{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:50:33Z","timestamp":1742914233103,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030841850"},{"type":"electronic","value":"9783030841867"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-84186-7_27","type":"book-chapter","created":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T10:03:42Z","timestamp":1628330622000},"page":"404-418","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sketchy Scene Captioning: Learning Multi-level Semantic Information from Sparse Visual Scene Cues"],"prefix":"10.1007","author":[{"given":"Lian","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangdong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuejie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,8]]},"reference":[{"key":"27_CR1","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 Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"27_CR2","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. CoRR abs\/1504.00325 (2015). http:\/\/arxiv.org\/abs\/1504.00325"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Denkowski, M.J., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Workshop on Statistical Machine Translation (WMT@ACL 2014), pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Eitz, M., Hays, J., Alexa, M.: How do humans sketch objects? ACM Trans. Graph. 31(4), 44:1\u201344:10 (2012)","DOI":"10.1145\/2185520.2185540"},{"key":"27_CR6","unstructured":"Elliott, D., Keller, F.: Image description using visual dependency representations. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 1292\u20131302 (2013)"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"He, J., Wu, X., Jiang, Y., Zhao, B., Peng, Q.: Sketch recognition with deep visual-sequential fusion model. In: Proceedings of the ACM on Multimedia Conference, pp. 448\u2013456 (2017)","DOI":"10.1145\/3123266.3123321"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"27_CR9","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":"27_CR10","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"27_CR11","unstructured":"Karpathy, A., Joulin, A., Li, F.: Deep fragment embeddings for bidirectional image sentence mapping. In: Proceedings of the Annual Conference on Neural Information Processing Systems, pp. 1889\u20131897 (2014)"},{"key":"27_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (2015). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Krause, J., Johnson, J., Krishna, R., Fei-Fei, L.: A hierarchical approach for generating descriptive image paragraphs. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 3337\u20133345 (2017)","DOI":"10.1109\/CVPR.2017.356"},{"key":"27_CR14","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Proceedings of the Workshop on Text Summarization Branches Out (Post-Conference Workshop of ACL 2004), pp. 74\u201381 (2004)"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Q., Xie, L., Wang, H., Yuille, A.L.: Semantic-aware knowledge preservation for zero-shot sketch-based image retrieval. In: Proceedings of the International Conference on Computer Vision, pp. 3661\u20133670 (2019)","DOI":"10.1109\/ICCV.2019.00376"},{"issue":"5","key":"27_CR16","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1016\/j.ipm.2017.04.002","volume":"53","author":"M Neshati","year":"2017","unstructured":"Neshati, M., Fallahnejad, Z., Beigy, H.: On dynamicity of expert finding in community question answering. Inf. Process. Manage. 53(5), 1026\u20131042 (2017)","journal-title":"Inf. Process. Manage."},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Sangkloy, P., Burnell, N., Ham, C., Hays, J.: The sketchy database: learning to retrieve badly drawn bunnies. ACM Trans. Graph. 35(4), 119:1\u2013119:12 (2016)","DOI":"10.1145\/2897824.2925954"},{"issue":"1","key":"27_CR19","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"27_CR20","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the Annual Conference on Neural Information Processing Systems, pp. 3104\u20133112 (2014)"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"27_CR22","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 Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"27_CR23","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of the International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Yu, Q., Yang, Y., Song, Y., Xiang, T., Hospedales, T.M.: Sketch-a-Net that beats humans. In: Proceedings of the British Machine Vision Conference, pp. 7.1\u20137.12 (2015)","DOI":"10.5244\/C.29.7"},{"key":"27_CR25","unstructured":"Zou, C., Mo, H., Du, R., Wu, X., Gao, C., Fu, H.: LUCSS: language-based user-customized colourization of scene sketches. CoRR abs\/1808.10544 (2018). http:\/\/arxiv.org\/abs\/1808.10544"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Zou, C., et al.: SketchyScene: richly-annotated scene sketches. In: Proceedings of the European Conference on Computer Vision, pp. 438\u2013454 (2018)","DOI":"10.1007\/978-3-030-01267-0_26"}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-84186-7_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T10:10:16Z","timestamp":1628331016000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-84186-7_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030841850","9783030841867"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-84186-7_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"8 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China National Conference on Chinese Computational Linguistics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hohhot","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cncl2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cips-cl.org\/static\/CCL2021\/en\/index.html","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":"www.softconf.com","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"90","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":"31","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":"34% - 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":"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)"}}]}}