{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T03:29:59Z","timestamp":1771558199816,"version":"3.50.1"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031440830","type":"print"},{"value":"9783031440847","type":"electronic"}],"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\/978-3-031-44084-7_3","type":"book-chapter","created":{"date-parts":[[2023,9,23]],"date-time":"2023-09-23T09:02:09Z","timestamp":1695459729000},"page":"25-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Image Captioning Using Xception-Long Short-Term Memory"],"prefix":"10.1007","author":[{"given":"Nisha","family":"Panchal","sequence":"first","affiliation":[]},{"given":"Dweepna","family":"Garg","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,24]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","unstructured":"Mathews, A.: Captioning images using different styles. In: MM 2015 \u2013 Proceedings of the 2015 ACM Multimedia Conference, Oct 2015, pp. 665\u2013668 (2015). https:\/\/doi.org\/10.1145\/2733373.2807998","DOI":"10.1145\/2733373.2807998"},{"issue":"11","key":"3_CR2","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1109\/TMM.2015.2477044","volume":"17","author":"K Cho","year":"2015","unstructured":"Cho, K., Courville, A., Bengio, Y.: Describing multimedia content using attention-based encoder-decoder networks. IEEE Trans. Multimedia 17(11), 1875\u20131886 (2015). https:\/\/doi.org\/10.1109\/TMM.2015.2477044","journal-title":"IEEE Trans. Multimedia"},{"issue":"4","key":"3_CR3","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2017","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 677\u2013691 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2599174","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"3_CR4","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"A Karpathy","year":"2017","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 664\u2013676 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2598339","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"3_CR5","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1109\/TMM.2017.2729019","volume":"19","author":"L Gao","year":"2017","unstructured":"Gao, L., Guo, Z., Zhang, H., Xu, X., Shen, H.T.: Video captioning with attention-based LSTM and semantic consistency. IEEE Trans. Multimedia 19(9), 2045\u20132055 (2017). https:\/\/doi.org\/10.1109\/TMM.2017.2729019","journal-title":"IEEE Trans. Multimedia"},{"issue":"11","key":"3_CR6","doi-asserted-by":"publisher","first-page":"5600","DOI":"10.1109\/TIP.2018.2855422","volume":"27","author":"Y Yang","year":"2018","unstructured":"Yang, Y., et al.: Video captioning by adversarial LSTM. IEEE Trans. Image Process. 27(11), 5600\u20135611 (2018). https:\/\/doi.org\/10.1109\/TIP.2018.2855422","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"3_CR7","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1109\/TPAMI.2017.2708709","volume":"40","author":"Q Wu","year":"2018","unstructured":"Wu, Q., Shen, C., Wang, P., Dick, A., van den Hengel, A.: Image captioning and visual question answering based on attributes and external knowledge. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1367\u20131381 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2708709","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"3_CR8","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1109\/TGRS.2017.2776321","volume":"56","author":"X Lu","year":"2018","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 (2018). https:\/\/doi.org\/10.1109\/TGRS.2017.2776321","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"3_CR9","doi-asserted-by":"publisher","first-page":"6143","DOI":"10.1007\/s10586-018-1885-9","volume":"22","author":"M Han","year":"2019","unstructured":"Han, M., Chen, W., Moges, A.D.: Fast image captioning using LSTM. Clust. Comput. 22, 6143\u20136155 (2019). https:\/\/doi.org\/10.1007\/s10586-018-1885-9","journal-title":"Clust. Comput."},{"issue":"5","key":"3_CR10","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.1109\/TMM.2019.2941820","volume":"22","author":"N Xu","year":"2020","unstructured":"Xu, N., et al.: Multi-level policy and reward-based deep reinforcement learning framework for image captioning. IEEE Trans. Multimedia 22(5), 1372\u20131383 (2020). https:\/\/doi.org\/10.1109\/TMM.2019.2941820","journal-title":"IEEE Trans. Multimedia"},{"issue":"12","key":"3_CR11","doi-asserted-by":"publisher","first-page":"4467","DOI":"10.1109\/TCSVT.2019.2947482","volume":"30","author":"J Yu","year":"2020","unstructured":"Yu, J., Li, J., Yu, Z., Huang, Q.: Multimodal transformer with multi-view visual representation for image captioning. IEEE Trans. Circuits Syst. Video Technol. 30(12), 4467\u20134480 (2020). https:\/\/doi.org\/10.1109\/TCSVT.2019.2947482","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3_CR12","doi-asserted-by":"publisher","unstructured":"Turkerud, I.R., Mengshoel, O.J.: Image captioning using deep learning: text augmentation by paraphrasing via back translation (2021). https:\/\/doi.org\/10.1109\/SSCI50451.2021.9659834","DOI":"10.1109\/SSCI50451.2021.9659834"},{"key":"3_CR13","doi-asserted-by":"publisher","unstructured":"Chen, N., et al.: Distributed attention for grounded image captioning. In: MM 2021 \u2013 Proceedings of the 29th ACM International Conference on Multimedia, Oct 2021, pp. 1966\u20131975. https:\/\/doi.org\/10.1145\/3474085.3475354","DOI":"10.1145\/3474085.3475354"},{"key":"3_CR14","doi-asserted-by":"publisher","first-page":"18289","DOI":"10.1109\/ACCESS.2022.3150414","volume":"10","author":"P Mahalakshmi","year":"2022","unstructured":"Mahalakshmi, P., Fatima, N.S.: Summarization of text and image captioning in information retrieval using deep learning techniques. IEEE Access 10, 18289\u201318297 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3150414","journal-title":"IEEE Access"},{"key":"3_CR15","doi-asserted-by":"publisher","unstructured":"Ji, J., Ma, Y., Sun, X., Zhou, Y., Wu, Y., Ji, R.: Knowing what to learn: a metric-oriented focal mechanism for image captioning. IEEE Trans. Image Process. 31, 4321\u20134335 (2022). https:\/\/doi.org\/10.1109\/tip.2022.3183434","DOI":"10.1109\/tip.2022.3183434"},{"key":"3_CR16","doi-asserted-by":"publisher","first-page":"45219","DOI":"10.1109\/ACCESS.2022.3169781","volume":"10","author":"JW Bae","year":"2022","unstructured":"Bae, J.W., Lee, S.H., Kim, W.Y., Seong, J.H., Seo, D.H.: Image captioning model using part-of-speech guidance module for description with diverse vocabulary. IEEE Access 10, 45219\u201345229 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3169781","journal-title":"IEEE Access"},{"key":"3_CR17","doi-asserted-by":"publisher","first-page":"24852","DOI":"10.1109\/ACCESS.2022.3151874","volume":"10","author":"R Ramos","year":"2022","unstructured":"Ramos, R., Martins, B.: Using neural encoder-decoder models with continuous outputs for remote sensing image captioning. IEEE Access 10, 24852\u201324863 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3151874","journal-title":"IEEE Access"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"3_CR19","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 (CVPR), pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"3_CR20","unstructured":"Xu, K., et al.: Neural image caption generation with visual attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3121\u20133129 (2015)"},{"key":"3_CR21","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 (CVPR), pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"3_CR22","unstructured":"Li, X., Yin, X., Li, C., Hu, Z., Zhang, H., Sun, F.: VLP: vision-language pre-training for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10976\u201310985 (2020)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1635\u20131644 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"3_CR24","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Unicoder-VL: a universal encoder for vision and language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2238\u20132247 (2021)"},{"key":"3_CR25","unstructured":"Huang, L., Li, Y., Shen, J., Wu, J.: Parallel decoding of hierarchical structure for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11168\u201311177 (2021)"},{"key":"3_CR26","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47, 853\u2013899 (2013)","journal-title":"J. Artif. Intell. Res."}],"container-title":["Lecture Notes in Computer Science","Mining Intelligence and Knowledge Exploration"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44084-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,23]],"date-time":"2023-09-23T09:02:28Z","timestamp":1695459748000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44084-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031440830","9783031440847"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44084-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"24 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MIKE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Mining Intelligence and Knowledge Exploration","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kristiansand","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 June 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 June 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mike2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mike.org.in\/2023\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"87","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":"22","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":"16","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":"25% - 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","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)"}}]}}