{"list":"other","total":60,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"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":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1711.02281","title":"Non-Autoregressive Neural Machine Translation","created":"2017-11-07","cited_by_count":463},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"1704.03155","title":"EAST: An Efficient and Accurate Scene Text Detector","created":"2017-04-11","cited_by_count":248},{"id":"1507.02672","title":"Semi-Supervised Learning with Ladder Networks","created":"2015-07-09","cited_by_count":247},{"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":"2003.12294","title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","created":"2020-03-27","cited_by_count":131},{"id":"1811.00751","title":"Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition","created":"2018-11-02","cited_by_count":130},{"id":"1412.1842","title":"Reading Text in the Wild with Convolutional Neural Networks","created":"2014-12-04","cited_by_count":122},{"id":"1603.03915","title":"Robust Scene Text Recognition with Automatic Rectification","created":"2016-03-12","cited_by_count":121},{"id":"2005.10977","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2020-05-22","cited_by_count":119},{"id":"1709.02054","title":"Focusing Attention: Towards Accurate Text Recognition in Natural Images","created":"2017-09-07","cited_by_count":110},{"id":"2006.11476","title":"Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning","created":"2020-06-20","cited_by_count":103},{"id":"1912.10205","title":"Decoupled Attention Network for Text Recognition","created":"2019-12-21","cited_by_count":102},{"id":"1609.03605","title":"Detecting Text in Natural Image with Connectionist Text Proposal Network","created":"2016-09-12","cited_by_count":85},{"id":"2007.07542","title":"RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition","created":"2020-07-15","cited_by_count":85},{"id":"2001.00294","title":"Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning","created":"2020-01-02","cited_by_count":81},{"id":"1812.05824","title":"ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification","created":"2018-12-14","cited_by_count":79},{"id":"1603.03101","title":"Recursive Recurrent Nets with Attention Modeling for OCR in the Wild","created":"2016-03-09","cited_by_count":74},{"id":"2003.11288","title":"SCATTER: Selective Context Attentional Scene Text Recognizer","created":"2020-03-25","cited_by_count":69},{"id":"1912.12422","title":"TextScanner: Reading Characters in Order for Robust Scene Text Recognition","created":"2019-12-28","cited_by_count":68},{"id":"2002.08926","title":"Imputer: Sequence Modelling via Imputation and Dynamic Programming","created":"2020-02-20","cited_by_count":66},{"id":"2005.03341","title":"Scene Text Image Super-Resolution in the Wild","created":"2020-05-07","cited_by_count":63},{"id":"1809.06508","title":"Scene Text Recognition from Two-Dimensional Perspective","created":"2018-09-18","cited_by_count":57},{"id":"1902.10245","title":"Non-Autoregressive Machine Translation with Auxiliary Regularization","created":"2019-02-22","cited_by_count":52},{"id":"2002.01276","title":"GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition","created":"2020-02-04","cited_by_count":52},{"id":"1908.01957","title":"Symmetry-constrained Rectification Network for Scene Text Recognition","created":"2019-08-06","cited_by_count":45},{"id":"1506.04395","title":"Reading Scene Text in Deep Convolutional Sequences","created":"2015-06-14","cited_by_count":44},{"id":"2010.14233","title":"Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment","created":"2020-10-24","cited_by_count":37},{"id":"2003.06606","title":"Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition","created":"2020-03-14","cited_by_count":36},{"id":"2107.01787","title":"Multi-View Correlation Distillation for Incremental Object Detection","created":"2021-07-05","cited_by_count":36},{"id":"2005.04690","title":"Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning","created":"2020-05-10","cited_by_count":29},{"id":"2007.07986","title":"Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer","created":"2020-07-15","cited_by_count":28},{"id":"2005.07903","title":"Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition","created":"2020-05-16","cited_by_count":24},{"id":"1904.08364","title":"Aggregation Cross-Entropy for Sequence Recognition","created":"2019-04-17","cited_by_count":22},{"id":"2005.13117","title":"SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition","created":"2020-05-27","cited_by_count":13},{"id":"1712.05404","title":"SEE: Towards Semi-Supervised End-to-End Scene Text Recognition","created":"2017-12-14","cited_by_count":12},{"id":"1908.09990","title":"Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning","created":"2019-08-27","cited_by_count":11},{"id":"2005.11487","title":"Self-Training for Domain Adaptive Scene Text Detection","created":"2020-05-23","cited_by_count":11},{"id":"2008.02711","title":"Exploring Relations in Untrimmed Videos for Self-Supervised Learning","created":"2020-08-06","cited_by_count":11},{"id":"2010.09169","title":"Gaussian Constrained Attention Network for Scene Text Recognition","created":"2020-10-19","cited_by_count":11},{"id":"2007.05113","title":"FC2RN: A Fully Convolutional Corner Refinement Network for Accurate Multi-Oriented Scene Text Detection","created":"2020-07-10","cited_by_count":10},{"id":"2007.02577","title":"Progressive Cluster Purification for Unsupervised Feature Learning","created":"2020-07-06","cited_by_count":8},{"id":"2009.07447","title":"Exploring Font-independent Features for Scene Text Recognition","created":"2020-09-16","cited_by_count":8},{"id":"1912.03656","title":"Bidirectional Scene Text Recognition with a Single Decoder","created":"2019-12-08","cited_by_count":7},{"id":"2007.13428","title":"Two-Level Residual Distillation based Triple Network for Incremental Object Detection","created":"2020-07-27","cited_by_count":7},{"id":"2007.06240","title":"Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification","created":"2020-07-13","cited_by_count":6},{"id":"2103.04009","title":"Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection","created":"2021-03-06","cited_by_count":5},{"id":"2107.00808","title":"MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification","created":"2021-07-02","cited_by_count":5},{"id":"2107.03578","title":"Video 3D Sampling for Self-supervised Representation Learning","created":"2021-07-08","cited_by_count":5},{"id":"2105.03341","title":"Exploring Instance Relations for Unsupervised Feature Embedding","created":"2021-05-07","cited_by_count":4}],"next_cursor":null}