{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"id":"1507.05717","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","created":"2015-07-21","cited_by_count":520},{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279},{"id":"1609.06773","title":"Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning","created":"2016-09-21","cited_by_count":257},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"2103.06495","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","created":"2021-03-11","cited_by_count":194},{"id":"1511.06085","title":"Variable Rate Image Compression with Recurrent Neural Networks","created":"2015-11-19","cited_by_count":173},{"id":"2006.01038","title":"DocBank: A Benchmark Dataset for Document Layout Analysis","created":"2020-06-01","cited_by_count":153},{"id":"2206.01062","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis","created":"2022-06-02","cited_by_count":148},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135},{"id":"2108.03032","title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","created":"2021-08-06","cited_by_count":116},{"id":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97},{"id":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85},{"id":"2005.13044","title":"Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition","created":"2020-05-26","cited_by_count":71},{"id":"2012.10873","title":"Sequence-to-Sequence Contrastive Learning for Text Recognition","created":"2020-12-20","cited_by_count":70},{"id":"2003.02567","title":"GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images","created":"2020-03-05","cited_by_count":68},{"id":"2203.12273","title":"DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition","created":"2022-03-23","cited_by_count":62},{"id":"1903.07377","title":"Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition","created":"2019-03-18","cited_by_count":58},{"id":"2006.07491","title":"OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold","created":"2020-06-12","cited_by_count":53},{"id":"2012.03868","title":"End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network","created":"2020-12-07","cited_by_count":50},{"id":"1604.08352","title":"Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition","created":"2016-04-28","cited_by_count":46},{"id":"1604.03286","title":"Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention","created":"2016-04-12","cited_by_count":45},{"id":"2104.07787","title":"Rethinking Text Line Recognition Models","created":"2021-04-15","cited_by_count":45},{"id":"2308.15996","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","created":"2023-08-30","cited_by_count":40},{"id":"1312.4569","title":"Dropout improves Recurrent Neural Networks for Handwriting Recognition","created":"2013-11-05","cited_by_count":39},{"id":"2305.13689","title":"Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training","created":"2023-05-23","cited_by_count":39},{"id":"2303.15269","title":"Handwritten Text Generation from Visual Archetypes","created":"2023-03-27","cited_by_count":32},{"id":"2104.01876","title":"MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition","created":"2021-04-05","cited_by_count":27},{"id":"1807.07965","title":"An Efficient End-to-End Neural Model for Handwritten Text Recognition","created":"2018-07-20","cited_by_count":25},{"id":"1904.09150","title":"A Scalable Handwritten Text Recognition System","created":"2019-04-19","cited_by_count":25},{"id":"2103.06450","title":"Full Page Handwriting Recognition via Image to Sequence Extraction","created":"2021-03-11","cited_by_count":24},{"id":"2409.08573","title":"HTR-VT: Handwritten Text Recognition with Vision Transformer","created":"2024-09-13","cited_by_count":24},{"id":"2012.02544","title":"Boosting offline handwritten text recognition in historical documents with few labeled lines","created":"2020-12-04","cited_by_count":19},{"id":"2102.08742","title":"SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition","created":"2021-02-17","cited_by_count":19},{"id":"2110.05909","title":"Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes","created":"2021-10-12","cited_by_count":18},{"id":"2402.10798","title":"VATr++: Choose Your Words Wisely for Handwritten Text Generation","created":"2024-02-16","cited_by_count":18},{"id":"2008.05373","title":"Attention-based Fully Gated CNN-BGRU for Russian Handwritten Text","created":"2020-08-12","cited_by_count":17},{"id":"2208.08109","title":"Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions","created":"2022-08-17","cited_by_count":14},{"id":"1912.10308","title":"Candidate Fusion: Integrating Language Modelling into a Sequence-to-Sequence Handwritten Word Recognition Architecture","created":"2019-12-21","cited_by_count":12},{"id":"2201.09390","title":"AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks","created":"2022-01-23","cited_by_count":12},{"id":"1608.04224","title":"Generating Synthetic Data for Text Recognition","created":"2016-08-15","cited_by_count":11},{"id":"1712.04046","title":"Character-Based Handwritten Text Transcription with Attention Networks","created":"2017-12-11","cited_by_count":11},{"id":"1909.08473","title":"Unsupervised Adaptation for Synthetic-to-Real Handwritten Word Recognition","created":"2019-09-18","cited_by_count":11},{"id":"2411.17332","title":"On the Generalization of Handwritten Text Recognition Models","created":"2024-11-26","cited_by_count":10},{"id":"2307.15045","title":"A Transformer-based Approach for Arabic Offline Handwritten Text Recognition","created":"2023-07-27","cited_by_count":9},{"id":"2407.09103","title":"DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents","created":"2024-07-12","cited_by_count":9},{"id":"2301.05935","title":"End-to-End Page-Level Assessment of Handwritten Text Recognition","created":"2023-01-14","cited_by_count":8},{"id":"2303.13931","title":"MSdocTr-Lite: A Lite Transformer for Full Page Multi-script Handwriting Recognition","created":"2023-03-24","cited_by_count":7},{"id":"2209.04817","title":"Lexicon and Attention based Handwritten Text Recognition System","created":"2022-09-11","cited_by_count":5},{"id":"2302.06308","title":"Fine-tuning Is a Surprisingly Effective Domain Adaptation Baseline in Handwriting Recognition","created":"2023-02-13","cited_by_count":5},{"id":"2306.06823","title":"Weakly supervised information extraction from inscrutable handwritten document images","created":"2023-06-12","cited_by_count":4}],"next_cursor":null}