{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T11:11:21Z","timestamp":1726053081922},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030313715"},{"type":"electronic","value":"9783030313722"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-31372-2_22","type":"book-chapter","created":{"date-parts":[[2019,9,26]],"date-time":"2019-09-26T20:02:49Z","timestamp":1569528169000},"page":"261-272","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Automatic Judgement of Neural Network-Generated Image Captions"],"prefix":"10.1007","author":[{"given":"Rajarshi","family":"Biswas","sequence":"first","affiliation":[]},{"given":"Aditya","family":"Mogadala","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Barz","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Sonntag","sequence":"additional","affiliation":[]},{"given":"Dietrich","family":"Klakow","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,9,27]]},"reference":[{"key":"22_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":"22_CR2","doi-asserted-by":"crossref","unstructured":"Barz, M., Polzehl, T., Sonntag, D.: Towards hybrid human-machine translation services. EasyChair Preprint (2018)","DOI":"10.29007\/kw5h"},{"key":"22_CR3","unstructured":"Biswas, R.: Diverse Image Caption Generation And Automated Human Judgement through Active Learning. Master\u2019s thesis, Saarland University (2019)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Cer, D., et al.: Universal sentence encoder. \n                      arXiv:1803.11175\n                      \n                     (2018)","DOI":"10.18653\/v1\/D18-2029"},{"key":"22_CR5","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"N Chawla","year":"2002","unstructured":"Chawla, N., Bowyer, K., Hall, L., Kegelmeyer, W.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002)","journal-title":"J. Artif. Intell. Res."},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Cho, K., Merrienboer, B., Gulcehre, C., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Haibo, H., Bai, Y., Garcia, E., Li, S.: ADASYN: adaptive synthetic sampling approach for imbalanced learning. In: IEEE International Joint Conference on Neural Networks, pp. 1322\u20131328 (2008)","DOI":"10.1109\/IJCNN.2008.4633969"},{"key":"22_CR9","first-page":"335","volume":"42","author":"S Harnad","year":"1990","unstructured":"Harnad, S.: The symbol grounding problem. Physica 42, 335\u2013346 (1990)","journal-title":"Physica"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Harzig, P., Brehm, S., Lienhart, R., Kaiser, C., Schallner, R.: Multimodal image captioning for marketing analysis, February 2018","DOI":"10.1109\/MIPR.2018.00035"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"22_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\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"22_CR13","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. \n                      arXiv:1502.03167\n                      \n                     (2015)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"22_CR15","unstructured":"Karpathy, A., Joulin, A., Fei-Fei, L.: Deep fragment embeddings for bidirectional image sentence mapping. In: NIPS (2014)"},{"key":"22_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/978-3-030-01216-8_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Kim","year":"2018","unstructured":"Kim, J., Rohrbach, A., Darrell, T., Canny, J., Akata, Z.: Textual explanations for self-driving vehicles. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 577\u2013593. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-030-01216-8_35"},{"key":"22_CR17","unstructured":"Kingma, D., Ba, J.: Adam: A method for stochastic optimization. In: ICLR (2015)"},{"key":"22_CR18","unstructured":"Kiros, R., Salahutdinov, R., Zemel, R.: Multimodal neural language models. In: ICLR, pp. 595\u2013603 (2014)"},{"key":"22_CR19","unstructured":"Kiros, R., Salahutdinov, R., Zemel, R.: Unifying visual-semantic embeddings with multimodal neural language models. \n                      arXiv:1411.2539\n                      \n                     (2014)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Kisilev, P., Sason, E., Barkan, E., Hashoul, S.Y.: Medical image captioning : learning to describe medical image findings using multitask-loss CNN (2016)","DOI":"10.1007\/978-3-319-46976-8_13"},{"key":"22_CR21","unstructured":"Lin, C.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out (2004)"},{"key":"22_CR22","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":"22_CR23","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1016\/B978-0-08-051584-7.50053-X","volume-title":"Readings in Speech Recognition","author":"Bruce Lowerre","year":"1990","unstructured":"Lowerre, B., Reddy, R.: The harpy speech understanding system. In: Readings in Speech Recognition, pp. 576\u2013586 (1990)"},{"key":"22_CR24","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Yuille, A.: Deep captioning with multimodal recurrent neural networks (m-RNN). \n                      arXiv:1412.6632\n                      \n                     (2014)"},{"key":"22_CR25","doi-asserted-by":"publisher","DOI":"10.1145\/3015783","volume-title":"The Handbook Of Multimodal-Multisensor Interfaces, Volume 1: Foundations, User Modeling, and Common Modality Combinations","author":"S Oviatt","year":"2017","unstructured":"Oviatt, S., Schuller, B., Cohen, P., Sonntag, D., Potamianos, G.: The Handbook Of Multimodal-Multisensor Interfaces, Volume 1: Foundations, User Modeling, and Common Modality Combinations. ACM, New York (2017)"},{"key":"22_CR26","first-page":"1","volume-title":"Introduction: scope, trends, and paradigm shift in the field of computer interfaces","author":"S Oviatt","year":"2017","unstructured":"Oviatt, S., Schuller, B., Cohen, P., Sonntag, D., Potamianos, G., Kruger, A.: Introduction: scope, trends, and paradigm shift in the field of computer interfaces, pp. 1\u201315. ACM, New York (2017)"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: Bleu: a method for automatic evaluation of machine translation. In: Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"22_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2005.06.002","volume":"167","author":"D Roy","year":"2005","unstructured":"Roy, D., Reiter, E.: Connecting language to the world. Artif. Intell. 167, 1\u201312 (2005)","journal-title":"Artif. Intell."},{"key":"22_CR29","unstructured":"Settles, B.: Active Learning Literature Survey, vol. 52, no. 55-66, p. 11. University of Wisconsin, Madison (2010)"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Xu, A., Liu, Z., Guo, Y., Sinha, V., Akkiraju, R.: A new chatbot for customer service on social media. In: Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, pp. 3506\u20133510 (2017)","DOI":"10.1145\/3025453.3025496"},{"key":"22_CR32","unstructured":"Xu, K., er al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-31372-2_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,26]],"date-time":"2019-09-26T20:05:31Z","timestamp":1569528331000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-31372-2_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030313715","9783030313722"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-31372-2_22","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":"27 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SLSP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Statistical Language and Speech Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"slsp2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/slsp2019.irdta.eu\/","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":"48","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":"25","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":"1","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":"52% - 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":"4","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)"}}]}}