{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T09:53:25Z","timestamp":1743069205283,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031243660"},{"type":"electronic","value":"9783031243677"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-24367-7_7","type":"book-chapter","created":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T16:04:38Z","timestamp":1673971478000},"page":"82-101","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automatic Image Caption Generation Using ResNet & Torch Vision"],"prefix":"10.1007","author":[{"given":"Vijeta","family":"Verma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sri Khetwat","family":"Saritha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sweta","family":"Jain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,18]]},"reference":[{"key":"7_CR1","unstructured":"Popular Mechanics, Google's Image-Captioning AI Is Getting Scary Good. .https:\/\/www.popularmechanics.com\/technology\/robots\/a23019\/google-aicaptioning. Accessed 28 March 2022"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Vijay, K., Ramya, D.: Generation of caption selection for news images using stemming algorithm. In: International Conference on Computation of Power, Energy, Information and Communication (ICCPEIC), pp. 0536\u20130540 (2015)","DOI":"10.1109\/ICCPEIC.2015.7259513"},{"key":"7_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/VCIP.2017.8305157","volume":"2017","author":"X Wei","year":"2017","unstructured":"Wei, X., Qi, Y., Liu, J., Liu, F.: Image retrieval by dense caption reasoning. IEEE Visual Commun. Image Process. 2017, 1\u20134 (2017). https:\/\/doi.org\/10.1109\/VCIP.2017.8305157","journal-title":"IEEE Visual Commun. Image Process."},{"issue":"6","key":"7_CR4","doi-asserted-by":"publisher","first-page":"2743","DOI":"10.1109\/TIP.2018.2889922","volume":"28","author":"N Yu","year":"2019","unstructured":"Yu, N., Hu, X., Song, B., Yang, J., Zhang, J.: Topic-oriented image captioning based on order-embedding. IEEE Trans. Image Process. 28(6), 2743\u20132754 (2019). https:\/\/doi.org\/10.1109\/TIP.2018.2889922","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"7_CR5","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1109\/TMM.2018.2869276","volume":"21","author":"M Yang","year":"2019","unstructured":"Yang, M., et al.: Multitask learning for cross-domain image captioning. IEEE Trans. Multimedia 21(4), 1047\u20131061 (2019). https:\/\/doi.org\/10.1109\/TMM.2018.2869276","journal-title":"IEEE Trans. Multimedia"},{"key":"7_CR6","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1109\/ICPHYS.2019.8780171","volume":"2019","author":"RC Luo","year":"2019","unstructured":"Luo, R.C., Hsu, Y.-T., Wen, Y.-C., Ye, H.-J.: Visual image caption generation for service robotics and industrial applications. IEEE Int. Conf. Indust. Cyber Phys. Syst. 2019, 827\u2013832 (2019). https:\/\/doi.org\/10.1109\/ICPHYS.2019.8780171","journal-title":"IEEE Int. Conf. Indust. Cyber Phys. Syst."},{"key":"7_CR7","doi-asserted-by":"publisher","unstructured":"Yanagimoto, H., Shozu, M.: Multiple perspective caption generation with attention mechanism. In: 2020 9th International Congress on Advanced Applied Informatics (IIAI-AAI), pp. 110\u2013115 (2020). https:\/\/doi.org\/10.1109\/IIAI-AAI50415.2020.00031","DOI":"10.1109\/IIAI"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Panicker, M.J., Upadhayay, V., Sethi, G., Mathur, V.: Image caption generator. Int. J. Innov. Technol. Explor. Eng. 10(3) (2021). ISSN: 2278\u20133075","DOI":"10.35940\/ijitee.C8383.0110321"},{"key":"7_CR9","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s40537-022-00571-w","volume":"9","author":"MA Al-Malla","year":"2022","unstructured":"Al-Malla, M.A., Jafar, A., Ghneim, N.: Image captioning model using attention and object features to mimic human image understanding. J. Big Data 9, 20 (2022). https:\/\/doi.org\/10.1186\/s40537-022-00571-w","journal-title":"J. Big Data"},{"key":"7_CR10","unstructured":"Lazar, D.: Building a ResNet in Keras (2020). https:\/\/towardsdatascience.com\/building-a-resnet-in-keras-e8f1322a49ba. Accessed 04 Mar 2022"},{"key":"7_CR11","unstructured":"Feng, V.: An Overview of ResNet and its Variants (2017). https:\/\/towardsdatascience.com\/an-overview-of-resnet-and-its-variants-5281e2f56035. Accessed 04 Mar 2022"},{"key":"7_CR12","unstructured":"Soheyla, A., Khaled, R., Thiab, T., Hamid, A.: Automatic Generation of Descriptive Titles for Video Clips Using Deep Learning (2021)"},{"key":"7_CR13","doi-asserted-by":"publisher","unstructured":"Jagannath, A.: Image captioning using deep learning. Int. J. Res. Appl. Sci. Eng. Technol. 8. 1430\u20131435 (2020). https:\/\/doi.org\/10.22214\/ijraset.2020.6232","DOI":"10.22214\/ijraset.2020.6232"},{"key":"7_CR14","doi-asserted-by":"publisher","unstructured":"Vijay, K., Ramya, D.: Generation of caption selection for news images using stemming algorithm. In: 2015 International Conference on Computation of Power, Energy, Information and Communication (ICCPEIC), pp. 0536\u20130540 (2015). https:\/\/doi.org\/10.1109\/ICCPEIC.2015.7259513","DOI":"10.1109\/ICCPEIC.2015.7259513"},{"key":"7_CR15","doi-asserted-by":"publisher","unstructured":"Varsha, K., Vaidehi, M., Megha, K.: Deep Learning based Automatic Image Caption Generation, pp. 1\u20136 (2019). https:\/\/doi.org\/10.1109\/GCAT47503.2019.8978293","DOI":"10.1109\/GCAT47503.2019.8978293"},{"key":"7_CR16","doi-asserted-by":"publisher","unstructured":"Amritkar, C., Jabade, V.: Image caption generation using deep learning technique. In: 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), pp. 1\u20134 (2018). https:\/\/doi.org\/10.1109\/ICCUBEA.2018.8697360","DOI":"10.1109\/ICCUBEA.2018.8697360"},{"key":"7_CR17","doi-asserted-by":"publisher","unstructured":"Xi, S.M., Cho, Y.I.: Image caption automatic generation method based on weighted feature. In: 2013 13th International Conference on Control, Automation and Systems (ICCAS 2013), pp. 548\u2013551 (2013). https:\/\/doi.org\/10.1109\/ICCAS.2013.6703998","DOI":"10.1109\/ICCAS.2013.6703998"},{"key":"7_CR18","doi-asserted-by":"publisher","unstructured":"Pranay, M., Aman, G., Aayush, Y., Anurag, M., Nand, B.: Camera2Caption: a real-time image caption generator, pp. 1\u20136 (2017). https:\/\/doi.org\/10.1109\/ICCIDS.2017.8272660","DOI":"10.1109\/ICCIDS.2017.8272660"},{"key":"7_CR19","unstructured":"Kuznetsova, P.,Ordonez, V., Berg, T.L., Choi, Y.: Treetalk: composition and compression of trees for image descriptions. ACL (2014)"},{"key":"7_CR20","unstructured":"Priyanka, K., Malde, N., Aromal, N., Saurabh, P., Sharma, G.: Visual Image Caption Generator Using Deep Learning (ICAST-2019) (2019)"},{"key":"7_CR21","unstructured":"Aker, A., Gaizauskas, R.: Generating Image Descriptions Using Dependency Relational Patterns. Annual Meeting of the Association for Computational Linguistics, pp. 1250\u20131258 (2010)"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Vinyals, O., et al.: Show and tell: a neural image caption generator. In: Computer Vision and Pattern Recognition. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Wadhwa, T., Virk, H., Aghav, J., Image, S.B.: Captioning using deep learning. Int. J. Res. Appl. Sci. Eng. Technol. 8(VI) (2020)","DOI":"10.22214\/ijraset.2020.6232"},{"key":"7_CR24","unstructured":"Kaviyarasu, B., .Krishnakumar, B., Kousalya, K., Gokul, S., Karthikeyan, R.: Image caption generator using deep learning. Int. J. Adv. Sci. Technol. 29(3s), 975\u2013980 (2020)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Hoxha, G., Melgani, F., Slaghenauffi, J.: A New CNN-RNN Framework For Remote Sensing Image Captioning. In: 2020 Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS), pp. 1\u20134 (2020)","DOI":"10.1109\/M2GARSS47143.2020.9105191"}],"container-title":["Communications in Computer and Information Science","Machine Learning, Image Processing, Network Security and Data Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-24367-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T16:09:47Z","timestamp":1673971787000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-24367-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031243660","9783031243677"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-24367-7_7","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"18 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MIND","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Image Processing, Network Security and Data Sciences","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mind2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/conf.manit.ac.in\/mind2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"399","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":"64","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":"16% - 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":"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":"5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}