{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:19:14Z","timestamp":1743124754508,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030891879"},{"type":"electronic","value":"9783030891886"}],"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\/978-3-030-89188-6_15","type":"book-chapter","created":{"date-parts":[[2021,10,24]],"date-time":"2021-10-24T22:02:23Z","timestamp":1635112943000},"page":"197-211","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adversarial Training for Image Captioning Incorporating Relation Attention"],"prefix":"10.1007","author":[{"given":"Tianyu","family":"Chen","sequence":"first","affiliation":[]},{"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Canlong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Huifang","family":"Ma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,25]]},"reference":[{"key":"15_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 IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"15_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Jin, Q.: Better captioning with sequence-level exploration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10890\u201310899 (2020)","DOI":"10.1109\/CVPR42600.2020.01090"},{"issue":"1","key":"15_CR4","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","volume":"35","author":"A Creswell","year":"2018","unstructured":"Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., Bharath, A.A.: Generative adversarial networks: an overview. IEEE Signal Process. Mag. 35(1), 53\u201365 (2018)","journal-title":"IEEE Signal Process. Mag."},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Dai, B., Fidler, S., Urtasun, R., Lin, D.: Towards diverse and natural image descriptions via a conditional GAN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2970\u20132979 (2017)","DOI":"10.1109\/ICCV.2017.323"},{"issue":"8","key":"15_CR6","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."},{"issue":"12","key":"15_CR7","doi-asserted-by":"publisher","first-page":"2313","DOI":"10.1007\/s10994-020-05919-y","volume":"109","author":"F Huang","year":"2020","unstructured":"Huang, F., Li, Z., Wei, H., Zhang, C., Ma, H.: Boost image captioning with knowledge reasoning. Mach. Learn. 109(12), 2313\u20132332 (2020)","journal-title":"Mach. Learn."},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"15_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-030-01216-8_31","volume-title":"Computer Vision \u2013 ECCV 2018","author":"W Jiang","year":"2018","unstructured":"Jiang, W., Ma, L., Jiang, Y.-G., Liu, W., Zhang, T.: Recurrent fusion network for image captioning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 510\u2013526. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_31"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Interactive dual generative adversarial networks for image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11588\u201311595 (2020)","DOI":"10.1609\/aaai.v34i07.6826"},{"key":"15_CR11","unstructured":"Ranzato, M., Chopra, S., Auli, M., Zaremba, W.: Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 (2015)"},{"key":"15_CR12","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"15_CR14","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"15_CR15","unstructured":"Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y., et al.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1057\u20131063 (1999)"},{"key":"15_CR16","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"15_CR17","doi-asserted-by":"publisher","first-page":"107075","DOI":"10.1016\/j.patcog.2019.107075","volume":"98","author":"J Wang","year":"2020","unstructured":"Wang, J., Wang, W., Wang, L., Wang, Z., Feng, D.D., Tan, T.: Learning visual relationship and context-aware attention for image captioning. Pattern Recogn. 98, 107075 (2020)","journal-title":"Pattern Recogn."},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Wang, L., Bai, Z., Zhang, Y., Lu, H.: Show, recall, and tell: image captioning with recall mechanism. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12176\u201312183 (2020)","DOI":"10.1609\/aaai.v34i07.6898"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Wang, W., Chen, Z., Hu, H.: Hierarchical attention network for image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8957\u20138964 (2019)","DOI":"10.1609\/aaai.v33i01.33018957"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Z., Huang, Z., Luo, Y.: Human consensus-oriented image captioning. In: IJCAI, pp. 659\u2013665 (2020)","DOI":"10.24963\/ijcai.2020\/92"},{"key":"15_CR21","doi-asserted-by":"publisher","first-page":"103068","DOI":"10.1016\/j.cviu.2020.103068","volume":"201","author":"H Wei","year":"2020","unstructured":"Wei, H., Li, Z., Zhang, C., Ma, H.: The synergy of double attention: combine sentence-level and word-level attention for image captioning. Comput. Vis. Image Underst. 201, 103068 (2020)","journal-title":"Comput. Vis. Image Underst."},{"key":"15_CR22","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"15_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1007\/978-3-030-01264-9_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Yao","year":"2018","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 711\u2013727. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_42"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Yu, L., Zhang, W., Wang, J., Yu, Y.: SeqGAN: sequence generative adversarial nets with policy gradient. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31, pp. 2852\u20132858 (2017)","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wang, M., Liu, D., Hu, Z., Zhang, H.: More grounded image captioning by distilling image-text matching model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4777\u20134786 (2020)","DOI":"10.1109\/CVPR42600.2020.00483"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2021: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89188-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T15:52:50Z","timestamp":1673625170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89188-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030891879","9783030891886"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89188-6_15","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":"25 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","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":"pricai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"382","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":"93","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":"28","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":"24% - 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)"}}]}}