{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:30:28Z","timestamp":1742913028172,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819916443"},{"type":"electronic","value":"9789819916450"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/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":[[2023]]},"DOI":"10.1007\/978-981-99-1645-0_38","type":"book-chapter","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T17:03:13Z","timestamp":1681405393000},"page":"458-469","update-policy":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Image Captioning with\u00a0Local-Global Visual Interaction Network"],"prefix":"10.1007","author":[{"given":"Changzhi","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xiaodong","family":"Gu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"38_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"38_CR2","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 IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"38_CR3","unstructured":"Banerjee, S., Lavie, A.: Meteor: An automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of Meeting of the Association for Computational Linguistics, pp. 65\u201372 (2005)"},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"issue":"10","key":"38_CR6","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1007\/s10489-020-01665-9","volume":"50","author":"X Ding","year":"2020","unstructured":"Ding, X., Li, Q., Cheng, Y., Wang, J., Bian, W., Jie, B.: Local keypoint-based faster R-CNN. Appl. Intell. 50(10), 3007\u20133022 (2020)","journal-title":"Appl. Intell."},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Gao, J., Wang, S., Wang, S., Ma, S., Gao, W.: Self-critical n-step training for image captioning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 6300\u20136308 (2019)","DOI":"10.1109\/CVPR.2019.00646"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Li, G., Zhu, L., Liu, P., Yang, Y.: Entangled transformer for image captioning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8928\u20138937 (2019)","DOI":"10.1109\/ICCV.2019.00902"},{"issue":"3","key":"38_CR9","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1109\/TMM.2017.2751140","volume":"20","author":"L Li","year":"2018","unstructured":"Li, L., Tang, S., Zhang, Y., Deng, L., Tian, Q.: GLA: global-local attention for image description. IEEE Trans. Multimedia 20(3), 726\u2013737 (2018)","journal-title":"IEEE Trans. Multimedia"},{"issue":"8","key":"38_CR10","doi-asserted-by":"publisher","first-page":"2117","DOI":"10.1109\/TMM.2019.2896516","volume":"20","author":"X Li","year":"2020","unstructured":"Li, X., Jiang, S.: Know more say less: image captioning based on scene graphs. IEEE Trans. Multimedia 20(8), 2117\u20132130 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"38_CR11","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Proceedings of Meeting of the Association for Computational Linguistics, pp. 74\u201381 (2004)"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: Dual-level collaborative transformer for image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 10971\u201310980 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"38_CR16","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., Romero, et al. : Graph attention networks. arXiv:1710.10903 (2017)"},{"issue":"6","key":"38_CR17","doi-asserted-by":"publisher","first-page":"6575","DOI":"10.1007\/s10489-021-02734-3","volume":"52","author":"C Wang","year":"2021","unstructured":"Wang, C., Gu, X.: Image captioning with adaptive incremental global context attention. Appl. Intell. 52(6), 6575\u20136597 (2021). https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1007\/s10489-021-02734-3","journal-title":"Appl. Intell."},{"key":"38_CR18","doi-asserted-by":"publisher","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":"38_CR19","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1109\/TMM.2020.3011317","volume":"23","author":"J Wu","year":"2021","unstructured":"Wu, J., Chen, T., Wu, H., Yang, Z., Luo, G., Lin, L.: Fine-grained image captioning with global-local discriminative objective. IEEE Trans. Multimedia 23, 2413\u20132427 (2021)","journal-title":"IEEE Trans. Multimedia"},{"issue":"8","key":"38_CR20","doi-asserted-by":"publisher","first-page":"3118","DOI":"10.1109\/TCSVT.2020.3036860","volume":"31","author":"L Wu","year":"2021","unstructured":"Wu, L., Xu, M., Sang, L., Yao, T., Mei, T.: Noise augmented double-stream graph convolutional networks for image captioning. IEEE Trans. Circuits Syst. Video Technol. 31(8), 3118\u20133127 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"11","key":"38_CR21","doi-asserted-by":"publisher","first-page":"2942","DOI":"10.1109\/TMM.2019.2915033","volume":"21","author":"X Xiao","year":"2019","unstructured":"Xiao, X., Wang, L., Ding, K., Xiang, S., Pan, C.: Deep hierarchical encoder-decoder network for image captioning. IEEE Trans. Multimedia 21(11), 2942\u20132956 (2019)","journal-title":"IEEE Trans. Multimedia"},{"issue":"3","key":"38_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3386725","volume":"16","author":"L Yang","year":"2020","unstructured":"Yang, L., Hu, H., Xing, S., Lu, X.: Constrained LSTM and residual attention for image captioning. ACM Trans. Multimed. Comput. Commun. Appl. 16(3), 1\u201318 (2020)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"38_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:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1007\/978-3-030-01264-9_42"},{"key":"38_CR24","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Hierarchy parsing for image captioning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2621\u20132629 (2019)","DOI":"10.1109\/ICCV.2019.00271"},{"key":"38_CR25","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/TMM.2020.2976552","volume":"23","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Mei, K., Zheng, Y., Fan, J.: Integrating part of speech guidance for image captioning. IEEE Trans. Multimedia 23, 92\u2013104 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"38_CR26","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.patrec.2020.12.020","volume":"143","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Shi, X., Mi, S., Yang, X.: Image captioning with transformer and knowledge graph. Pattern Recogn. Lett. 143, 43\u201349 (2021)","journal-title":"Pattern Recogn. Lett."}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1645-0_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T17:18:20Z","timestamp":1681406300000},"score":1,"resource":{"primary":{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/link.springer.com\/10.1007\/978-981-99-1645-0_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916443","9789819916450"],"references-count":26,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1007\/978-981-99-1645-0_38","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/linproxy.fan.workers.dev:443\/https\/iconip2022.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","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":"359","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":"44% - 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":"2.65","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","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":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","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)"}}]}}