{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T21:06:50Z","timestamp":1743023210300,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031138317"},{"type":"electronic","value":"9783031138324"}],"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\/978-3-031-13832-4_31","type":"book-chapter","created":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T11:32:22Z","timestamp":1660563142000},"page":"367-379","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Sub-captions Semantic-Guided Network for Image Captioning"],"prefix":"10.1007","author":[{"given":"Wei-Dong","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun-jun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong-Qiu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Zheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian-yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,16]]},"reference":[{"key":"31_CR1","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":"31_CR2","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"31_CR3","unstructured":"Liu, F., Liu, Y., Ren, X., He, X., Sun, X.: Aligning visual regions and textual concepts for semantic-grounded image representations. In: NIPS (2019)"},{"key":"31_CR4","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"key":"31_CR5","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"31_CR7","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"31_CR9","unstructured":"Mahajan, S., Roth, S.: Diverse image captioning with context-object split latent spaces. In: NIPS (2020)"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: RSTNET: captioning with adaptive attention on visual and non-visual words. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"31_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"31_CR12","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2text: describing images using 1 million captioned photographs. In: NIPS (2011)"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Neural baby talk. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00754"},{"key":"31_CR14","unstructured":"Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. arXiv preprint arXiv:1409.2329 (2014)"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"31_CR16","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: Scene graph parsing with global context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"31_CR18","unstructured":"Klusowski, J.M., Wu, Y.: Counting motifs with graph sampling. In: COLT (2018)"},{"key":"31_CR19","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"issue":"8","key":"31_CR20","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":"31_CR21","unstructured":"Chen, X., Fang, H., Lin, T.Y., Vedantam, R., Gupta, S., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"31_CR23","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":"31_CR24","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. In: IJCV (2016)"},{"key":"31_CR25","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Gu, J., Cai, J., Wang, G., Chen, T.: Stack-captioning: coarse-to-fine learning for image captioning. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"31_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/978-3-030-58568-6_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zhong","year":"2020","unstructured":"Zhong, Y., Wang, L., Chen, J., Yu, D., Li, Y.: Comprehensive image captioning via scene graph decomposition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 211\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_13"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"31_CR29","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"31_CR30","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1007\/978-3-030-88480-2_63","volume-title":"Natural Language Processing and Chinese Computing","author":"Q Xia","year":"2021","unstructured":"Xia, Q., et al.: XGPT: cross-modal Generative Pre-Training for Image Captioning. In: Wang, L., Feng, Y., Hong, Y., He, R. (eds.) NLPCC 2021. LNCS (LNAI), vol. 13028, pp. 786\u2013797. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-88480-2_63"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Cucchiara, R.: Show, control and tell: A framework for generating controllable and grounded captions. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00850"},{"key":"31_CR32","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":"31_CR33","doi-asserted-by":"crossref","unstructured":"Deshpande, A., Aneja, J., Wang, L., Schwing, A.G., Forsyth, D.: Fast, diverse and accurate image captioning guided by part-of-speech. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01095"},{"key":"31_CR34","doi-asserted-by":"publisher","first-page":"3884","DOI":"10.1016\/j.apm.2010.03.027","volume":"34","author":"ZQ Zhao","year":"2010","unstructured":"Zhao, Z.Q., Gao, J., Glotin, H., Wu, X.: A matrix modular neural network based on task decomposition with subspace division by adaptive affinity propagation clustering. Appl. Math. Modell. 34, 3884\u20133895 (2010). https:\/\/doi.org\/10.1016\/j.apm.2010.03.027","journal-title":"Appl. Math. Modell."},{"issue":"5","key":"31_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-013-4850-5","volume":"57","author":"Z Zhao","year":"2014","unstructured":"Zhao, Z., Wu, X., Lu, C., Glotin, H., Gao, J.: Optimizing widths with PSO for center selection of gaussian radial basis function networks. Sci. China Inf. Sci. 57(5), 1\u201317 (2014). https:\/\/doi.org\/10.1007\/s11432-013-4850-5","journal-title":"Sci. China Inf. Sci."}],"container-title":["Lecture Notes in Computer Science","Intelligent Computing Methodologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-13832-4_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T14:08:02Z","timestamp":1710338882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-13832-4_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031138317","9783031138324"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-13832-4_31","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":"16 August 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xi'an","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":"7 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2022\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Open","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"IC-ICC-CN","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"449","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":"209","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":"47% - 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":"2.5","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}