{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:12:05Z","timestamp":1742911925454,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030880095"},{"type":"electronic","value":"9783030880101"}],"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\/978-3-030-88010-1_13","type":"book-chapter","created":{"date-parts":[[2021,10,21]],"date-time":"2021-10-21T23:06:25Z","timestamp":1634857585000},"page":"151-163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Relational Attention with Textual Enhanced Transformer for Image Captioning"],"prefix":"10.1007","author":[{"given":"Lifei","family":"Song","sequence":"first","affiliation":[]},{"given":"Yiwen","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Xinyu","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Chunxia","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,22]]},"reference":[{"key":"13_CR1","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Yuille, A.L.: Deep captioning with multimodal recurrent neural networks (m-rnn). In: ICLR (2015)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Jia, X., Gavves, E., Fernando, B., Tuytelaars, T.: Guiding the long-short term memory model for image caption generation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.277"},{"key":"13_CR3","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":"13_CR4","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. NIPS (2014)"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.J.: Stacked attention networks for image question answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.10"},{"key":"13_CR6","volume-title":"and Richard Socher","author":"L Jiasen","year":"2017","unstructured":"Jiasen, L., Xiong, C., Parikh, D.: and Richard Socher. Adaptive attention via a visual sentinel for image captioning. CVPR, Knowing when to look (2017)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Kim, D.-J., Choi, J., Tae-Hyun, O., Kweon, I.S.: Dense relational captioning: Triple-stream networks for relationship-based captioning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00643"},{"key":"13_CR9","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":"13_CR10","unstructured":"Hong, D., Gao, L., Yao, J., Zhang, B., Plaza, A., Chanussot, J.: Graph convolutional networks for hyperspectral image classification. CoRR, vol. abs\/2008.02457 (2020)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"13_CR12","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. NIPS (2017)"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Li, G., Zhu, L., Liu, P., Yang, Y.: Entangled transformer for image captioning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00902"},{"key":"13_CR14","unstructured":"Herdade, S., Kappeler, A., Boakye, K., Soares, J.: Image captioning, Transforming objects into words. NIPS (2019)"},{"key":"13_CR15","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. NIPS (2015)"},{"key":"13_CR16","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":"13_CR17","doi-asserted-by":"crossref","unstructured":"Fang, H., et al.: From captions to visual concepts and back. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Steven, J.: Rennie, E.M., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Cider, D.P.: Consensus-based image description evaluation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"13_CR20","unstructured":"Chen, X., et al.: Microsoft COCO captions: Data collection and evaluation server. vol. abs\/1504.00325 (2015)"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Li, F.-F.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. ACL (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"13_CR23","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. ACL (2005)"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE:semantic propositional image caption evaluation. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"13_CR25","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":"13_CR26","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.: Attention on attention for image captioning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Yang, X., Zhang, H., Cai, J.: Learning to Collocate Neural Modules for Image Captioning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00435"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Wang, W., Chen, Z., Hu, H.: Hierarchical Attention Network for Image Captioning, AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018957"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-88010-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T08:05:06Z","timestamp":1654502706000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-88010-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030880095","9783030880101"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-88010-1_13","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":"22 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv.cn\/2021\/index_en.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"513","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":"201","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":"39% - 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":"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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"There were 30 oral and 171 poster presentations at the conference.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}