retrieval"],"prefix":"10.1007","author":[{"given":"Zheng","family":"Cui","sequence":"first","affiliation":[]},{"given":"Yongli","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Yanfeng","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Junbin","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,12,2]]},"reference":[{"key":"48_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"48_CR2","doi-asserted-by":"crossref","unstructured":"Chen, H., Ding, G., Lin, Z., Zhao, S., Han, J.: Cross-modal image-text retrieval with semantic consistency. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1749\u20131757 (2019)","DOI":"10.1145\/3343031.3351055"},{"key":"48_CR3","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"},{"key":"48_CR4","doi-asserted-by":"crossref","unstructured":"Chen, T., Luo, J.: Expressing objects just like words: recurrent visual embedding for image-text matching. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10583\u201310590 (2020)","DOI":"10.1609\/aaai.v34i07.6631"},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Eisenschtat, A., Wolf, L.: Linking image and text with 2-way nets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4601\u20134611(2017)","DOI":"10.1109\/CVPR.2017.201"},{"key":"48_CR6","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)"},{"key":"48_CR7","unstructured":"Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: Advances in Neural Information Processing Systems, pp. 2121\u20132129 (2013)"},{"key":"48_CR8","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"48_CR9","doi-asserted-by":"crossref","unstructured":"Klein, B., Lev, G., Sadeh, G., Wolf, L.: Associating neural word embeddings with deep image representations using fisher vectors. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"48_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-01225-0_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K-H Lee","year":"2018","unstructured":"Lee, K.-H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018, Part IV. LNCS, vol. 11208, pp. 212\u2013228. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_13"},{"key":"48_CR11","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, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"48_CR12","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.neucom.2018.11.089","volume":"345","author":"L Ma","year":"2019","unstructured":"Ma, L., Jiang, W., Jie, Z., Wang, X.: Bidirectional image-sentence retrieval by local and global deep matching. Neurocomputing 345, 36\u201344 (2019)","journal-title":"Neurocomputing"},{"key":"48_CR13","doi-asserted-by":"crossref","unstructured":"Niu, Z., Zhou, M., Wang, L., Gao, X., Hua, G.: Hierarchical multimodal LSTM for dense visual-semantic embedding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1881\u20131889 (2017)","DOI":"10.1109\/ICCV.2017.208"},{"issue":"11","key":"48_CR14","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"48_CR15","doi-asserted-by":"crossref","unstructured":"Wang, B., Yang, Y., Xu, X., Hanjalic, A., Shen, H.T.: Adversarial cross-modal retrieval. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 154\u2013162 (2017)","DOI":"10.1145\/3123266.3123326"},{"key":"48_CR16","doi-asserted-by":"crossref","unstructured":"Wang, J.J., He, Y., Kang, C., Xiang, S., Pan, C.: Image-text cross-modal retrieval via modality-specific feature learning. In: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval (2015)","DOI":"10.1145\/2671188.2749341"},{"key":"48_CR17","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Camp: cross-modal adaptive message passing for text-image retrieval. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5764\u20135773 (2019)","DOI":"10.1109\/ICCV.2019.00586"},{"key":"48_CR18","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92310-5_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T08:11:36Z","timestamp":1655799096000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92310-5_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030923099","9783030923105"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92310-5_48","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 December 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Sanur, Bali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2021.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1093","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":"226","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":"177","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":"21% - 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":"2.57","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":"6","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)"}},{"value":"Due to the COVID-19 pandemic the conference was held online.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}