{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:59:48Z","timestamp":1771919988899,"version":"3.50.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030884796","type":"print"},{"value":"9783030884802","type":"electronic"}],"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\/978-3-030-88480-2_63","type":"book-chapter","created":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T11:04:52Z","timestamp":1633950292000},"page":"786-797","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["XGPT: Cross-modal Generative Pre-Training for Image Captioning"],"prefix":"10.1007","author":[{"given":"Qiaolin","family":"Xia","sequence":"first","affiliation":[]},{"given":"Haoyang","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Nan","family":"Duan","sequence":"additional","affiliation":[]},{"given":"Dongdong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Ji","sequence":"additional","affiliation":[]},{"given":"Zhifang","family":"Sui","sequence":"additional","affiliation":[]},{"given":"Edward","family":"Cui","sequence":"additional","affiliation":[]},{"given":"Taroon","family":"Bharti","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,6]]},"reference":[{"key":"63_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"63_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: Vqa: Visual question answering. In: ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"63_CR3","doi-asserted-by":"crossref","unstructured":"Chen, T., Liu, S., Chang, S., Cheng, Y., Amini, L., Wang, Z.: Adversarial robustness: From self-supervised pre-training to fine-tuning. In: CVPR, pp. 699\u2013708 (2020)","DOI":"10.1109\/CVPR42600.2020.00078"},{"key":"63_CR4","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"63_CR5","unstructured":"Chen, Y.C., et al.: Uniter: learning universal image-text representations. arXiv preprint arXiv:1909.11740 (2019)"},{"key":"63_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Jiang, L., Macherey, W.: Robust neural machine translation with doubly adversarial inputs. In: ACL, pp. 4324\u20134333 (2019)","DOI":"10.18653\/v1\/P19-1425"},{"key":"63_CR7","unstructured":"Dong, L., et al.: Unified language model pre-training for natural language understanding and generation. arXiv preprint arXiv:1905.03197 (2019)"},{"key":"63_CR8","doi-asserted-by":"crossref","unstructured":"Ebrahimi, J., Rao, A., Lowd, D., Dou, D.: Hotflip: white-box adversarial examples for text classification. In: ACL, pp. 31\u201336 (2018)","DOI":"10.18653\/v1\/P18-2006"},{"key":"63_CR9","unstructured":"Gan, Z., Chen, Y.C., Li, L., Zhu, C., Cheng, Y., Liu, J.: Large-scale adversarial training for vision-and-language representation learning. arXiv:2006.06195 (2020)"},{"key":"63_CR10","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"63_CR11","unstructured":"Hendrycks, D., Gimpel, K.: Bridging nonlinearities and stochastic regularizers with gaussian error linear units (2016)"},{"key":"63_CR12","unstructured":"Hendrycks, D., Lee, K., Mazeika, M.: Using pre-training can improve model robustness and uncertainty. In: ICML (2019)"},{"key":"63_CR13","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: Unicoder: a universal language encoder by pre-training with multiple cross-lingual tasks. arXiv preprint arXiv:1909.00964 (2019)","DOI":"10.18653\/v1\/D19-1252"},{"key":"63_CR14","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: ICCV, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"63_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, H., He, P., Chen, W., Liu, X., Gao, J., Zhao, T.: Smart: robust and efficient fine-tuning for pre-trained natural language models through principled regularized optimization. arXiv preprint arXiv:1911.03437 (2019)","DOI":"10.18653\/v1\/2020.acl-main.197"},{"key":"63_CR16","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"63_CR17","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: Referitgame: referring to objects in photographs of natural scenes. In: EMNLP, pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"63_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. international conference on learning representations (2015)"},{"key":"63_CR19","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"63_CR20","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. arXiv preprint arXiv:2004.06165 (2020)","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"63_CR21","unstructured":"Liu, X., et al.: Adversarial training for large neural language models. arXiv preprint arXiv:2004.08994 (2020)"},{"key":"63_CR22","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, pp. 13\u201323 (2019)"},{"key":"63_CR23","doi-asserted-by":"crossref","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Neural baby talk. In: CVPR, pp. 7219\u20137228 (2018)","DOI":"10.1109\/CVPR.2018.00754"},{"key":"63_CR24","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: ICLR (2018)"},{"key":"63_CR25","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: ICCV, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"63_CR26","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL, pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"63_CR27","unstructured":"Song, K., Tan, X., Qin, T., Lu, J., Liu, T.Y.: Mass: masked sequence to sequence pre-training for language generation. arXiv preprint arXiv:1905.02450 (2019)"},{"key":"63_CR28","unstructured":"Sun, C., Baradel, F., Murphy, K., Schmid, C.: Contrastive bidirectional transformer for temporal representation learning. ArXiv abs\/1906.05743 (2019)"},{"key":"63_CR29","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: Videobert: a joint model for video and language representation learning. ICCV (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"63_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"63_CR31","unstructured":"Wang, D., Gong, C., Liu, Q.: Improving neural language modeling via adversarial training. arXiv preprint arXiv:1906.03805 (2019)"},{"key":"63_CR32","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: ECCV, pp. 684\u2013699 (2018)","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"63_CR33","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. TACL 2, 67\u201378 (2014)","journal-title":"TACL"},{"key":"63_CR34","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: CVPR, pp. 6720\u20136731 (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"63_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, L., Kalantidis, Y., Chen, X., Corso, J.J., Rohrbach, M.: Grounded video description. In: CVPR, pp. 6578\u20136587 (2019)","DOI":"10.1109\/CVPR.2019.00674"},{"key":"63_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J.J., Gao, J.: Unified vision-language pre-training for image captioning and vqa. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"63_CR37","unstructured":"Zhu, C., Cheng, Y., Gan, Z., Sun, S., Goldstein, T., Liu, J.: Freelb: enhanced adversarial training for language understanding. arXiv:1909.11764 (2019)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-88480-2_63","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T15:51:16Z","timestamp":1709826676000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-88480-2_63"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030884796","9783030884802"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-88480-2_63","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"6 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Qingdao","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 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2021\/","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":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"446","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":"66","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":"15% - 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":"1.5","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)"}},{"value":"23 poster papers and 27 workshop papers are also included.","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)"}}]}}