{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:20:48Z","timestamp":1742998848275,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819723898"},{"type":"electronic","value":"9789819723904"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-981-97-2390-4_25","type":"book-chapter","created":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T18:02:02Z","timestamp":1714240922000},"page":"363-376","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Benefit from\u00a0AMR: Image Captioning with\u00a0Explicit Relations and\u00a0Endogenous Knowledge"],"prefix":"10.1007","author":[{"given":"Feng","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shasha","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,28]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: In IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"25_CR2","unstructured":"Banarescu, L., et al.: Abstract meaning representation for sembanking. In: LAW@ACL (2013)"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Chatterjee, R., Weller, M., Negri, M., Turchi, M.: Exploring the planet of the apes: a comparative study of state-of-the-art methods for MT automatic post-editing. In: In 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, vol.\u00a02, pp. 156\u2013161 (2015)","DOI":"10.3115\/v1\/P15-2026"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Chen, F., Xie, S., Li, X., Li, S., Tang, J., Wang, T.: What topics do images say: a neural image captioning model with topic representation. In: In IEEE International Conference on Multimedia & Expo Workshops (ICMEW), pp. 447\u2013452. IEEE (2019)","DOI":"10.1109\/ICMEW.2019.00083"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: In IEEE Conference on Computer Vision and Pattern Recognition, pp. 6298\u20136306. IEEE (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., Jin, Q., Wang, P., Wu, Q.: Say as you wish: fine-grained control of image caption generation with abstract scene graphs. In: In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9962\u20139971 (2020)","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"25_CR7","doi-asserted-by":"publisher","unstructured":"Dong, G., Zhang, X., Lan, L. et al. Label guided correlation hashing for large-scale cross-modal retrieval. Multimed. Tools Appl. 78, 30895\u201330922 (2019). https:\/\/doi.org\/10.1007\/s11042-019-7192-5","DOI":"10.1007\/s11042-019-7192-5"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Feng, Y., Chen, X., Lin, B.Y., Wang, P., Yan, J., Ren, X.: Scalable multi-hop relational reasoning for knowledge-aware question answering. In: In Conference on Empirical Methods in Natural Language Processing (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.99"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Flanigan, J., Thomson, S., Carbonell, J., Dyer, C., Smith, N.A.: A discriminative graph-based parser for the abstract meaning representation. In: In Annual Meeting of the Association for Computational Linguistics (2014)","DOI":"10.3115\/v1\/P14-1134"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Gao, L., Fan, K., Song, J., Liu, X., Xu, X., Shen, H.T.: Deliberate attention networks for image captioning. In: In AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33018320"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Gu, J., Cai, J., Wang, G., Chen, T.: Stack-captioning: Coarse-to-fine learning for image captioning. In: AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12266"},{"issue":"1","key":"25_CR12","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1145\/3292058","volume":"15","author":"C He","year":"2019","unstructured":"He, C., Hu, H.: Image captioning with visual-semantic double attention. ACM Trans. Multimed. Comput. Commun. Appl. 15(1), 26 (2019)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Huang, F., Li, Z., Chen, S., Zhang, C., Ma, H.: Image captioning with internal and external knowledge. In 29th ACM International Conference on Information and Knowledge Management (2020)","DOI":"10.1145\/3340531.3411948"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: In IEEE International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"25_CR15","unstructured":"Huang, L., Wang, W., Xia, Y., Chen, J.: Adaptively aligned image captioning via adaptive attention time. In: In Advances in Neural Information Processing Systems, pp. 8942\u20138951 (2019)"},{"key":"25_CR16","doi-asserted-by":"publisher","first-page":"4013","DOI":"10.1109\/TIP.2020.2969330","volume":"29","author":"Y Huang","year":"2020","unstructured":"Huang, Y., Chen, J., Ouyang, W., Wan, W., Xue, Y.: Image captioning with end-to-end attribute detection and subsequent attributes prediction. IEEE Trans. Image Process. 29, 4013\u20134026 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR17","doi-asserted-by":"publisher","first-page":"7615","DOI":"10.1109\/TIP.2020.3004729","volume":"29","author":"J Ji","year":"2020","unstructured":"Ji, J., Xu, C., Zhang, X., Wang, B., Song, X.: Spatio-temporal memory attention for image captioning. IEEE Trans. Image Process. 29, 7615\u20137628 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, W., Ma, L., Jiang, Y.G., Liu, W., Zhang, T.: Recurrent fusion network for image captioning. In: In European Conference on Computer Vision, pp. 499\u2013515 (2018)","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"issue":"1","key":"25_CR20","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Liu, D., Zha, Z.J., Zhang, H., Zhang, Y., Wu, F.: Context-aware visual policy network for sequence-level image captioning. In: In 26th ACM international conference on Multimedia, pp. 1416\u20131424 (2018)","DOI":"10.1145\/3240508.3240632"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: IEEE Conference on Computer Vision and Pattern Recognition, vol.\u00a06, p.\u00a02 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Lyu, N.H.M.F.F.: TSFNET: triple-steam image captioning. IEEE Trans. Multimedia 25, 1\u201314 (2022)","DOI":"10.1109\/TMM.2022.3215861"},{"key":"25_CR24","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":"25_CR25","doi-asserted-by":"crossref","unstructured":"Tan, H., Zhang, X., Lan, L., Huang, X., Luo, Z.: Nonnegative constrained graph based canonical correlation analysis for multi-view feature learning. Neural Processing Letters, pp. 1\u201326 (2018)","DOI":"10.1007\/s11063-018-9904-7"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: Cider: consensus-based image description evaluation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"issue":"4","key":"25_CR27","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2016","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: Lessons learned from the 2015 MSCOCO image captioning challenge. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 652\u2013663 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"25_CR29","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2021.10.014","volume":"468","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Xu, J., Sun, Y.: A visual persistence model for image captioning. Neurocomputing 468, 48\u201359 (2022)","journal-title":"Neurocomputing"},{"key":"25_CR30","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1109\/TPAMI.2017.2708709","volume":"40","author":"Q Wu","year":"2018","unstructured":"Wu, Q., Shen, C., Wang, P., Dick, A., Hengel, A.V.: Image captioning and visual question answering based on attributes and external knowledge. IEEE Trans. Pattern Anal. Mach. Intell. 40, 1367\u20131381 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR31","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Computer Science, pp. 2048\u20132057 (2015)"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10685\u201310694 (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: European Conference on Computer Vision, pp. 684\u2013699 (2018)","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Hierarchy parsing for image captioning. In: IEEE\/CVF International Conference on Computer Vision, pp. 2621\u20132629 (2019)","DOI":"10.1109\/ICCV.2019.00271"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., Mei, T.: Boosting image captioning with attributes. In: IEEE International Conference on Computer Vision, pp. 22\u201329 (2017)","DOI":"10.1109\/ICCV.2017.524"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"25_CR37","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/TMM.2020.2976552","volume":"23","author":"J Zhang","year":"2020","unstructured":"Zhang, J., Mei, K., Zheng, Y., Fan, J.: Integrating part of speech guidance for image captioning. IEEE Trans. Multimedia 23, 92\u2013104 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, S., Ma, X., Duh, K., Durme, B.V.: Amr parsing as sequence-to-graph transduction. In: Annual Meeting of the Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1009"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Sun, Y., Honavar, V.G.: Improving image captioning by leveraging knowledge graphs. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 283\u2013293 (2019)","DOI":"10.1109\/WACV.2019.00036"},{"key":"25_CR40","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: 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","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2390-4_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T18:18:10Z","timestamp":1714241890000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2390-4_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819723898","9789819723904"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2390-4_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apweb-waim2023.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}