{"type":"ScholarlyArticle","title":"Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding","authors":[{"name":"Mingliang Zhai","slug":"mingliang-zhai","given":"Mingliang","family":"Zhai","affiliation":"Beijing Key Laboratory of Intelligent Information Technology , Beijing Institute of Technology , China; Department of Computer Vision Technology (VIS) , Baidu Inc."},{"name":"Yulin Li","slug":"yulin-li","given":"Yulin","family":"Li","affiliation":"Department of Computer Vision Technology (VIS) , Baidu Inc."},{"name":"Xiameng Qin","slug":"xiameng-qin","given":"Xiameng","family":"Qin","affiliation":"Department of Computer Vision Technology (VIS) , Baidu Inc."},{"name":"Chen Yi","slug":"chen-yi","given":"Chen","family":"Yi","affiliation":"Department of Computer Vision Technology (VIS) , Baidu Inc."},{"name":"Qunyi Xie","slug":"qunyi-xie","given":"Qunyi","family":"Xie","affiliation":"Department of Computer Vision Technology (VIS) , Baidu Inc."},{"name":"Chengquan Zhang","slug":"chengquan-zhang","given":"Chengquan","family":"Zhang","affiliation":"Department of Computer Vision Technology (VIS) , Baidu Inc."},{"name":"Kun Yao","slug":"kun-yao","given":"Kun","family":"Yao","affiliation":"Department of Computer Vision Technology (VIS) , Baidu Inc."},{"name":"Yuwei Wu","slug":"yuwei-wu","given":"Yuwei","family":"Wu","affiliation":"Beijing Key Laboratory of Intelligent Information Technology , Beijing Institute of Technology , China; Guangdong Laboratory of Machine Perception and Intelligent Computing , Shenzhen MSU-BIT University , China"},{"name":"Yunde Jia","slug":"yunde-jia","given":"Yunde","family":"Jia","affiliation":"Beijing Key Laboratory of Intelligent Information Technology , Beijing Institute of Technology , China; Guangdong Laboratory of Machine Perception and Intelligent Computing , Shenzhen MSU-BIT University , China"}],"abstract":"Transformers achieve promising performance in document understanding because of their high effectiveness and still suffer from quadratic computational complexity dependency on the sequence length. General efficient transformers are challenging to be directly adapted to model document. They are unable to handle the layout representation in documents, e.g. word, line and paragraph, on different granularity levels and seem hard to achieve a good trade-off between efficiency and performance. To tackle the concerns, we propose Fast-StrucTexT, an efficient multi-modal framework based on the StrucTexT algorithm with an hourglass transformer architecture, for visual document understanding. Specifically, we design a modality-guided dynamic token merging block to make the model learn multi-granularity representation and prunes redundant tokens. Additionally, we present a multi-modal interaction module called Symmetry Cross-Attention (SCA) to consider multi-modal fusion and efficiently guide the token mergence. The SCA allows one modality input as query to calculate cross attention with another modality in a dual phase. Extensive experiments on FUNSD, SROIE, and CORD datasets demonstrate that our model achieves the state-of-the-art performance and almost 1.9x faster inference time than the state-of-the-art methods.","doi":"10.24963/ijcai.2023/585","url":"https://ijcai.org/proceedings/2023/585","pdf":"https://ijcai.org/proceedings/2023/0585.pdf","markdown":"https://ijcai.org/proceedings/2023/585.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/585","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Natural Language Processing","track":"Main Track","number":585,"pages":{"first":5269,"last":5277},"keywords":["Machine Learning: ML: Multi-modal learning","Natural Language Processing: NLP: Information extraction"],"videos":[],"references":[{"position":1,"raw":"[Appalaraju et al., 2021] Srikar Appalaraju, Bhavan Jasani, Bhargava Urala Kota, Yusheng Xie, and R. Manmatha. Docformer: End-to-end transformer for document under- standing. In ICCV, pages 973-983, 2021.","title":"Docformer: End-to-end transformer for document understanding","authors":"Srikar Appalaraju, Bhavan Jasani, Urala Bhargava, Yusheng Kota, R Xie, Manmatha","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Beltagy et al., 2020] Iz Beltagy, Matthew E. Peters, and Ar- man Cohan. Longformer: The long-document trans- former. CoRR, 2020.","title":"Longformer: The long-document transformer","authors":"Iz Beltagy, Matthew E Peters, Arman Cohan","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2022] Xiaokang Chen, Mingyu Ding, Xiaodi Wang, Ying Xin, Shentong Mo, Yunhao Wang, Shumin Han, Ping Luo, Gang Zeng, and Jingdong Wang. Con- text autoencoder for self-supervised representation learn- ing. arXiv preprint:2202.03026, 2022.","title":"Context autoencoder for self-supervised representation learning","authors":"Xiaokang Chen, Mingyu Ding, Xiaodi Wang, Ying Xin, Shentong Mo, Yunhao Wang, Shumin Han, Ping Luo, Gang Zeng, Jingdong Wang","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Child et al., 2019] Rewon Child, Scott Gray, Alec Radford, and Ilya Sutskever. Generating long sequences with sparse transformers. CoRR, 2019.","title":"Generating long sequences with sparse transformers","authors":"Child","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Dai et al., 2020a] Zihang Dai, Guokun Lai, Yiming Yang, and Quoc Le. Funnel-transformer: Filtering out sequential redundancy for efficient language processing. In NeurIPS, pages 4271-4282, 2020.","title":"Funnel-transformer: Filtering out sequential redundancy for efficient language processing","authors":"Dai","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dai et al., 2020b] Zihang Dai, Guokun Lai, Yiming Yang, and Quoc Le. Funnel-transformer: Filtering out sequential redundancy for efficient language processing. In NeurIPS, pages 4271-4282, 2020.","title":"Funnel-transformer: Filtering out sequential redundancy for efficient language processing","authors":"Dai","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR, pages 248-255, 2009.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Devlin et al., 2019] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. BERT: pre-training of deep bidirectional transformers for language understand- ing. In NAACL-HLT, pages 4171-4186, 2019.","title":"BERT: pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2019","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gu et al., 2021] Jiuxiang Gu, Jason Kuen, Vlad I. Morariu, Handong Zhao, Rajiv Jain, Nikolaos Barmpalios, Ani Nenkova, and Tong Sun. Unidoc: Unified pretraining framework for document understanding. In NeurIPS, pages 39-50, 2021.","title":"Unidoc: Unified pretraining framework for document understanding","authors":"Jiuxiang Gu, Jason Kuen, Vlad I Morariu, Handong Zhao, Rajiv Jain, Nikolaos Barmpalios, Ani Nenkova, Tong Sun","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gu et al., 2022] Zhangxuan Gu, Changhua Meng, Ke Wang, Jun Lan, Weiqiang Wang, Ming Gu, and Liqing Zhang. Xylayoutlm: Towards layout-aware multi- modal networks for visually-rich document understanding. In CVPR, pages 4573-4582, 2022.","title":"Xylayoutlm: Towards layout-aware multimodal networks for visually-rich document understanding","authors":"Gu","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Guo et al., 2021] Menghao Guo, Zhengning Liu, Taijiang Mu, and Shimin Hu. Beyond self-attention: External at- tention using two linear layers for visual tasks. TPAMI, pages 5436-5447, 2021.","title":"Beyond self-attention: External attention using two linear layers for visual tasks","authors":"Guo","year":"2021","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Harley et al., 2015] Adam W. Harley, Alex Ufkes, and Kon- stantinos G. Derpanis. Evaluation of deep convolutional nets for document image classification and retrieval. In ICDAR, pages 991-995, 2015.","title":"Evaluation of deep convolutional nets for document image classification and retrieval","authors":"Adam W Harley, Alex Ufkes, Konstantinos G Derpanis","year":"2015","venue":"ICDAR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"He","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hong et al., 2022] Teakgyu Hong, Donghyun Kim, Mingi Ji, Wonseok Hwang, Daehyun Nam, and Sungrae Park. BROS: A pre-trained language model focusing on text and layout for better key information extraction from docu- ments. In AAAI, 2022.","title":"BROS: A pre-trained language model focusing on text and layout for better key information extraction from documents","authors":"Hong","year":"2022","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Hongxu et al., 2022] Yin Hongxu, Vahdat Arash, Al- varez Jose M, Mallya Arun, Kautz Jan, and Molchanov Pavlo. A-vit: Adaptive tokens for efficient vision trans- former. In CVPR, pages 10809-10818, 2022.","title":"A-vit: Adaptive tokens for efficient vision transformer","authors":"Yin Hongxu, Alvarez Vahdat Arash, M Jose, Mallya Arun, Jan Kautz, Molchanov Pavlo","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Huang et al., 2021] Zheng Huang, Kai Chen, Jianhua He, Xiang Bai, Dimosthenis Karatzas, Shijian Lu, and C. V. Jawahar. Icdar. CoRR, 2021.","title":"Icdar. CoRR","authors":"Zheng Huang, Kai Chen, Jianhua He, Xiang Bai, Dimosthenis Karatzas, Shijian Lu, C V Jawahar","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Huang et al., 2022] Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, and Furu Wei. Layoutlmv3: Pre-training for document AI with unified text and image masking. In ACM Multimedia, 2022.","title":"Layoutlmv3: Pre-training for document AI with unified text and image masking","authors":"Huang","year":"2022","venue":"ACM Multimedia","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Hwang et al., 2021] Wonseok Hwang, Jinyeong Yim, Se- unghyun Park, Sohee Yang, and Minjoon Seo. Spatial dependency parsing for semi-structured document infor- mation extraction. In ACL, pages 330-343, 2021.","title":"Spatial dependency parsing for semi-structured document information extraction","authors":"Hwang","year":"2021","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Jaegle Andrew, 2021] Alayrac Jean-Baptiste Doersch Carl Ionescu Catalin Ding David Koppula Skanda Zoran Daniel Brock Andrew Shelhamer Evan others Jaegle Andrew, Borgeaud Sebastian. Perceiver IO: A general architecture for structured inputs & outputs. In ICLR, 2021.","title":"Perceiver IO: A general architecture for structured inputs & outputs","authors":"Jaegle Andrew, ; Ionescu, Catalin Ding, David Koppula, Skanda Zoran, Daniel Brock, Andrew Shelhamer, Evan Others, Jaegle Andrew, Borgeaud Sebastian","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Jaume et al., 2019] Guillaume Jaume, Hazim Kemal Ekenel, and Jean-Philippe Thiran. FUNSD: A dataset for form understanding in noisy scanned documents. In ICDAR, pages 1-6, 2019.","title":"FUNSD: A dataset for form understanding in noisy scanned documents","authors":"Guillaume Jaume, Hazim Kemal Ekenel, Jean-Philippe Thiran","year":"2019","venue":"ICDAR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Jiao et al., 2020] Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, and Qun Liu. Tinybert: Distilling BERT for natural language un- derstanding. In EMNLP, pages 4163-4174, 2020.","title":"Tinybert: Distilling BERT for natural language understanding","authors":"Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, Qun Liu","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Kim et al., 2022] Sehoon Kim, Sheng Shen, David Thors- ley, Amir Gholami, Woosuk Kwon, Joseph Hassoun, and Kurt Keutzer. Learned token pruning for transformers. In SIGKDD, pages 784-794, 2022.","title":"Learned token pruning for transformers","authors":"Kim","year":"2022","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Lee et al., 2022] Chen-Yu Lee, Chun-Liang Li, Timothy Dozat, Vincent Perot, Guolong Su, Nan Hua, Joshua Ainslie, Renshen Wang, Yasuhisa Fujii, and Tomas Pfister. Formnet: Structural encoding beyond sequential modeling in form document information extraction. In ACL, pages 3735-3754, 2022.","title":"Formnet: Structural encoding beyond sequential modeling in form document information extraction","authors":"Chen-Yu Lee, Chun-Liang Li, Timothy Dozat, Vincent Perot, Guolong Su, Nan Hua, Joshua Ainslie, Renshen Wang, Yasuhisa Fujii, Tomas Pfister","year":"2022","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Lee Juho, 2019] Kim Jungtaek-Kosiorek Adam Choi Se- ungjin Teh Yee Whye Lee Juho, Lee Yoonho. Set trans- former: A framework for attention-based permutation- invariant neural networks. In ICML, pages 3744-3753, 2019.","title":"Set transformer: A framework for attention-based permutationinvariant neural networks","authors":"Lee Juho, ; Kim, Jungtaek-Kosiorek, Adam Choi, Seungjin Teh, Yee Whye, Lee Juho, Lee Yoonho","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Li et al., 2021a] Chenliang Li, Bin Bi, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, and Luo Si. Struc- turallm: Structural pre-training for form understanding. In ACL, pages 6309-6318, 2021.","title":"Structurallm: Structural pre-training for form understanding","authors":"Li","year":"2021","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Li et al., 2021b] Peizhao Li, Jiuxiang Gu, Jason Kuen, Vlad I. Morariu, Handong Zhao, Rajiv Jain, Varun Man- junatha, and Hongfu Liu. Selfdoc: Self-supervised docu- ment representation learning. In CVPR, pages 5652-5660, 2021.","title":"Selfdoc: Self-supervised document representation learning","authors":"Li","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Li et al., 2021c] Yulin Li, Yuxi Qian, Yuechen Yu, Xiameng Qin, Chengquan Zhang, Yan Liu, Kun Yao, Junyu Han, Jingtuo Liu, and Errui Ding. Structext: Structured text un- derstanding with multi-modal transformers. In ACM Mul- timedia, pages 1912-1920, 2021.","title":"Structext: Structured text understanding with multi-modal transformers","authors":"Li","year":"2021","venue":"ACM Multimedia","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Liu et al., 2019] Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized BERT pretraining approach. CoRR, 2019.","title":"Roberta: A robustly optimized BERT pretraining approach","authors":"Liu","year":"2019","venue":"CoRR","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Marin et al., 2023] Dmitrii Marin, Jen-Hao Rick Chang, Anurag Ranjan, Anish Prabhu, Mohammad Rastegari, and Oncel Tuzel. Token pooling in vision transformers for im- age classification. In WACV, pages 12-21, 2023.","title":"Token pooling in vision transformers for image classification","authors":"Dmitrii Marin, Jen - Hao, Rick Chang, Anurag Ranjan, Anish Prabhu, Mohammad Rastegari, Oncel Tuzel","year":"2023","venue":"WACV","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Pan et al., 2022] Junting Pan, Adrian Bulat, Fuwen Tan, Xi- atian Zhu, Lukasz Dudziak, Hongsheng Li, Georgios Tz- imiropoulos, and Brais Martínez. Edgevits: Competing light-weight cnns on mobile devices with vision trans- formers. In ECCV, pages 294-311, 2022.","title":"Edgevits: Competing light-weight cnns on mobile devices with vision transformers","authors":"Pan","year":"2022","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Park et al., 2019] Seunghyun Park, Seung Hyun Shin, Bado Lee, Junyeop Lee, Jaeheung Surh, Minjoon Seo, and Hwalsuk Lee. Cord: A consolidated receipt dataset for post-ocr parsing. In NIPS Workshop, 2019.","title":"Cord: A consolidated receipt dataset for post-ocr parsing","authors":"Seunghyun Park, Hyun Seung, Bado Shin, Junyeop Lee, Jaeheung Lee, Minjoon Surh, Hwalsuk Seo, Lee","year":"2019","venue":"NIPS Workshop","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Ryoo et al., 2021] Michael S. Ryoo, A. J. Piergiovanni, Anurag Arnab, Mostafa Dehghani, and Anelia Angelova. Tokenlearner: What can 8 learned tokens do for images and videos? CoRR, 2021.","title":"Tokenlearner: What can 8 learned tokens do for images and videos? CoRR","authors":"Michael S Ryoo, A J Piergiovanni, Anurag Arnab, Mostafa Dehghani, Anelia Angelova","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Tang et al., 2021] Guozhi Tang, Lele Xie, Lianwen Jin, Ji- apeng Wang, Jingdong Chen, Zhen Xu, Qianying Wang, Yaqiang Wu, and Hui Li. Matchvie: Exploiting match rel- evancy between entities for visual information extraction. In IJCAI, pages 1039-1045, 2021.","title":"Matchvie: Exploiting match relevancy between entities for visual information extraction","authors":"Guozhi Tang, Lele Xie, Lianwen Jin, Jiapeng Wang, Jingdong Chen, Zhen Xu, Qianying Wang, Yaqiang Wu, Hui Li","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/144"},{"position":34,"raw":"[Verma, 2021] Madhusudan Verma. Revisiting linformer with a modified self-attention with linear complexity. CoRR, 2021.","title":"Revisiting linformer with a modified self-attention with linear complexity","authors":"Madhusudan Verma","year":"2021","venue":"CoRR","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Wang et al., 2021] Jiapeng Wang, Chongyu Liu, Lianwen Jin, Guozhi Tang, Jiaxin Zhang, Shuaitao Zhang, Qianying Wang, Yaqiang Wu, and Mingxiang Cai. Towards robust visual information extraction in real world: new dataset and novel solution. In AAAI, pages 2738-2745, 2021.","title":"Towards robust visual information extraction in real world: new dataset and novel solution","authors":"Wang","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Wang et al., 2022] Jian Wang, Chenhui Gou, Qiman Wu, Haocheng Feng, Junyu Han, Errui Ding, and Jingdong Wang. Rtformer: Efficient design for real-time semantic segmentation with transformer. In NeurIPS, 2022.","title":"Rtformer: Efficient design for real-time semantic segmentation with transformer","authors":"Jian Wang, Chenhui Gou, Qiman Wu, Haocheng Feng, Junyu Han, Errui Ding, Jingdong Wang","year":"2022","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Wu et al., 2022] Kan Wu, Jinnian Zhang, Houwen Peng, Mengchen Liu, Bin Xiao, Jianlong Fu, and Lu Yuan. Tinyvit: Fast pretraining distillation for small vision trans- formers. In ECCV, pages 68-85, 2022.","title":"Tinyvit: Fast pretraining distillation for small vision transformers","authors":"Kan Wu, Jinnian Zhang, Houwen Peng, Mengchen Liu, Bin Xiao, Jianlong Fu, Lu Yuan","year":"2022","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Xia et al., 2022] Zhuofan Xia, Xuran Pan, Shiji Song, Li Er- ran Li, and Gao Huang. Vision transformer with de- formable attention. In CVPR, pages 4784-4793, 2022.","title":"Vision transformer with deformable attention","authors":"Xia","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Xiong et al., 2021] Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty, Mingxing Tan, Glenn Fung, Yin Li, and Vikas Singh. Nyströmformer: A nyström-based algorithm for approximating self-attention. In AAAI, pages 14138-14148, 2021.","title":"Nyströmformer: A nyström-based algorithm for approximating self-attention","authors":"Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty, Mingxing Tan, Glenn Fung, Yin Li, Vikas Singh","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Xu et al., 2020] Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, and Ming Zhou. Layoutlm: Pre-training of text and layout for document image understanding. In ACM SIGKDD, pages 1192-1200, 2020.","title":"Layoutlm: Pre-training of text and layout for document image understanding","authors":"Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou","year":"2020","venue":"ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Xu et al., 2021] Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei A. F. Florêncio, Cha Zhang, Wanxiang Che, Min Zhang, and Lidong Zhou. Layoutlmv2: Multi-modal pre-training for visually-rich document understanding. In ACL, pages 2579-2591, 2021.","title":"Layoutlmv2: Multi-modal pre-training for visually-rich document understanding","authors":"Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, A F Dinei, Cha Florêncio, Wanxiang Zhang, Min Che, Lidong Zhang, Zhou","year":"2021","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Xu et al., 2022a] Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Thomas M. Breuel, Jan Kautz, and Xi- aolong Wang. Groupvit: Semantic segmentation emerges from text supervision. In CVPR, pages 18113-18123, 2022.","title":"Groupvit: Semantic segmentation emerges from text supervision","authors":"Xu","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Xu et al., 2022b] Yiheng Xu, Tengchao Lv, Lei Cui, Guoxin Wang, Yijuan Lu, Dinei A. F. Florêncio, Cha Zhang, and Furu Wei. XFUND: A benchmark dataset for multilingual visually rich form understanding. In ACL, pages 3214- 3224, 2022.","title":"XFUND: A benchmark dataset for multilingual visually rich form understanding","authors":"Xu","year":"2022","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Zhang et al., 2020] Peng Zhang, Yunlu Xu , Zhanzhan Cheng , Shiliang Pu , Jing Lu , Liang Qiao , Yi Niu , and Fei Wu . TRIE: end-to-end text reading and information extraction for document understanding. In ACM Multimedia, pages 1413-1422, 2020.","title":"TRIE: end-to-end text reading and information extraction for document understanding","authors":"Peng Zhang, Yunlu Xu, Zhanzhan Cheng, Shiliang Pu, Jing Lu, Liang Qiao, Yi Niu, Fei Wu","year":"2020","venue":"ACM Multimedia","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Zhang et al., 2021] Yue Zhang, Bo Zhang, Rui Wang, Jun- jie Cao, Chen Li, and Zuyi Bao. Entity relation extrac- tion as dependency parsing in visually rich documents. In EMNLP, pages 2759-2768, 2021.","title":"Entity relation extraction as dependency parsing in visually rich documents","authors":"Yue Zhang, Bo Zhang, Rui Wang, Junjie Cao, Chen Li, Zuyi Bao","year":"2021","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Zhang et al., 2022] Jinnian Zhang, Houwen Peng, Kan Wu, Mengchen Liu, Bin Xiao, Jianlong Fu, and Lu Yuan. Minivit: Compressing vision transformers with weight multiplexing. In CVPR, pages 12135-12144, 2022.","title":"Minivit: Compressing vision transformers with weight multiplexing","authors":"Jinnian Zhang, Houwen Peng, Kan Wu, Mengchen Liu, Bin Xiao, Jianlong Fu, Lu Yuan","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}