{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"1905.13538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","created":"2019-05-27","cited_by_count":349},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"2103.10213","title":"ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction","created":"2021-03-18","cited_by_count":256},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"1502.07058","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","created":"2015-02-25","cited_by_count":213},{"id":"2002.12804","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","created":"2020-02-28","cited_by_count":204},{"id":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117},{"id":"2108.04539","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","created":"2021-08-10","cited_by_count":104},{"id":"2104.08836","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","created":"2021-04-18","cited_by_count":103},{"id":"1905.04226","title":"Language Modeling with Deep Transformers","created":"2019-05-10","cited_by_count":96},{"id":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91},{"id":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90},{"id":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85},{"id":"2004.07464","title":"PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks","created":"2020-04-16","cited_by_count":72},{"id":"2210.06155","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","created":"2022-10-12","cited_by_count":67},{"id":"2005.13118","title":"TRIE: End-to-End Text Reading and Information Extraction for Document Understanding","created":"2020-05-27","cited_by_count":61},{"id":"1903.07377","title":"Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition","created":"2019-03-18","cited_by_count":58},{"id":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","cited_by_count":46},{"id":"2304.04052","title":"Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder","created":"2023-04-08","cited_by_count":44},{"id":"2303.00289","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","created":"2023-03-01","cited_by_count":39},{"id":"2011.13534","title":"A Survey of Deep Learning Approaches for OCR and Document Understanding","created":"2020-11-27","cited_by_count":32},{"id":"2210.07124","title":"RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer","created":"2022-10-13","cited_by_count":31},{"id":"1608.03542","title":"WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia","created":"2016-08-11","cited_by_count":26},{"id":"1909.02576","title":"Deep Visual Template-Free Form Parsing","created":"2019-09-05","cited_by_count":24},{"id":"2211.08469","title":"Deep learning for table detection and structure recognition: A survey","created":"2022-11-15","cited_by_count":15},{"id":"2106.15322","title":"TNCR: Table Net Detection and Classification Dataset","created":"2021-06-19","cited_by_count":14},{"id":"2007.03579","title":"HKR For Handwritten Kazakh & Russian Database","created":"2020-07-07","cited_by_count":12},{"id":"2010.05322","title":"Revising FUNSD dataset for key-value detection in document images","created":"2020-10-11","cited_by_count":10},{"id":"2110.04075","title":"KOHTD: Kazakh Offline Handwritten Text Dataset","created":"2021-09-22","cited_by_count":10},{"id":"2307.11278","title":"Generator-Retriever-Generator Approach for Open-Domain Question Answering","created":"2023-07-21","cited_by_count":8},{"id":"1911.03782","title":"Enforcing Encoder-Decoder Modularity in Sequence-to-Sequence Models","created":"2019-11-09","cited_by_count":7},{"id":"2305.11392","title":"Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding","created":"2023-05-19","cited_by_count":6},{"id":"2102.04816","title":"Classification of Handwritten Names of Cities and Handwritten Text Recognition using Various Deep Learning Models","created":"2021-02-09","cited_by_count":5},{"id":"2112.01177","title":"MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion Attention","created":"2021-12-02","cited_by_count":5},{"id":"1905.12571","title":"Flat2Layout: Flat Representation for Estimating Layout of General Room Types","created":"2019-05-29","cited_by_count":4},{"id":"2108.13297","title":"VTLayout: Fusion of Visual and Text Features for Document Layout Analysis","created":"2021-08-12","cited_by_count":4},{"id":"2001.08687","title":"Navigation-Based Candidate Expansion and Pretrained Language Models for Citation Recommendation","created":"2020-01-23","cited_by_count":3},{"id":"2302.05454","title":"Distillation of encoder-decoder transformers for sequence labelling","created":"2023-02-10","cited_by_count":3},{"id":"2305.10448","title":"Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding","created":"2023-05-16","cited_by_count":2}],"next_cursor":null}