{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:38:08Z","timestamp":1743151088622,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819970216"},{"type":"electronic","value":"9789819970223"}],"license":[{"start":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T00:00:00Z","timestamp":1699574400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T00:00:00Z","timestamp":1699574400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-7022-3_19","type":"book-chapter","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T00:02:57Z","timestamp":1699574577000},"page":"210-222","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multilayer Vision and\u00a0Language Augmented Transformer for\u00a0Image Captioning"],"prefix":"10.1007","author":[{"given":"Qiang","family":"Su","sequence":"first","affiliation":[]},{"given":"Zhixin","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,10]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., 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":"19_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104340","volume":"117","author":"T Chen","year":"2022","unstructured":"Chen, T., Li, Z., Wu, J., et al.: Improving image captioning with pyramid attention and SC-GAN. Image Vis. Comput. 117, 104340 (2022)","journal-title":"Image Vis. Comput."},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., et al.: Meshed-memory transformer for image captioning. In: CVPR, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Zhu, X., et al.: Normalized and geometry-aware self-attention network for image captioning. In: CVPR, pp. 10327\u201310336 (2020)","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"19_CR5","unstructured":"Herdade, S., Kappeler, A., Boakye, K., et al.: Image captioning: transforming objects into words. In: NeurIPS (2019)"},{"issue":"12","key":"19_CR6","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). https:\/\/doi.org\/10.1007\/s10994-020-05919-y","journal-title":"Mach. Learn."},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., et al.: Attention on attention for image captioning. In: ICCV, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Ji, J., Luo, Y., Sun, X., et al.: Improving image captioning by leveraging intra- and inter-layer global representation in transformer network. In: AAAI, pp. 1655\u20131663 (2021)","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"19_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Kuo, C.W., Kira, Z.: Beyond a pre-trained object detector: cross-modal textual and visual context for image captioning. In: CVPR, pp. 17969\u201317979 (2022)","DOI":"10.1109\/CVPR52688.2022.01744"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Li, B., Yao, Y., Tan, J., et al.: Equalized focal loss for dense long-tailed object detection. In: CVPR, pp. 6990\u20136999 (2022)","DOI":"10.1109\/CVPR52688.2022.00686"},{"key":"19_CR12","unstructured":"Li, J., Li, D., Xiong, C., et al.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, pp. 12888\u201312900 (2022)"},{"key":"19_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Luo, J., et al.: Semantic-conditional diffusion networks for image captioning. arXiv preprint arXiv:2212.03099 (2022)","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Luo, Y., Ji, J., Sun, X., et al.: Dual-level collaborative transformer for image captioning. In: AAAI, pp. 2286\u20132293 (2021)","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Mao, Y., Chen, L., Jiang, Z., et al.: Rethinking the reference-based distinctive image captioning. In: ACM MM, pp. 4374\u20134384 (2022)","DOI":"10.1145\/3503161.3548358"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., et al.: X-linear attention networks for image captioning. In: CVPR, pp. 10971\u201310980 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., et al.: BLEU: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"19_CR19","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"19_CR20","unstructured":"Ren, S., He, K., Girshick, R.B., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: CVPR, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"issue":"3","key":"19_CR22","doi-asserted-by":"publisher","first-page":"2706","DOI":"10.1007\/s10489-022-03624-y","volume":"53","author":"J Wei","year":"2023","unstructured":"Wei, J., Li, Z., Zhu, J., et al.: Enhance understanding and reasoning ability for image captioning. Appl. Intell. 53(3), 2706\u20132722 (2023)","journal-title":"Appl. Intell."},{"issue":"9","key":"19_CR23","doi-asserted-by":"publisher","first-page":"5762","DOI":"10.1109\/TCSVT.2022.3155795","volume":"32","author":"T Xian","year":"2022","unstructured":"Xian, T., Li, Z., Tang, Z., et al.: Adaptive path selection for dynamic image captioning. IEEE Trans. Circuits Syst. Video Technol. 32(9), 5762\u20135775 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"19_CR24","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.neunet.2022.01.011","volume":"148","author":"T Xian","year":"2022","unstructured":"Xian, T., Li, Z., Zhang, C., et al.: Dual global enhanced transformer for image captioning. Neural Netw. 148, 129\u2013141 (2022)","journal-title":"Neural Netw."},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., et al.: Auto-encoding scene graphs for image captioning. In: CVPR, pp. 10685\u201310694 (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"19_CR26","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":"19_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, P., Li, X., Hu, X., et al.: VinVL: revisiting visual representations in vision-language models. In: CVPR, pp. 5579\u20135588 (2021)","DOI":"10.1109\/CVPR46437.2021.00553"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2023: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-7022-3_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T00:10:39Z","timestamp":1699575039000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-7022-3_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,10]]},"ISBN":["9789819970216","9789819970223"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-7022-3_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,11,10]]},"assertion":[{"value":"10 November 2023","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":"Jakarta","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2023","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":"pricai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2023\/","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":"422","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":"95","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":"36","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":"23% - 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":"3.4","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":"3.1","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)"}}]}}