{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T22:17:58Z","timestamp":1743113878032,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030209834"},{"type":"electronic","value":"9783030209841"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-20984-1_2","type":"book-chapter","created":{"date-parts":[[2019,5,27]],"date-time":"2019-05-27T23:03:25Z","timestamp":1558998205000},"page":"18-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Image Captioning Method for Infant Sleeping Environment Diagnosis"],"prefix":"10.1007","author":[{"given":"Xinyi","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mariofanna","family":"Milanova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,15]]},"reference":[{"key":"2_CR1","unstructured":"https:\/\/www1.nichd.nih.gov\/sts\/about\/SIDS\/Pages\/default.aspx. Accessed 01 June 2018"},{"key":"2_CR2","unstructured":"https:\/\/www.cdc.gov\/sids\/data.htm. Accessed 01 June 2018"},{"key":"2_CR3","unstructured":"Kiros, R, Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)"},{"key":"2_CR4","unstructured":"Mao, J., Xu, W., Yang, Y., et al.: Deep captioning with multimodal recurrent neural networks (m-RNN). arXiv preprint arXiv:1412.6632 (2014)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Wu, Q., Shen, C., Liu, L., et al.: What value do explicit high level concepts have in vision to language problems? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 203\u2013212 (2016)","DOI":"10.1109\/CVPR.2016.29"},{"issue":"3","key":"2_CR6","first-page":"154","volume":"4","author":"X Liu","year":"2018","unstructured":"Liu, X., Milanova, M.: Visual attention in deep learning: a review. Int. Rob. Auto. J. 4(3), 154\u2013155 (2018)","journal-title":"Int. Rob. Auto. J."},{"key":"2_CR7","unstructured":"http:\/\/pediatrics.aappublications.org\/content\/early\/2016\/10\/20\/peds.2016-2938"},{"key":"2_CR8","unstructured":"https:\/\/store.nanit.com\/. Accessed 01 June 2018"},{"key":"2_CR9","unstructured":"https:\/\/owletcare.com\/. Accessed 01 June 2018"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Fang, H., Gupta, S., Iandola, F., et al.: From captions to visual concepts and back. In: Proceedings of the IEEE Conference on Computer Vision And Pattern Recognition, pp. 1473\u20131482 (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"2_CR11","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 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"issue":"1","key":"2_CR12","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., et al.: Grounded compositional semantics for finding and describing images with sentences. Trans. Assoc. Comput. Linguist. 2(1), 207\u2013218 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., et al.: Show and tell: a neural image caption generator. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"2_CR14","unstructured":"Xu, K., Ba, J., Kiros, R., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"issue":"3","key":"2_CR15","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/TPAMI.2014.2345401","volume":"37","author":"MM Cheng","year":"2015","unstructured":"Cheng, M.M., Mitra, N.J., Huang, X., et al.: Global contrast based salient region detection. IEEE Trans. Patt. Anal. Mach. Intell. 37(3), 569\u2013582 (2015)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"2_CR16","unstructured":"Mnih, V., Heess, N., Graves, A.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, pp. 2204\u20132212 (2014)"},{"key":"2_CR17","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. arXiv preprint arXiv:1412.7755 (2014)"},{"key":"2_CR18","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1162\/089976600300015015","volume":"12","author":"FA Gers","year":"2000","unstructured":"Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Neural Comput. 12, 2451\u20132471 (2000)","journal-title":"Neural Comput."},{"key":"2_CR19","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1109\/TSMC.1973.4309314","volume":"6","author":"RM Haralick","year":"1973","unstructured":"Haralick, R.M., Shanmugam, K.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. 6, 610\u2013621 (1973)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"issue":"9","key":"2_CR20","doi-asserted-by":"publisher","first-page":"8424","DOI":"10.3390\/rs6098424","volume":"6","author":"X Huang","year":"2014","unstructured":"Huang, X., Liu, X., Zhang, L.: A multichannel gray level co-occurrence matrix for multi\/hyperspectral image texture representation. Remote Sens. 6(9), 8424\u20138445 (2014)","journal-title":"Remote Sens."},{"issue":"2","key":"2_CR21","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1109\/36.752194","volume":"37","author":"LK Soh","year":"1999","unstructured":"Soh, L.K., Tsatsoulis, C.: Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Trans. Geosci. Remote Sens. 37(2), 780\u2013795 (1999)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2_CR22","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"2_CR23","unstructured":"Chen, X., Fang, H., Lin, T.Y., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"issue":"12","key":"2_CR24","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kulkarni","year":"2013","unstructured":"Kulkarni, G., Premraj, V., Ordonez, V., et al.: Babytalk: understanding and generating simple image descriptions. IEEE Trans. Patt. Anal. Mach. Intell. 35(12), 2891\u20132903 (2013)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"2_CR25","unstructured":"Mitchell, M., Han, X., Dodge, J., et al.: Midge: generating image descriptions from computer vision detections. In: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pp. 747\u2013756. Association for Computational Linguistics (2012)"},{"key":"2_CR26","unstructured":"Yang, Y., Teo, C.L., Daum\u00e9 III, H., et al.: Corpus-guided sentence generation of natural images. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 444\u2013454. Association for Computational Linguistics (2011)"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Davis, J., Goadrich, M.: The relationship between Precision-Recall and ROC curves. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 233\u2013240. ACM (2006)","DOI":"10.1145\/1143844.1143874"},{"issue":"4","key":"2_CR28","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/5254.708428","volume":"13","author":"MA Hearst","year":"1998","unstructured":"Hearst, M.A., Dumais, S.T., Osuna, E., et al.: Support vector machines. IEEE Intell. Syst. Appl. 13(4), 18\u201328 (1998)","journal-title":"IEEE Intell. Syst. Appl."}],"container-title":["Lecture Notes in Computer Science","Multimodal Pattern Recognition of Social Signals in Human-Computer-Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20984-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,28]],"date-time":"2023-05-28T00:02:39Z","timestamp":1685232159000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-20984-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030209834","9783030209841"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20984-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"15 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MPRSS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IAPR Workshop on Multimodal Pattern Recognition of Social Signals in Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mprss2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/neuro.informatik.uni-ulm.de\/MPRSS2018\/","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":"12","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":"9","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":"75% - 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","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":"This content has been made available to all.","name":"free","label":"Free to read"}]}}