{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:27:50Z","timestamp":1742912870331,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819916412"},{"type":"electronic","value":"9789819916429"}],"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\/978-981-99-1642-9_12","type":"book-chapter","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T12:14:57Z","timestamp":1681388097000},"page":"136-147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generating Textual Description Using Modified Beam Search"],"prefix":"10.1007","author":[{"given":"Divyansh","family":"Rai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arpit","family":"Agarwal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bagesh","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"O. P.","family":"Vyas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suhaib","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Shourya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"12_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv:1409.0473 (2014)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using rnn encoder-decoder for statistical machine translation cite arxiv:1406.1078 (2014). Comment: EMNLP 2014","DOI":"10.3115\/v1\/D14-1179"},{"key":"12_CR3","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Over feat: integrated recognition, localization, and detection using convolutional networks (2013)"},{"key":"12_CR4","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation (2002). https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"12_CR5","doi-asserted-by":"publisher","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator, pp. 3156\u20133164. https:\/\/doi.org\/10.1109\/CVPR.2015.7298935 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"12_CR6","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention (2015)"},{"key":"12_CR7","unstructured":"Owoputi, O., O\u2019Connor, B., Dyer, C., Gimpel, K., Schneider, N., Smith, N.A.: Improved part-of-speech tagging for online conversational text with word clusters. In: 2013 Proceedings of NAACL-HLT, pp. 380\u2013390 (2013)"},{"key":"12_CR8","doi-asserted-by":"publisher","unstructured":"Freitag, M., Al-Onaizan, Y.: Beam search strategies for neural machine translation, pp. 56\u201360 (2017). https:\/\/doi.org\/10.18653\/v1\/W17-3207","DOI":"10.18653\/v1\/W17-3207"},{"key":"12_CR9","unstructured":"Ozkan, E., Roig, G., Goksel, O., Boix, X.: Herding generalizes diverse M-best solutions (2016)"},{"key":"12_CR10","doi-asserted-by":"publisher","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20139 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"12_CR11","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR, abs\/1409.1556 (2015)"},{"key":"12_CR12","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, 1735\u201380 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"key":"12_CR13","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1017\/S1351324918000098","volume":"24","author":"M Tanti","year":"2018","unstructured":"Tanti, M., Gatt, A., Camilleri, K.: Where to put the image in an image caption generator. Nat. Lang. Eng. 24, 467\u2013489 (2018)","journal-title":"Nat. Lang. Eng."},{"key":"12_CR14","doi-asserted-by":"publisher","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description, pp. 2625\u20132634 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298878","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"12_CR15","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.: Multimodal Neural Language Models. In: Proceedings of the 31st International Conference on Machine Learning, in Proceedings of Machine Learning Research, vol. 32, no. 2, pp. 595\u2013603 (2014). https:\/\/proceedings.mlr.press\/v32\/kiros14.html"},{"key":"12_CR16","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). In: ICLR (2015)"},{"key":"12_CR17","doi-asserted-by":"publisher","unstructured":"Chen, X., Zitnick, C.: Mind\u2019s eye: a recurrent visual representation for image caption generation, pp. 2422\u20132431 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298856","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"12_CR18","doi-asserted-by":"publisher","unstructured":"Wiseman, S., Rush, A.: Sequence-to-sequence learning as beam-search optimization, pp. 1296\u20131306 (2016). https:\/\/doi.org\/10.18653\/v1\/D16-1137","DOI":"10.18653\/v1\/D16-1137"},{"key":"12_CR19","unstructured":"Cohen, E., Beck, C.: Empirical analysis of beam search performance degradation in neural sequence models. In: Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research, vol. 97, pp. 1290\u20131299 (2019). https:\/\/proceedings.mlr.press\/v97\/cohen19a.html"},{"key":"12_CR20","unstructured":"Xie, H., Sherborne, T., Kuhnle, A., Copestake, A.: Going beneath the surface: evaluating image captioning for grammaticality, truthfulness and diversity (2019)"},{"key":"12_CR21","doi-asserted-by":"publisher","unstructured":"Xu, G., Niu, S., Tan, M., Luo, Y., Du, Q., Wu, Q.: Towards accurate text-based image captioning with content diversity exploration. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12632\u201312641 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01245","DOI":"10.1109\/CVPR46437.2021.01245"},{"key":"12_CR22","unstructured":"Sundaramoorthy, C., Kelvin, L., Sarin, M., Gupta, S.: End-to-end attention-based image captioning (2021)"},{"key":"12_CR23","doi-asserted-by":"publisher","unstructured":"Sadler, P., Scheffler, T., Schlangen, D.: Can neural image captioning be controlled via forced attention?, pp. 427\u2013431 (2019). https:\/\/doi.org\/10.18653\/v1\/W19-8653","DOI":"10.18653\/v1\/W19-8653"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Sun, Q., Lee, S., Batra, D.: Bidirectional beam search: forward-backward inference in neural sequence models for fill-in-the-blank image captioning (2017)","DOI":"10.1109\/CVPR.2017.763"},{"key":"12_CR25","unstructured":"Agnihotri, S.: Hyperparameter optimization on neural machine translation. Creat. Components 124 (2019). https:\/\/lib.dr.iastate.edu\/creativecomponents\/124"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Elliott, D., Keller, F.: Comparing automatic evaluation measures for image description. In: ACL, pp. 452\u2013457 (2014)","DOI":"10.3115\/v1\/P14-2074"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"You, Q., et al.: Image Captioning with semantic attention. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Hsu, T.-Y., Giles, C., Huang, T-H.: SCICAP: generating captions for scientific figures (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.277"},{"key":"12_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/978-3-030-68780-9_32","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"M Kalimuthu","year":"2021","unstructured":"Kalimuthu, M., Mogadala, A., Mosbach, M., Klakow, D.: Fusion models for improved image captioning. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12666, pp. 381\u2013395. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68780-9_32"},{"key":"12_CR30","doi-asserted-by":"publisher","unstructured":"Fisch, A., Lee, K., Chang, M.-W., Clark, J., Barzilay, R.: CapWAP: image captioning with a purpose, pp. 8755\u20138768 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.705","DOI":"10.18653\/v1\/2020.emnlp-main.705"},{"key":"12_CR31","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1109\/TCYB.2020.2997034","volume":"52","author":"M Liu","year":"2020","unstructured":"Liu, M., Hu, H., Li, L., Yu, Y., Guan, W.: Chinese image caption generation via visual attention and topic modeling. IEEE Trans. Cybern. 52, 1247\u20131257 (2020)","journal-title":"IEEE Trans. Cybern."},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Laskar, S.R., Singh, R.P., Pakray, P., Bandyopadhyay, S.: English to Hindi multi-modal neural machine translation and Hindi image captioning. In: Proceedings of the 6th Workshop on Asian Translation. Association for Computational Linguistics, Hong Kong (2019)","DOI":"10.18653\/v1\/D19-5205"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, J., Sun, Y.: End-to-end transformer based model for image captioning (2022)","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"12_CR34","doi-asserted-by":"publisher","unstructured":"Cornia, M., Baraldi, L., Cucchiara, R.: Explaining transformer-based image captioning models: an empirical analysis, pp. 111\u2013129 (2022). https:\/\/doi.org\/10.3233\/AIC-210172","DOI":"10.3233\/AIC-210172"},{"key":"12_CR35","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale (2020)"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"12_CR37","unstructured":"Herdade, S., Kappeler, A., Boakye, K., Soares, J.: Image captioning: transforming objects into words (2019)"},{"key":"12_CR38","doi-asserted-by":"publisher","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 10575\u201310584 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01059","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and VQA (2019)","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1642-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T12:23:58Z","timestamp":1681388638000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1642-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916412","9789819916429"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1642-9_12","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","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":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","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":"359","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":"44% - 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":"2.65","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","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)"}},{"value":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}