{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T10:59:48Z","timestamp":1760785188565,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819724208"},{"type":"electronic","value":"9789819724215"}],"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\/978-981-97-2421-5_16","type":"book-chapter","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:01:48Z","timestamp":1715414508000},"page":"232-245","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["HM-Transformer: Hierarchical Multi-modal Transformer for\u00a0Long Document Image Understanding"],"prefix":"10.1007","author":[{"given":"Xi","family":"Deng","sequence":"first","affiliation":[]},{"given":"Shasha","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Ma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,5,12]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: Docformer: end-to-end transformer for document understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 993\u20131003 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"16_CR2","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)"},{"key":"16_CR3","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)"},{"key":"16_CR4","unstructured":"Cui, L., Xu, Y., Lv, T., Wei, F.: Document ai: benchmarks, models and applications. arXiv preprint arXiv:2111.08609 (2021)"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J.G., Le, Q., Salakhutdinov, R.: Transformer-xl: attentive language models beyond a fixed-length context. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2978\u20132988 (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"16_CR6","unstructured":"Ding, S., et al.: Ernie-doc: a retrospective long-document modeling transformer. In: ACL-IJCNLP, pp. 2914\u20132927 (2021)"},{"key":"16_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"16_CR8","first-page":"39","volume":"34","author":"J Gu","year":"2021","unstructured":"Gu, J., et al.: Unidoc: unified pretraining framework for document understanding. Adv. Neural. Inf. Process. Syst. 34, 39\u201350 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Gu, Z., et al.: Xylayoutlm: towards layout-aware multimodal networks for visually-rich document understanding. In: CVPR, pp. 4583\u20134592 (2022)","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: ICDAR, pp. 991\u2013995. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"16_CR11","doi-asserted-by":"crossref","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. In: AAAI, vol.\u00a036, pp. 10767\u201310775 (2022)","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Hu, Y., Ding, W., Liu, T., Gao, J., Sun, Y., Yin, B.: Hierarchical multiple granularity attention network for long document classification. In: IJCNN, pp.\u00a01\u20137. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892046"},{"key":"16_CR13","doi-asserted-by":"crossref","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, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: ICDARW, vol.\u00a02, pp.\u00a01\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"16_CR15","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., et al.: Formnet: structural encoding beyond sequential modeling in form document information extraction. In: ACL, pp. 3735\u20133754 (2022)","DOI":"10.18653\/v1\/2022.acl-long.260"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Structurallm: structural pre-training for form understanding. In: ACL, vol. pp. 6309\u20136318 (2021)","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: Selfdoc: self-supervised document representation learning. In: CVPR, pp. 5652\u20135660 (2021)","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph convolution for multimodal information extraction from visually rich documents. In: NAACL-HLT, pp. 32\u201339 (2019)","DOI":"10.18653\/v1\/N19-2005"},{"key":"16_CR20","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Pappagari, R., Zelasko, P., Villalba, J., Carmiel, Y., Dehak, N.: Hierarchical transformers for long document classification. In: ASRU, pp. 838\u2013844. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003958"},{"key":"16_CR22","unstructured":"Park, S., et al.: Cord: a consolidated receipt dataset for post-ocr parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Peng, Q., et\u00a0al.: Ernie-layout: layout knowledge enhanced pre-training for visually-rich document understanding. arXiv preprint arXiv:2210.06155 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.274"},{"key":"16_CR24","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1007\/978-3-030-86331-9_47","volume-title":"ICDAR","author":"R Powalski","year":"2021","unstructured":"Powalski, R., Borchmann, \u0141, Jurkiewicz, D., Dwojak, T., Pietruszka, M., Pa\u0142ka, G.: Going full-tilt boogie on document understanding with text-image-layout transformer. In: Llados, J., Lopresti, D., Uchida, S. (eds.) ICDAR, vol. 12822, pp. 732\u2013747. Springer, Heidelberg (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_47"},{"key":"16_CR25","first-page":"1","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28, 1\u20139 (2015)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"16_CR26","unstructured":"Su, J., Lu, Y., Pan, S., Murtadha, A., Wen, B., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. arXiv preprint arXiv:2104.09864 (2021)"},{"key":"16_CR27","first-page":"1","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 1\u201311 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Wang, J., Jin, L., Ding, K.: Lilt: a simple yet effective language-independent layout transformer for structured document understanding. In: ACL, pp. 7747\u20137757 (2022)","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Wu, C., Wu, F., Qi, T., Huang, Y.: Hi-transformer: hierarchical interactive transformer for efficient and effective long document modeling. In: ACL-IJCNLP, pp. 848\u2013853 (2021)","DOI":"10.18653\/v1\/2021.acl-short.107"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: Layoutlmv2: multi-modal pre-training for visually-rich document understanding. In: ACL, pp. 2579\u20132591 (2021)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"16_CR31","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: KDD, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Yang, X., Yumer, E., Asente, P., Kraley, M., Kifer, D., Giles, C.L.: Learning to extract semantic structure from documents using multimodal fully convolutional neural network. IEEE Computer Society (2017)","DOI":"10.1109\/CVPR.2017.462"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., Hovy, E.: Hierarchical attention networks for document classification. In: NAACL-HLT, pp. 1480\u20131489 (2016)","DOI":"10.18653\/v1\/N16-1174"},{"key":"16_CR34","first-page":"17283","volume":"33","author":"M Zaheer","year":"2020","unstructured":"Zaheer, M., et al.: Big bird: transformers for longer sequences. Adv. Neural. Inf. Process. Syst. 33, 17283\u201317297 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, F., Zhou, M.: Hibert: document level pre-training of hierarchical bidirectional transformers for document summarization. In: ACL, pp. 5059\u20135069 (2019)","DOI":"10.18653\/v1\/P19-1499"}],"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\/978-981-97-2421-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T18:18:23Z","timestamp":1731953903000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2421-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819724208","9789819724215"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2421-5_16","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":"12 May 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"}}]}}