{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T12:09:19Z","timestamp":1767528559136,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031585340"},{"type":"electronic","value":"9783031585357"}],"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\/978-3-031-58535-7_2","type":"book-chapter","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T17:01:50Z","timestamp":1719939710000},"page":"14-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Comparative Study on Deep CNN Visual Encoders for Image Captioning"],"prefix":"10.1007","author":[{"given":"M.","family":"Arun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Arivazhagan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Harinisri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P. S.","family":"Raghavi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,3]]},"reference":[{"issue":"12","key":"2_CR1","doi-asserted-by":"publisher","first-page":"8887","DOI":"10.1007\/s00521-019-04228-3","volume":"31","author":"R Ahila Priyadharshini","year":"2019","unstructured":"Ahila Priyadharshini, R., Arivazhagan, S., Arun, M., Mirnalini, A.: Maize leaf disease classification using deep convolutional neural networks. Neural Comput. Appl. 31(12), 8887\u20138895 (2019). https:\/\/doi.org\/10.1007\/s00521-019-04228-3","journal-title":"Neural Comput. Appl."},{"key":"2_CR3","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) (2018). https:\/\/doi.org\/10.1109\/iccubea.2018.8697360","DOI":"10.1109\/iccubea.2018.8697360"},{"key":"2_CR4","doi-asserted-by":"publisher","unstructured":"Anitha Kumari, K., Mouneeshwari, C., Udhaya, R.B., Jasmitha, R.: Automated image captioning for Flickr8k dataset. In: Proceedings of International Conference on Artificial Intelligence, Smart Grid and Smart City Applications, 679\u2013687 (2020). https:\/\/doi.org\/10.1007\/978-3-030-24051-6_62","DOI":"10.1007\/978-3-030-24051-6_62"},{"issue":"8","key":"2_CR5","doi-asserted-by":"publisher","first-page":"2939","DOI":"10.1007\/s00371-021-02166-7","volume":"38","author":"K Bayoudh","year":"2021","unstructured":"Bayoudh, K., Knani, R., Hamdaoui, F., Mtibaa, A.: A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Vis. Comput. 38(8), 2939\u20132970 (2021). https:\/\/doi.org\/10.1007\/s00371-021-02166-7","journal-title":"Vis. Comput."},{"key":"2_CR6","doi-asserted-by":"publisher","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2014). https:\/\/doi.org\/10.3115\/v1\/d14-1179","DOI":"10.3115\/v1\/d14-1179"},{"key":"2_CR7","doi-asserted-by":"publisher","unstructured":"Devlin, J., et al.: Language models for image captioning: the quirks and what works. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) (2015). https:\/\/doi.org\/10.3115\/v1\/p15-2017","DOI":"10.3115\/v1\/p15-2017"},{"issue":"4","key":"2_CR8","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."},{"key":"2_CR9","doi-asserted-by":"publisher","unstructured":"Fang, H., et al.: From captions to visual concepts and back. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015). https:\/\/doi.org\/10.1109\/cvpr.2015.7298754","DOI":"10.1109\/cvpr.2015.7298754"},{"key":"2_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A Farhadi","year":"2010","unstructured":"Farhadi, A., et al.: Every picture tells a story: generating sentences from images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) Computer Vision \u2013 ECCV 2010. LNCS, vol. 6314, pp. 15\u201329. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_2"},{"key":"2_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-3-319-10593-2_35","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Gong","year":"2014","unstructured":"Gong, Y., Wang, L., Hodosh, M., Hockenmaier, J., Lazebnik, S.: Improving image-sentence embeddings using large weakly annotated photo collections. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision \u2013 ECCV 2014. LNCS, vol. 8692, pp. 529\u2013545. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_35"},{"key":"2_CR12","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/cvpr.2016.90"},{"key":"2_CR13","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). https:\/\/doi.org\/10.1613\/jair.3994","journal-title":"J. Artif. Intell. Res."},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Kulkarni, G., et al.: Baby talk: understanding and generating simple image descriptions. In: CVPR 2011 (2011)https:\/\/doi.org\/10.1109\/cvpr.2011.5995466","DOI":"10.1109\/cvpr.2011.5995466"},{"issue":"11","key":"2_CR16","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998). https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc. IEEE"},{"key":"2_CR17","doi-asserted-by":"publisher","unstructured":"Liu, S., Bai, L., Hu, Y., Wang, H.: Image captioning based on deep neural networks. In: MATEC Web of Conferences, vol. 232, p. 01052 (2018). https:\/\/doi.org\/10.1051\/matecconf\/201823201052","DOI":"10.1051\/matecconf\/201823201052"},{"issue":"15","key":"2_CR18","doi-asserted-by":"publisher","first-page":"11373","DOI":"10.1007\/s00521-019-04632-9","volume":"32","author":"A Madakannu","year":"2019","unstructured":"Madakannu, A., Selvaraj, A.: DIGI-net: a deep convolutional neural network for multi-format digit recognition. Neural Comput. Appl. 32(15), 11373\u201311383 (2019). https:\/\/doi.org\/10.1007\/s00521-019-04632-9","journal-title":"Neural Comput. Appl."},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.91","DOI":"10.1109\/cvpr.2016.91"},{"key":"2_CR20","doi-asserted-by":"publisher","first-page":"102490","DOI":"10.1016\/j.displa.2023.102490","volume":"79","author":"R Yang","year":"2023","unstructured":"Yang, R., Cui, X., Qin, Q., Deng, Z., Lan, R., Luo, X.: Fast RF-UIC: a fast unsupervised image captioning model. Displays 79, 102490 (2023). https:\/\/doi.org\/10.1016\/j.displa.2023.102490","journal-title":"Displays"},{"key":"2_CR21","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations (ICLR 2015) (2015). https:\/\/arxiv.org\/pdf\/1409.1556.pdf"},{"key":"2_CR22","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1162\/tacl_a_00177","volume":"2","author":"R Socher","year":"2014","unstructured":"Socher, R., Karpathy, A., Le, Q.V., Manning, C.D., Ng, A.Y.: Grounded compositional semantics for finding and describing images with sentences. Trans. Assoc. Comput. Linguist. 2, 207\u2013218 (2014). https:\/\/doi.org\/10.1162\/tacl_a_00177","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"2_CR23","doi-asserted-by":"publisher","unstructured":"Sun, C., Gan, C., Nevatia, R.: Automatic concept discovery from parallel text and visual corpora. In: 2015 IEEE International Conference on Computer Vision (ICCV) (2015). https:\/\/doi.org\/10.1109\/iccv.2015.298","DOI":"10.1109\/iccv.2015.298"},{"key":"2_CR24","doi-asserted-by":"publisher","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015). https:\/\/doi.org\/10.1109\/cvpr.2015.7298594","DOI":"10.1109\/cvpr.2015.7298594"},{"key":"2_CR25","unstructured":"Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. In: 36th International Conference on Machine Learning, pp. 6105\u20136114 (2019). https:\/\/arxiv.org\/abs\/1905.11946"},{"issue":"1","key":"2_CR26","doi-asserted-by":"publisher","first-page":"012029","DOI":"10.1088\/1742-6596\/2335\/1\/012029","volume":"2335","author":"S Veena","year":"2022","unstructured":"Veena, S., Ashwin, K.S., Gupta, P.: Comparison of various CNN encoders for image captioning. J. Phys: Conf. Ser. 2335(1), 012029 (2022). https:\/\/doi.org\/10.1088\/1742-6596\/2335\/1\/012029","journal-title":"J. Phys: Conf. Ser."},{"key":"2_CR27","doi-asserted-by":"publisher","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015). https:\/\/doi.org\/10.1109\/cvpr.2015.7298935","DOI":"10.1109\/cvpr.2015.7298935"},{"key":"2_CR28","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014). https:\/\/doi.org\/10.1162\/tacl_a_00166","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"2_CR29","doi-asserted-by":"publisher","first-page":"108429","DOI":"10.1016\/j.compeleceng.2022.108429","volume":"104","author":"Z Zhang","year":"2022","unstructured":"Zhang, Z., Zhang, H., Wang, J., Sun, Z., Yang, Z.: Generating news image captions with semantic discourse extraction and contrastive style-coherent learning. Comput. Electri. Eng. 104, 108429 (2022). https:\/\/doi.org\/10.1016\/j.compeleceng.2022.108429","journal-title":"Comput. Electri. Eng."}],"container-title":["Communications in Computer and Information Science","Computer Vision and Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-58535-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T17:02:24Z","timestamp":1719939744000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-58535-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031585340","9783031585357"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-58535-7_2","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision and Image Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jammu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"3 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 November 2023","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":"cvip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iitjammu.ac.in\/cvip2023\/","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":"Online CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"461","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":"140","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":"30% - 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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}