{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T04:50:17Z","timestamp":1746766217716,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819772438"},{"type":"electronic","value":"9789819772445"}],"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\/978-981-97-7244-5_9","type":"book-chapter","created":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T17:02:38Z","timestamp":1724778158000},"page":"130-145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Entity Semantic Feature Fusion Network for\u00a0Remote Sensing Image-Text Retrieval"],"prefix":"10.1007","author":[{"given":"Jianan","family":"Shui","sequence":"first","affiliation":[]},{"given":"Shuaipeng","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Mingyong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Ma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,28]]},"reference":[{"issue":"3","key":"9_CR1","doi-asserted-by":"publisher","first-page":"405","DOI":"10.3390\/rs12030405","volume":"12","author":"T Abdullah","year":"2020","unstructured":"Abdullah, T., Bazi, Y., Al Rahhal, M.M., Mekhalfi, M.L., Rangarajan, L., Zuair, M.: TextRS: deep bidirectional triplet network for matching text to remote sensing images. Remote Sens. 12(3), 405 (2020)","journal-title":"Remote Sens."},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, Q., Zhou, Y., Fu, P., Xu, Y., Zhang, L.: A deep semantic alignment network for the cross-modal image-text retrieval in remote sensing. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 14, 4284\u20134297 (2021)","DOI":"10.1109\/JSTARS.2021.3070872"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"9_CR4","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)"},{"issue":"5","key":"9_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3580501","volume":"19","author":"D Feng","year":"2023","unstructured":"Feng, D., He, X., Peng, Y.: MKVSE: multimodal knowledge enhanced visual-semantic embedding for image-text retrieval. ACM Trans. Multimed. Comput. Commun. Appl. 19(5), 1\u201321 (2023)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"9_CR7","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wu, Q., Song, C., Wang, L.: Learning semantic concepts and order for image and sentence matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6163\u20136171 (2018)","DOI":"10.1109\/CVPR.2018.00645"},{"key":"9_CR9","first-page":"1","volume":"61","author":"Z Ji","year":"2023","unstructured":"Ji, Z., Meng, C., Zhang, Y., Pang, Y., Li, X.: Knowledge-aided momentum contrastive learning for remote-sensing image text retrieval. IEEE Trans. Geosci. Remote Sens. 61, 1\u201313 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"9_CR10","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":"9_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"9_CR12","doi-asserted-by":"publisher","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. LNCS, vol. 11208, pp. 212\u2013228. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_13","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"9_CR13","unstructured":"Liu, S., Huang, D., Wang, Y.: Learning spatial fusion for single-shot object detection. arxiv 2019. arXiv preprint arXiv:1911.09516 (1911)"},{"issue":"4","key":"9_CR14","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1109\/TGRS.2017.2776321","volume":"56","author":"X Lu","year":"2017","unstructured":"Lu, X., Wang, B., Zheng, X., Li, X.: Exploring models and data for remote sensing image caption generation. IEEE Trans. Geosci. Remote Sens. 56(4), 2183\u20132195 (2017)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"9_CR15","first-page":"1","volume":"19","author":"Y Lv","year":"2021","unstructured":"Lv, Y., Xiong, W., Zhang, X., Cui, Y.: Fusion-based correlation learning model for cross-modal remote sensing image retrieval. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2021)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Mannor, S., Peleg, D., Rubinstein, R.: The cross entropy method for classification. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 561\u2013568 (2005)","DOI":"10.1145\/1102351.1102422"},{"key":"9_CR17","unstructured":"Mi, L., Li, S., Chappuis, C., Tuia, D.: Knowledge-aware cross-modal text-image retrieval for remote sensing images. In: Proceedings of the Second Workshop on Complex Data Challenges in Earth Observation (CDCEO 2022) (2022)"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Pan, J., Ma, Q., Bai, C.: Reducing semantic confusion: Scene-aware aggregation network for remote sensing cross-modal retrieval. In: Proceedings of the 2023 ACM International Conference on Multimedia Retrieval, pp. 398\u2013406 (2023)","DOI":"10.1145\/3591106.3592236"},{"key":"9_CR19","unstructured":"Vaswani, A., et\u00a0al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Z., et\u00a0al.: CAMP: cross-modal adaptive message passing for text-image retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5764\u20135773 (2019)","DOI":"10.1109\/ICCV.2019.00586"},{"issue":"7","key":"9_CR21","doi-asserted-by":"publisher","first-page":"3965","DOI":"10.1109\/TGRS.2017.2685945","volume":"55","author":"GS Xia","year":"2017","unstructured":"Xia, G.S., et al.: AID: a benchmark data set for performance evaluation of aerial scene classification. IEEE Trans. Geosci. Remote Sens. 55(7), 3965\u20133981 (2017)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Yao, F., et\u00a0al.: Hypergraph-enhanced textual-visual matching network for cross-modal remote sensing image retrieval via dynamic hypergraph learning. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. 16, 688\u2013701 (2022)","DOI":"10.1109\/JSTARS.2022.3226325"},{"key":"9_CR23","first-page":"1","volume":"60","author":"Z Yuan","year":"2022","unstructured":"Yuan, Z., et al.: Exploring a fine-grained multiscale method for cross-modal remote sensing image retrieval. IEEE Trans. Geosci. Remote Sens. 60, 1\u201319 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"9_CR24","first-page":"1","volume":"60","author":"Z Yuan","year":"2021","unstructured":"Yuan, Z., et al.: A lightweight multi-scale crossmodal text-image retrieval method in remote sensing. IEEE Trans. Geosci. Remote Sens. 60, 1\u201319 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"9_CR25","first-page":"1","volume":"60","author":"Z Yuan","year":"2022","unstructured":"Yuan, Z., et al.: Remote sensing cross-modal text-image retrieval based on global and local information. IEEE Trans. Geosci. Remote Sens. 60, 1\u201316 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Zhang, X., Li, H., Wang, J., Zhang, J., Zhou, W.: X2-VLM: all-in-one pre-trained model for vision-language tasks. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3339661"},{"issue":"1","key":"9_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3603628","volume":"20","author":"C Zheng","year":"2023","unstructured":"Zheng, C., Song, N., Zhang, R., Huang, L., Wei, Z., Nie, J.: Scale-semantic joint decoupling network for image-text retrieval in remote sensing. ACM Trans. Multimed. Comput. Commun. Appl. 20(1), 1\u201320 (2023)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Kang, J., Diao, W., Feng, Y., Li, J., Ni, J.: SIRS: multi-task joint learning for remote sensing foreground-entity image-text retrieval. IEEE Trans. Geosci. Remote Sens (2024)","DOI":"10.1109\/TGRS.2024.3402216"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-7244-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T17:05:28Z","timestamp":1724778328000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-7244-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819772438","9789819772445"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-7244-5_9","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 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jinhua","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/apweb2024.zjnu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}