{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:23:59Z","timestamp":1743078239363,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031264085"},{"type":"electronic","value":"9783031264092"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26409-2_24","type":"book-chapter","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T09:04:46Z","timestamp":1678957486000},"page":"390-406","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained Bidirectional Attention-Based Generative Networks for\u00a0Image-Text Matching"],"prefix":"10.1007","author":[{"given":"Zhixin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahui","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufei","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,17]]},"reference":[{"key":"24_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":"24_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 Conference on Computer Vision and Pattern Recognition, pp. 12655\u201312663 (2020)","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"24_CR3","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.1109\/LSP.2020.3025128","volume":"27","author":"S Chen","year":"2020","unstructured":"Chen, S., Li, Z., Tang, Z.: Relation R-CNN: a graph based relation-aware network for object detection. IEEE Signal Process. Lett. 27, 1680\u20131684 (2020)","journal-title":"IEEE Signal Process. Lett."},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z.M., Wei, X.S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5177\u20135186 (2019)","DOI":"10.1109\/CVPR.2019.00532"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Gu, J., Cai, J., Joty, S.R., Niu, L., Wang, G.: Look, imagine and match: improving textual-visual cross-modal retrieval with generative models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7181\u20137189 (2018)","DOI":"10.1109\/CVPR.2018.00750"},{"issue":"5","key":"24_CR7","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MSP.2008.926652","volume":"25","author":"X He","year":"2008","unstructured":"He, X., Deng, L., Chou, W.: Discriminative learning in sequential pattern recognition. IEEE Signal Process. Mag. 25(5), 14\u201336 (2008)","journal-title":"IEEE Signal Process. Mag."},{"key":"24_CR8","unstructured":"Herdade, S., Kappeler, A., Boakye, K., Soares, J.: Image captioning: transforming objects into words. arXiv preprint arXiv:1906.05963 (2019)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Ji, Z., Chen, K., Wang, H.: Step-wise hierarchical alignment network for image-text matching. arXiv preprint arXiv:2106.06509 (2021)","DOI":"10.24963\/ijcai.2021\/106"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"24_CR12","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"24_CR13","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, pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"24_CR14","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"},{"key":"24_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104475","volume":"106","author":"Z Li","year":"2021","unstructured":"Li, Z., Xie, X., Ling, F., Ma, H., Shi, Z.: Matching images and texts with multi-head attention network for cross-media hashing retrieval. Eng. Appl. Artif. Intell. 106, 104475 (2021)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"24_CR16","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":"24_CR17","doi-asserted-by":"crossref","unstructured":"Liu, C., Mao, Z., Liu, A.A., Zhang, T., Wang, B., Zhang, Y.: Focus your attention: a bidirectional focal attention network for image-text matching. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 3\u201311 (2019)","DOI":"10.1145\/3343031.3350869"},{"issue":"11","key":"24_CR18","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using T-SNE. J. Mach. Learn. Res. 9(11), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"24_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3284750","volume":"15","author":"Y Peng","year":"2019","unstructured":"Peng, Y., Qi, J.: CM-GANs: cross-modal generative adversarial networks for common representation learning. ACM Trans. Multimed. Comput. Commun. Appl. 15(1), 1\u201324 (2019)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"24_CR20","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR21","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, R., Yao, Z., Shan, S., Chen, X.: Cross-modal scene graph matching for relationship-aware image-text retrieval. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1508\u20131517 (2020)","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Position focused attention network for image-text matching. arXiv preprint arXiv:1907.09748 (2019)","DOI":"10.24963\/ijcai.2019\/526"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Z., Liu, X., Li, H., Sheng, L., Yan, J., Wang, X., Shao, J.: 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":"24_CR25","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of the International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"24_CR27","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":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26409-2_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T09:26:34Z","timestamp":1678958794000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26409-2_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031264085","9783031264092"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26409-2_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2022.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1060","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":"236","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":"22% - 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":"3-4","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":"3-4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17 demo track papers have been accepted from 28 submissions","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)"}}]}}