{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:20:12Z","timestamp":1742955612748,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442094"},{"type":"electronic","value":"9783031442100"}],"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:\/\/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:\/\/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\/978-3-031-44210-0_15","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T08:02:34Z","timestamp":1695283354000},"page":"180-191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Contour-Augmented Concept Prediction Network for\u00a0Image Captioning"],"prefix":"10.1007","author":[{"given":"Ting","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weidong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixing","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., et al.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Zeng, P., Zhang, H., Song, J., et al.: S2 transformer for image captioning. In: Proceedings of the International Joint Conferences on Artificial Intelligence, vol. 5 (2022)","DOI":"10.24963\/ijcai.2022\/224"},{"key":"15_CR3","doi-asserted-by":"publisher","unstructured":"Lian, Z., Wang, R., Li, H., Hu, X.: Context-assisted attention for image captioning. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds.) Artificial Neural Networks and Machine Learning - ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol. 13529, pp 722\u2013733. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15919-0_60","DOI":"10.1007\/978-3-031-15919-0_60"},{"key":"15_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/978-3-030-86362-3_18","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2021","author":"X Wang","year":"2021","unstructured":"Wang, X., Huang, J.: Say in human-like way: hierarchical cross-modal information abstraction and\u00a0summarization for controllable captioning. In: Farka\u0161, I., Masulli, P., Otte, S., Wermter, S. (eds.) ICANN 2021. LNCS, vol. 12891, pp. 217\u2013228. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86362-3_18"},{"key":"15_CR5","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_CR6","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"15_CR7","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., et al.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"15_CR9","doi-asserted-by":"publisher","unstructured":"Nguyen, V.Q., Suganuma, M., Okatani, T.: GRIT: faster and better image captioning transformer using dual visual features. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022. ECCV 2022. LNCS, vol. 13696, pp. 167\u2013184 Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_10","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Yang, X., Liu, Y., Wang, X.: Reformer: the relational transformer for image captioning. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5398\u20135406 (2022)","DOI":"10.1145\/3503161.3548409"},{"key":"15_CR11","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Zhu, X., et al.: Normalized and geometry-aware self-attention network for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10327\u201310336 (2020)","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"15_CR13","unstructured":"Herdade, S., Kappeler, A., Boakye, K., et al.: Image captioning: transforming objects into words. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sun, X., Luo, Y., et al.: Rstnet: captioning with adaptive attention on visual and non-visual words. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15465\u201315474 (2021)","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., et al.: Exploring visual relationship for image captioning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 684\u2013699 (2018)","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., et al.: 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_CR17","doi-asserted-by":"crossref","unstructured":"Luo, Y., Ji, J., Sun, X., et al.: Dual-level collaborative transformer for image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 3, pp. 2286\u20132293 (2021)","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., et al.: X-linear attention networks for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10971\u201310980 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Fei, Z.: Attention-aligned transformer for image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 1, pp. 607\u2013615 (2022)","DOI":"10.1609\/aaai.v36i1.19940"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Wu, M., Zhang, X., Sun, X., et al.: DIFNet: boosting visual information flow for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18020\u201318029 (2022)","DOI":"10.1109\/CVPR52688.2022.01749"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Dai, Y., Gieseke, F., Oehmcke, S., et al.: Attentional feature fusion. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3560\u20133569 (2021)","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"15_CR23","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.neucom.2021.01.034","volume":"437","author":"B Dong","year":"2021","unstructured":"Dong, B., Zhou, Y., Hu, C., et al.: BCNet: Bidirectional collaboration network for edge-guided salient object detection. Neurocomputing 437, 58\u201371 (2021)","journal-title":"Neurocomputing"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Li, Y., Pan, Y., Yao, T., et al.: Comprehending and ordering semantics for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17990\u201317999 (2022)","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Fang, Z., Wang, J., Hu, X., et al.: Injecting semantic concepts into end-to-end image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18009\u201318019 (2022)","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Ridnik, T., Ben-Baruch, E., Zamir, N., et al.: Asymmetric loss for multi-label classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 82\u201391 (2021)","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"15_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft coco: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei. L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.: Holistically-nested edge detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1395\u20131403 (2015)","DOI":"10.1109\/ICCV.2015.164"},{"key":"15_CR30","unstructured":"Mokady, R., Hertz, A., Bermano, A.H.: Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734 (2021)"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., et al.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"15_CR33","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"15_CR35","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:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44210-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T08:04:37Z","timestamp":1695283477000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44210-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442094","9783031442100"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44210-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","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":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"4","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":"type of other papers accepted  : 9 Abstract","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)"}}]}}