{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:05:15Z","timestamp":1779419115591,"version":"3.53.1"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819500086","type":"print"},{"value":"9789819500093","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\/978-981-95-0009-3_3","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T13:24:24Z","timestamp":1753363464000},"page":"27-38","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Semantic Graph Learning with Progressive Alignment for Image-Text Matching"],"prefix":"10.1007","author":[{"given":"Yudi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bailing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kexuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Huynh, C.,et al.: Simpson: simplifying photo cleanup with single-click distracting object segmentation network. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01395"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Chun, S., Oh, S.J., De Rezende, R.S., Kalantidis, Y., Larlus, D.: Probabilistic embeddings for cross-modal retrieval. In: CVPR, pp. 8415\u20138424 (2021)","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Liu, A., Jin, S., Lai, C., Rouditchenko, A., Oliva, A., Glass, J.: Cross-modal discrete representation learning. In: ACL, pp. 3013\u20133035 (2022)","DOI":"10.18653\/v1\/2022.acl-long.215"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Theodoridis, T., Chatzis, T., Solachidis, V., Dimitropoulos, K., Daras, P.: Cross-Modal Variational Alignment of Latent Spaces. In CVPRW, 960\u2013961 (2020)","DOI":"10.1109\/CVPRW50498.2020.00488"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Vision-language pre-training with triple contrastive learning. In: CVPR, pp. 15671\u201315680 (2022)","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Wei, J., Yang, Y., Xu, X., Zhu, X., Shen, H.T.: Universal weighting metric learning for cross-modal retrieval. PAMI (2021)","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Wu, Y., Wang, S., Huang, Q.: Online asymmetric similarity learning for cross-modal retrieval. In: CVPR, pp. 4269\u20134278 (2017)","DOI":"10.1109\/CVPR.2017.424"},{"issue":"2","key":"3_CR8","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., Li, Y., Huang, J., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. PAMI. 41(2), 394\u2013407 (2018)","journal-title":"PAMI."},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Wang, K., Wang, X.: Scene graph generation from objects, phrases and region captions. In: ICCV, pp. 1261\u20131270 (2017)","DOI":"10.1109\/ICCV.2017.142"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Liu, C., Mao, Z., Zhang, T., Xie, H., Wang, B., Zhang, Y.: Graph structured network for image-text matching. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Long, S., Han, S.C., Wan, X., Poon, J.: Gradual: graph-based dual-modal representation for image-text matching. In: WACV (2022)","DOI":"10.1109\/WACV51458.2022.00252"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Pham, K., Huynh, C., Lim, S.N., Shrivastava, A.: Composing object relations and attributes for image-text matching. In: CVPR, pp. 14354\u201314363 (2024)","DOI":"10.1109\/CVPR52733.2024.01361"},{"key":"3_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: ECCV, pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, K., Mao, Z., Wang, Q., Zhang, Y.: Negative-aware attention framework for image-text matching. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Lei, Z., Zhang, Z., Li, S.Z.: Context-aware attention network for image-text retrieval. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Pan, Z., Wu, F., Zhang, B.: Fine-grained image-text matching by cross-modal hard aligning network. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Chen, J., Hu, H., Wu, H., Jiang, Y., Wang, C.: Learning the best pooling strategy for visual semantic embedding. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"3_CR18","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137\u20131149 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR19","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":"3_CR20","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)"},{"key":"3_CR21","unstructured":"Karpathy, A., Joulin, A., Fei-Fei, L.: Deep fragment embeddings for bidirectional image sentence mapping. In: NIPS (2014)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Visual semantic reasoning for image-text matching. In: ICCV, pp. 4654\u20134662 (2019)","DOI":"10.1109\/ICCV.2019.00475"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0009-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T02:21:28Z","timestamp":1779416488000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0009-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500086","9789819500093"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0009-3_3","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":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}