{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:45:35Z","timestamp":1742913935166,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030038007"},{"type":"electronic","value":"9783030038014"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-03801-4_37","type":"book-chapter","created":{"date-parts":[[2018,11,9]],"date-time":"2018-11-09T07:40:49Z","timestamp":1541749249000},"page":"423-432","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Detailed Sentence Generation Architecture for Image Semantics Description"],"prefix":"10.1007","author":[{"given":"Imran","family":"Khurram","sequence":"first","affiliation":[]},{"given":"Muhammad Moazam","family":"Fraz","sequence":"additional","affiliation":[]},{"given":"Muhammad","family":"Shahzad","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,11,10]]},"reference":[{"key":"37_CR1","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"37_CR2","unstructured":"Grubinger, M., Clough, P., M\u00fcller, H., Deselaers, T.: The IAPR TC-12 benchmark: A new evaluation resource for visual information systems. In: International workshop ontoImage. vol. 5, p. 10 (2006)"},{"issue":"8","key":"37_CR3","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(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"37_CR4","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017\u20132025 (2015)"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: Densecap: fully convolutional localization networks for dense captioning. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4565\u20134574 (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"37_CR7","unstructured":"Kelvin, X., et al.: Show, attend and tell: neural image caption generation with visual attention, 1 June 2015"},{"key":"37_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint \n                      arXiv:1412.6980\n                      \n                     (2014)"},{"key":"37_CR9","unstructured":"Kolb, P.: DISCO: A multilingual database of distributionally similar words. In: In Proceedings of KONVENS (2008)"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 554\u2013561. IEEE (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"issue":"1","key":"37_CR11","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Kulkarni, G., et al.: Baby talk: understanding and generating image descriptions. In: Proceedings of the 24th CVPR. Citeseer (2011)","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"37_CR13","unstructured":"Lin, C.Y.: ROUGE: A package for automatic evaluation of summaries. Text Summarization Branches Out (2004)"},{"key":"37_CR14","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). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 6 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"37_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/978-3-642-19400-9_14","volume-title":"Computational Linguistics and Intelligent Text Processing","author":"CD Manning","year":"2011","unstructured":"Manning, C.D.: Part-of-speech tagging from 97% to 100%: is it time for some linguistics? In: Gelbukh, A.F. (ed.) CICLing 2011. LNCS, vol. 6608, pp. 171\u2013189. Springer, Heidelberg (2011). \n                      https:\/\/doi.org\/10.1007\/978-3-642-19400-9_14"},{"key":"37_CR17","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/978-3-642-31603-6_3","volume-title":"Advances in Intelligent Systems and Computing","author":"Julius T. Nganji","year":"2012","unstructured":"Nganji, J.T., Brayshaw, M., Tompsett, B.: Describing and assessing image descriptions for visually impaired web users with IDAT. In: Proceedings of the Third International Conference on Intelligent Human Computer Interaction (IHCI 2011), Prague, Czech Republic, August 2011, pp. 27\u201337. Springer, Heidelberg (2013). \n                      https:\/\/doi.org\/10.1007\/978-3-642-31603-6_3"},{"key":"37_CR18","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 on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"37_CR19","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks, pp. 91\u201399 (2015)"},{"issue":"11","key":"37_CR20","doi-asserted-by":"publisher","first-page":"4786","DOI":"10.1109\/TIP.2014.2358082","volume":"23","author":"J Shen","year":"2014","unstructured":"Shen, J., et al.: Unified structured learning for simultaneous human pose estimation and garment attribute classification. IEEE Trans. Image Process. 23(11), 4786\u20134798 (2014)","journal-title":"IEEE Trans. Image Process."},{"key":"37_CR21","unstructured":"Trundle, S.S., McCarthy, R.J., Martin, J.P., Slavin, A.J., Hutz, D.J.: Image surveillance and reporting technology (2015)"},{"key":"37_CR22","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. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Ye, C., Yang, Y., Mao, R., Ferm\u00fcller, C., Aloimonos, Y.: What can i do around here? Deep functional scene understanding for cognitive robots. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 4604\u20134611. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989535"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-03801-4_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T05:12:38Z","timestamp":1558329158000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-03801-4_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030038007","9783030038014"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-03801-4_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"10 November 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Las Vegas, NV","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"19 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isvc2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isvc.net\/","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"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"113","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"66","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"58% - 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"}},{"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"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"54 papers were accepted for the main symposium out of 91 submissions; and 12 papers were accepted for the special tracks out of 22 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}