{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:37:01Z","timestamp":1742913421062,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031192135"},{"type":"electronic","value":"9783031192142"}],"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.springer.com\/tdm"},{"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.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19214-2_38","type":"book-chapter","created":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T00:03:45Z","timestamp":1668643425000},"page":"450-459","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Efficiency and\u00a0Quality of\u00a0Image Caption Generation with\u00a0CARU"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8670-1283","authenticated-orcid":false,"given":"Xuefei","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0952-0961","authenticated-orcid":false,"given":"Wei","family":"Ke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2811-8962","authenticated-orcid":false,"given":"Hao","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,17]]},"reference":[{"key":"38_CR1","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, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"38_CR2","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, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"38_CR3","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."},{"issue":"7553","key":"38_CR4","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Parikh, H., Sawant, H., Parmar, B., Shah, R., Chapaneri, S., Jayaswal, D.: Encoder-decoder architecture for image caption generation. In: 2020 3rd International Conference on Communication System, Computing and IT Applications (CSCITA), pp. 174\u2013179. IEEE (2020)","DOI":"10.1109\/CSCITA47329.2020.9137802"},{"key":"38_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1007\/978-3-030-63830-6_58","volume-title":"Neural Information Processing","author":"K-H Chan","year":"2020","unstructured":"Chan, K.-H., Ke, W., Im, S.-K.: CARU: a content-adaptive recurrent unit for the transition of hidden state in NLP. In: Yang, H., Pasupa, K., Leung, A.C.-S., Kwok, J.T., Chan, J.H., King, I. (eds.) ICONIP 2020. LNCS, vol. 12532, pp. 693\u2013703. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-63830-6_58"},{"key":"38_CR9","unstructured":"Kuznetsova, P., Ordonez, V., Berg, A., Berg, T., Choi, Y.: Collective generation of natural image descriptions. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 359\u2013368 (2012)"},{"issue":"9","key":"38_CR10","doi-asserted-by":"publisher","first-page":"16600","DOI":"10.1109\/TITS.2022.3149657","volume":"23","author":"H Xu","year":"2022","unstructured":"Xu, H., Cai, Z., Li, R., Li, W.: Efficient CityCam-to-edge cooperative learning for vehicle counting in ITS. IEEE Trans. Intell. Transp. Syst. 23(9), 16600\u201316611 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"6","key":"38_CR11","doi-asserted-by":"publisher","first-page":"4242","DOI":"10.1109\/TII.2019.2950057","volume":"16","author":"J Wang","year":"2019","unstructured":"Wang, J., Cai, Z., Yu, J.: Achieving personalized $$ k $$-anonymity-based content privacy for autonomous vehicles in CPS. IEEE Trans. Industr. Inf. 16(6), 4242\u20134251 (2019)","journal-title":"IEEE Trans. Industr. Inf."},{"key":"38_CR12","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). arXiv preprint arXiv:1412.6632 (2014)"},{"key":"38_CR13","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, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"38_CR14","series-title":"EAI\/Springer Innovations in Communication and Computing","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-030-76167-7_9","volume-title":"Concepts and Real-Time Applications of Deep Learning","author":"A Sawarn","year":"2021","unstructured":"Sawarn, A., Srivastava, S., Gupta, M., Srivastava, S.: BeamAtt: generating medical diagnosis from chest X-Rays using sampling-based intelligence. In: Srivastava, S., Khari, M., Gonzalez Crespo, R., Chaudhary, G., Arora, P. (eds.) Concepts and Real-Time Applications of Deep Learning. EICC, pp. 135\u2013150. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-76167-7_9"},{"issue":"1","key":"38_CR15","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1861\/1\/012044","volume":"1861","author":"Y Pan","year":"2021","unstructured":"Pan, Y., Wang, L., Duan, S., Gan, X., Hong, L.: Chinese image caption of inceptionv4 and double-layer GRUs based on attention mechanism. J. Phys. Conf. Ser. 1861(1), 012044 (2021)","journal-title":"J. Phys. Conf. Ser."},{"key":"38_CR16","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"38_CR18","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"}],"container-title":["Lecture Notes in Computer Science","Wireless Algorithms, Systems, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19214-2_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T00:24:01Z","timestamp":1668644641000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19214-2_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031192135","9783031192142"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19214-2_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WASA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Wireless Algorithms, Systems, and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dalian","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"24 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":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wasa2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/wasa-conference.org\/WASA2022\/","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":"265","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":"95","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":"62","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":"36% - 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":"8","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)"}}]}}