{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T02:52:11Z","timestamp":1768272731502,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556755","type":"print"},{"value":"9789819556762","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5676-2_6","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:31:51Z","timestamp":1768249911000},"page":"79-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TriBiaNet: Hierarchical-Biaffine Multimodal Fusion for\u00a0Key Information Extraction in\u00a0Visually Rich Documents"],"prefix":"10.1007","author":[{"given":"Linying","family":"Wang","sequence":"first","affiliation":[]},{"given":"Mayire","family":"Ibrayim","sequence":"additional","affiliation":[]},{"given":"Peichao","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Wenjie","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Yang, D., et al.: A natural language processing and semantic-based system for contract analysis. In: 2013 IEEE 25th International Conference on Tools with Artificial Intelligence, pp. 707\u2013712. IEEE (2013)","DOI":"10.1109\/ICTAI.2013.109"},{"key":"6_CR2","doi-asserted-by":"publisher","unstructured":"Park, S., et al.: CORD: a consolidated receipt dataset for post-OCR parsing. arXiv preprint arXiv:1908.08218 (2019). https:\/\/doi.org\/10.48550\/arXiv.1908.08218","DOI":"10.48550\/arXiv.1908.08218"},{"key":"6_CR3","doi-asserted-by":"publisher","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 991\u2013995. IEEE, Nancy, France (2015). https:\/\/doi.org\/10.1109\/ICDAR.2015.7333942","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"6_CR4","unstructured":"Katti, A.R., et al.: Chargrid: towards understanding 2D documents. arXiv preprint arXiv:1809.08799 (2018). arxiv.org\/abs\/1809.08799"},{"key":"6_CR5","doi-asserted-by":"publisher","unstructured":"Palm, R.B., Laws, F., Winther, O.: Attend, copy, parse end-to-end information extraction from documents. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 329\u2013336. IEEE (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00060","DOI":"10.1109\/ICDAR.2019.00060"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Ha, H.T., Hor\u00e1k, A.: Information extraction from scanned invoice images using text analysis and layout features. Sig. Process. Image Commun. (to appear). arXiv preprint arXiv:2208.04011 (2022). arxiv.org\/abs\/2208.04011","DOI":"10.1016\/j.image.2021.116601"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"6_CR8","unstructured":"Koroteev, M.V.: BERT: a review of applications in natural language processing and understanding. arXiv preprint arXiv:2103.11943 (2021). arxiv.org\/abs\/2103.11943"},{"key":"6_CR9","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. arXiv preprint arXiv:2012.14740 (2020). arxiv.org\/abs\/2012.14740"},{"key":"6_CR10","doi-asserted-by":"publisher","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document AI with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia (MM \u201922), pp. 4083\u20134091. ACM, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3503161.3548112","DOI":"10.1145\/3503161.3548112"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Yu, W., Lu, N., Qi, X., Gong, P., Xiao, R.: Pick: processing key information extraction from documents using improved graph learning\u2013convolutional networks. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 4363\u20134370. IEEE, Milan, Italy (2021)","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"6_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1007\/978-3-031-70552-6_15","volume-title":"Document Analysis and Recognition - ICDAR 2024","author":"H Gbada","year":"2024","unstructured":"Gbada, H., Kalti, K., Mahjoub, M.A.: Information extraction from visually rich documents using directed weighted graph neural network. In: Barney Smith, E.H., Liwicki, M., Peng, L. (eds.) ICDAR 2024. LNCS, vol. 14809, pp. 248\u2013263. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-70552-6_15"},{"key":"6_CR13","doi-asserted-by":"publisher","unstructured":"Shi, T., Huang, S.-L.: MultiEMO: an attention-based correlation-aware multimodal fusion framework for emotion recognition in conversations. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 14752\u201314766. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.824","DOI":"10.18653\/v1\/2023.acl-long.824"},{"key":"6_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109542","volume":"140","author":"P Cao","year":"2023","unstructured":"Cao, P., Wu, J.: GraphRevisedIE: multimodal information extraction with graph-revised network. Pattern Recogn. 140, 109542 (2023). https:\/\/doi.org\/10.1016\/j.patcog.2023.109542","journal-title":"Pattern Recogn."},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.-P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol. 2, pp. 1\u20136. IEEE, Sydney, Australia (2019). https:\/\/doi.org\/10.1109\/ICDARW.2019.10029","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"6_CR16","doi-asserted-by":"publisher","unstructured":"Yang, Z., et al.: Modeling entities as semantic points for visual information extraction in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15358\u201315367. IEEE\/CVF, Vancouver, Canada (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01474","DOI":"10.1109\/CVPR52729.2023.01474"},{"key":"6_CR17","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019). arxiv.org\/abs\/1907.11692"},{"key":"6_CR18","unstructured":"Bao, H., et al.: UniLMv2: pseudo-masked language models for unified language model pre-training. In: Proceedings of the International Conference on Machine Learning, pp. 642\u2013652. PMLR (2020)"},{"key":"6_CR19","unstructured":"Hong, T., Kim, D., Ji, M., Hwang, W., Nam, D., Park, S.: BROS: a pre-trained language model focusing on text and layout for better key information extraction from documents. arXiv preprint arXiv:2108.04539 (2021). arxiv.org\/abs\/2108.04539"},{"key":"6_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/978-3-031-41679-8_7","volume-title":"Document Analysis and Recognition - ICDAR 2023","author":"D Belhadj","year":"2023","unstructured":"Belhadj, D., Bela\u00efd, A., Bela\u00efd, Y.: Improving information extraction from semi-structured documents using attention-based semi-variational graph auto-encoder. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14188, pp. 113\u2013129. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_7"},{"key":"6_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/978-3-031-41682-8_3","volume-title":"Document Analysis and Recognition - ICDAR 2023","author":"Y-M Chen","year":"2023","unstructured":"Chen, Y.-M., Hou, X.-T., Lou, D.-F., Liao, Z.-L., Liu, C.-L.: DAMGCN: entity linking in visually rich documents with dependency-aware multimodal graph convolutional network. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14189, pp. 33\u201347. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41682-8_3"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Tang, G., et al.: MatchVIE: exploiting match relevancy between entities for visual information extraction. arXiv preprint arXiv:2106.12940 (2021). arxiv.org\/abs\/2106.12940","DOI":"10.24963\/ijcai.2021\/144"},{"key":"6_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127223","volume":"573","author":"H Gbada","year":"2024","unstructured":"Gbada, H., Kalti, K., Mahjoub, M.A.: Multimodal weighted graph representation for information extraction from visually rich documents. Neurocomputing 573, 127223 (2024). https:\/\/doi.org\/10.1016\/j.neucom.2023.127223","journal-title":"Neurocomputing"},{"key":"6_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/978-3-031-41682-8_10","volume-title":"Document Analysis and Recognition - ICDAR 2023","author":"D Shi","year":"2023","unstructured":"Shi, D., Liu, S., Du, J., Zhu, H.: LayoutGCN: a lightweight architecture for visually rich document understanding. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14189, pp. 149\u2013165. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41682-8_10"},{"key":"6_CR25","unstructured":"Guo, X., Wang, Y., Du, T., Wang, Y.: Contranorm: a contrastive learning perspective on oversmoothing and beyond. arXiv preprint arXiv:2303.06562 (2023)"},{"key":"6_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"6_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-981-97-8493-6_2","volume-title":"Pattern Recognition and Computer Vision - PRCV 2024","author":"P Wang","year":"2024","unstructured":"Wang, P., Liu, S., Yilahun, H., Hamdulla, A.: Lightweight and multi-scale adaptive network for infrared small target detection. In: Lin, Z., et al. (eds.) PRCV 2024. LNCS, vol. 15043, pp. 18\u201331. Springer, Singapore (2024). https:\/\/doi.org\/10.1007\/978-981-97-8493-6_2"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5676-2_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:31:54Z","timestamp":1768249914000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5676-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556755","9789819556762"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5676-2_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}