{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:07:31Z","timestamp":1742911651825,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031581809"},{"type":"electronic","value":"9783031581816"}],"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\/978-3-031-58181-6_35","type":"book-chapter","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T10:03:42Z","timestamp":1719914622000},"page":"419-431","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Image Captioning with\u00a0Visual Positional Embedding and\u00a0Bi-linear Pooling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0277-0379","authenticated-orcid":false,"given":"Sidharth","family":"Nair","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2885-0026","authenticated-orcid":false,"given":"Prithwijit","family":"Guha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,3]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"35_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal Image-TExt Representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Fei, Z.: Attention-aligned transformer for image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 1, pp. 607\u2013615 (2022)","DOI":"10.1609\/aaai.v36i1.19940"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 457\u2013468. ACL (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Gao, Y., Beijbom, O., Zhang, N., Darrell, T.: Compact bilinear pooling. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 317\u2013326 (2016)","DOI":"10.1109\/CVPR.2016.41"},{"key":"35_CR6","unstructured":"Garncarek, \u0141., Powalski, R., Stanis\u0142awek, T., Topolski, B., Halama, P., Grali\u0144ski, F.: LAMBERT: layout-aware (language) modeling using BERT for information extraction (2020). arXiv:cs.CL\/2002.08087"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Zhu, X., Yao, P., Lu, S., Lu, H.: Normalized and geometry-aware self-attention network for image captioning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10324\u201310333 (2020)","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"He, S., Liao, W., Tavakoli, H.R., Yang, M., Rosenhahn, B., Pugeault, N.: Image captioning through image transformer. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69538-5_10"},{"key":"35_CR9","unstructured":"Herdade, S., Kappeler, A., Boakye, K., Soares, J.: Image captioning: transforming objects into words. In: Advances in Neural Information Processing Systems, vol.\u00a032, pp. 11137\u201311147 (2019)"},{"key":"35_CR10","unstructured":"Hong, T., Kim, D., Ji, M., Hwang, W., Nam, D., Park, S.: BROS: a pre-trained language model focusing on text and layout for better key information extraction from documents (2021). arXiv:cs.CL\/2108.04539"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"35_CR13","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Advances in Neural Information Processing Systems, vol.\u00a031 (2018)"},{"key":"35_CR14","unstructured":"Kingma, D.P., Ba, L.J.: Adam: a method for stochastic optimization. In: Proceedings of the Third International Conference on Learning Representations (2015)"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., Mao, Z., Fang, S., Li, H.: ER-SAN: enhanced-adaptive relation self-attention network for image captioning. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, pp. 1081\u20131087 (2022)","DOI":"10.24963\/ijcai.2022\/151"},{"key":"35_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1449\u20131457 (2015)","DOI":"10.1109\/ICCV.2015.170"},{"key":"35_CR18","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, vol.\u00a032 (2019)"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Luo, J., et al.: Semantic-conditional diffusion networks for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23359\u201323368 (2023)","DOI":"10.1109\/CVPR52729.2023.02237"},{"issue":"8","key":"35_CR20","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1109\/JAS.2022.105734","volume":"9","author":"Y Ming","year":"2022","unstructured":"Ming, Y., Hu, N., Fan, C., Feng, F., Zhou, J., Yu, H.: Visuals to text: a comprehensive review on automatic image captioning. IEEE\/CAA J. Autom. Sin. 9(8), 1339\u20131365 (2022)","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10968\u201310977 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1179\u20131195 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"35_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol.\u00a030, pp. 5998\u20136008 (2017)"},{"key":"35_CR24","doi-asserted-by":"crossref","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), pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"35_CR25","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of the 32nd International Conference on Machine Learning, vol.\u00a037, pp. 2048\u20132057 (2015)"},{"key":"35_CR26","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10677\u201310686 (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"35_CR27","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)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"35_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/978-3-030-01270-0_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Yu","year":"2018","unstructured":"Yu, C., Zhao, X., Zheng, Q., Zhang, P., You, X.: Hierarchical bilinear pooling for fine-grained visual recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 595\u2013610. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_35"}],"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\/978-3-031-58181-6_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T08:02:20Z","timestamp":1732348940000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-58181-6_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031581809","9783031581816"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-58181-6_35","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)"}}]}}