{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T04:03:57Z","timestamp":1745467437260,"version":"3.40.4"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819660049","type":"print"},{"value":"9789819660056","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\/978-981-96-6005-6_6","type":"book-chapter","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T03:15:35Z","timestamp":1745378135000},"page":"72-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Efficiency Image Captioning by Using Attention Mechanism Combined with Knowledge Graph"],"prefix":"10.1007","author":[{"given":"Tam Khoi","family":"Tran","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nguyen Thi Uyen","family":"Nhi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thanh Manh","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nguyen Thi","family":"Dinh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,21]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126287","volume":"546","author":"L Xu","year":"2023","unstructured":"Xu, L., Tang, Q., Lv, J., Zheng, B., Zeng, X., Li, W.: Deep image captioning: a review of methods, trends and future challenges. Neurocomputing 546, 126287 (2023)","journal-title":"Neurocomputing"},{"issue":"11","key":"6_CR2","doi-asserted-by":"publisher","first-page":"1387","DOI":"10.1111\/mice.12793","volume":"37","author":"PJ Chun","year":"2022","unstructured":"Chun, P.J., Yamane, T., Maemura, Y.: A deep learning-based image captioning method to automatically generate comprehensive explanations of bridge damage. Comput.-Aided Civil Infrastruct. Eng. 37(11), 1387\u20131401 (2022)","journal-title":"Comput.-Aided Civil Infrastruct. Eng."},{"key":"6_CR3","doi-asserted-by":"publisher","first-page":"2659","DOI":"10.1109\/TMM.2023.3301279","volume":"26","author":"W Zhao","year":"2023","unstructured":"Zhao, W., Wu, X.: Boosting entity-aware image captioning with multi-modal knowledge graph. IEEE Trans. Multimedia 26, 2659\u20132670 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Elbedwehy, S., Medhat, T., Hamza, T., Alrahmawy, M. F., Efficient image captioning based on vision transformer models. Comput. Mater. Continua 73(1) (2022)","DOI":"10.32604\/cmc.2022.029313"},{"issue":"2","key":"6_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102178","volume":"57","author":"M Liu","year":"2020","unstructured":"Liu, M., Li, L., Hu, H., Guan, W., Tian, J.: Image caption generation with dual attention mechanism. Inf. Process. Manage. 57(2), 102178 (2020)","journal-title":"Inf. Process. Manage."},{"key":"6_CR6","unstructured":"MS-COCO Image Dataset. https:\/\/cocodataset.org\/#download. Accessed 10 Oct 2024"},{"key":"6_CR7","unstructured":"Flickr Image Dataset. https:\/\/www.kaggle.com\/datasets\/hsankesara\/flickr-image-dataset. Accessed 10 Oct 2024"},{"key":"6_CR8","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.patrec.2019.03.021","volume":"123","author":"S Ding","year":"2019","unstructured":"Ding, S., et al.: Image caption generation with high-level image features. Pattern Recogn. Lett. 123, 89\u201395 (2019)","journal-title":"Pattern Recogn. Lett."},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Predi\u0107, B., et al., Automatic image caption generation based on some machine learning algorithms. Math. Prob. Eng. (2022)","DOI":"10.1155\/2022\/4001460"},{"issue":"2","key":"6_CR10","doi-asserted-by":"publisher","first-page":"8366","DOI":"10.48084\/etasr.4772","volume":"12","author":"M Bhalekar","year":"2022","unstructured":"Bhalekar, M., Bedekar, M.: D-CNN: A new model for generating image captions with text extraction using deep learning for visually challenged individuals. Eng. Technol. Appl. Sci. Res. 12(2), 8366\u20138373 (2022)","journal-title":"Eng. Technol. Appl. Sci. Res."},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Yuan, J., Zhang, L., Guo, S., Xiao, Y., Li, Z., Image captioning with a joint attention mechanism by visual concept samples. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 16(3), 1\u201322 (2020)","DOI":"10.1145\/3394955"},{"key":"6_CR12","doi-asserted-by":"publisher","first-page":"1270850","DOI":"10.3389\/fnins.2023.1270850","volume":"17","author":"T Bai","year":"2023","unstructured":"Bai, T., Zhou, S., Pang, Y., Luo, J., Wang, H., Du, Y.: An image caption model based on attention mechanism and deep reinforcement learning. Front. Neurosci. 17, 1270850 (2023)","journal-title":"Front. Neurosci."},{"key":"6_CR13","unstructured":"Khan, R., Islam, M.S., Kanwal, K., Iqbal, M., Hossain, M.I., Ye, Z.: A deep neural framework for image caption generation using gru-based attention mechanism. arXiv preprint arXiv:2203.01594 (2022)"},{"issue":"1","key":"6_CR14","doi-asserted-by":"publisher","DOI":"10.1002\/eng2.12785","volume":"6","author":"MS Wajid","year":"2024","unstructured":"Wajid, M.S., Terashima-Marin, H., Najafirad, P., Wajid, M.A.: Deep learning and knowledge graph for image\/video captioning: a review of datasets, evaluation metrics, and methods. Eng. Rep. 6(1), e12785 (2024)","journal-title":"Eng. Rep."},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Wang, X., Meng, B., Chen, H., Meng, Y., Lv, K., Zhu, W.: TIVA-KG: a multimodal knowledge graph with text, image, video and audio. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2391\u20132399 (2023)","DOI":"10.1145\/3581783.3612266"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In\u00a0Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"issue":"1","key":"6_CR17","doi-asserted-by":"publisher","first-page":"11307","DOI":"10.1038\/s41598-020-67529-x","volume":"10","author":"W Li","year":"2020","unstructured":"Li, W., Liu, K., Zhang, L., Cheng, F.: Object detection based on an adaptive attention mechanism. Sci. Rep. 10(1), 11307 (2020)","journal-title":"Sci. Rep."},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"Dinh, N.T., Linh, T.T., Van, T.T., Le, T.M.: A technique of knowledge graph construction applied to the image retrieval. In: Proceedings of the National Conference on Basic Research and Application of Information Technology (FAIR 2024) (2024). https:\/\/doi.org\/10.15625\/vap.2024.0244","DOI":"10.15625\/vap.2024.0244"},{"key":"6_CR19","doi-asserted-by":"publisher","unstructured":"Khoi, T.T., Phuoc, T.T., Van, T.T.: Images retrieval based on deep learning and knowledge graph. In: Proceedings of the National Conference on Basic Research and Application of Information Technology (FAIR2024) (2024). https:\/\/doi.org\/10.15625\/vap.2024.0278","DOI":"10.15625\/vap.2024.0278"},{"key":"6_CR20","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/978-3-031-60227-6_2","volume-title":"Good Practices and New Perspectives in Information Systems and Technologies: WorldCIST 2024, Volume 5","author":"NT Dinh","year":"2024","unstructured":"Dinh, N.T., Le, T.M., Van, T.T.: Using knowledge graph and KD-tree random forest for image retrieval. In: Rocha, \u00c1., Adeli, H., Dzemyda, G., Moreira, F., Poniszewska-Mara\u0144da, A. (eds.) Good Practices and New Perspectives in Information Systems and Technologies: WorldCIST 2024, Volume 5, pp. 13\u201325. Springer Nature Switzerland, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-60227-6_2"},{"key":"6_CR21","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.patrec.2020.12.020","volume":"143","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Shi, X., Mi, S., Yang, X.: Image captioning with transformer and knowledge graph. Pattern Recogn. Lett. 143, 43\u201349 (2021)","journal-title":"Pattern Recogn. Lett."},{"key":"6_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107075","volume":"98","author":"J Wang","year":"2020","unstructured":"Wang, J., Wang, W., Wang, L., Wang, Z., Feng, D.D., Tan, T.: Learning visual relationship and context-aware attention for image captioning. Pattern Recogn. 98, 107075 (2020)","journal-title":"Pattern Recogn."}],"container-title":["Lecture Notes in Computer Science","Intelligent Information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6005-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T03:15:45Z","timestamp":1745378145000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6005-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819660049","9789819660056"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6005-6_6","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":"21 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kitakyushu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"23 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}