{"list":"other","total":51,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"1902.06162","title":"Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey","created":"2019-02-16","cited_by_count":657},{"id":"2011.00362","title":"A Survey on Contrastive Self-supervised Learning","created":"2020-10-31","cited_by_count":554},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250},{"id":"1904.01906","title":"What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis","created":"2019-04-03","cited_by_count":191},{"id":"2108.03032","title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","created":"2021-08-06","cited_by_count":116},{"id":"1709.02054","title":"Focusing Attention: Towards Accurate Text Recognition in Natural Images","created":"2017-09-07","cited_by_count":110},{"id":"1811.11212","title":"Self-Supervised GANs via Auxiliary Rotation Loss","created":"2018-11-27","cited_by_count":94},{"id":"1901.04596","title":"AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data","created":"2019-01-14","cited_by_count":77},{"id":"2012.10873","title":"Sequence-to-Sequence Contrastive Learning for Text Recognition","created":"2020-12-20","cited_by_count":70},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65},{"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":"2012.03868","title":"End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network","created":"2020-12-07","cited_by_count":50},{"id":"2104.07787","title":"Rethinking Text Line Recognition Models","created":"2021-04-15","cited_by_count":45},{"id":"2207.00193","title":"Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition","created":"2022-07-01","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":"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":"2206.00311","title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining","created":"2022-06-01","cited_by_count":34},{"id":"1804.01552","title":"Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection","created":"2018-04-04","cited_by_count":27},{"id":"2203.10492","title":"SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization","created":"2022-03-20","cited_by_count":21},{"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":"2110.05909","title":"Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes","created":"2021-10-12","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":"2203.04814","title":"Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement","created":"2022-03-09","cited_by_count":16},{"id":"2201.09390","title":"AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks","created":"2022-01-23","cited_by_count":12},{"id":"1712.04046","title":"Character-Based Handwritten Text Transcription with Attention Networks","created":"2017-12-11","cited_by_count":11},{"id":"2307.15045","title":"A Transformer-based Approach for Arabic Offline Handwritten Text Recognition","created":"2023-07-27","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":"1912.11603","title":"Image Enhanced Rotation Prediction for Self-Supervised Learning","created":"2019-12-25","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":"2306.06823","title":"Weakly supervised information extraction from inscrutable handwritten document images","created":"2023-06-12","cited_by_count":4}],"next_cursor":null}