{"list":"other","total":54,"rows":[{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1704.03976","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","created":"2017-04-13","cited_by_count":920},{"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":"1703.01780","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","created":"2017-03-06","cited_by_count":472},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"1905.03670","title":"S4L: Self-Supervised Semi-Supervised Learning","created":"2019-05-09","cited_by_count":335},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"1601.07140","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","created":"2016-01-26","cited_by_count":236},{"id":"1406.2227","title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","created":"2014-06-09","cited_by_count":214},{"id":"1708.07120","title":"Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates","created":"2017-08-23","cited_by_count":199},{"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":"1908.08207","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","created":"2019-08-22","cited_by_count":171},{"id":"2002.10200","title":"ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network","created":"2020-02-24","cited_by_count":170},{"id":"1909.07145","title":"ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)","created":"2019-09-16","cited_by_count":147},{"id":"1907.00945","title":"ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019","created":"2019-07-01","cited_by_count":139},{"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":"1912.09641","title":"ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard","created":"2019-12-20","cited_by_count":128},{"id":"1909.07741","title":"ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT","created":"2019-09-17","cited_by_count":122},{"id":"1603.03915","title":"Robust Scene Text Recognition with Automatic Rectification","created":"2016-03-12","cited_by_count":121},{"id":"1611.06779","title":"TextBoxes: A Fast Text Detector with a Single Deep Neural Network","created":"2016-11-21","cited_by_count":119},{"id":"1801.02765","title":"TextBoxes++: A Single-Shot Oriented Scene Text Detector","created":"2018-01-09","cited_by_count":119},{"id":"2005.10977","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2020-05-22","cited_by_count":119},{"id":"1708.09585","title":"ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)","created":"2017-08-31","cited_by_count":105},{"id":"1912.10205","title":"Decoupled Attention Network for Text Recognition","created":"2019-12-21","cited_by_count":102},{"id":"2007.07542","title":"RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition","created":"2020-07-15","cited_by_count":85},{"id":"1812.05824","title":"ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification","created":"2018-12-14","cited_by_count":79},{"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":"2005.03341","title":"Scene Text Image Super-Resolution in the Wild","created":"2020-05-07","cited_by_count":63},{"id":"1903.02271","title":"High-Fidelity Image Generation With Fewer Labels","created":"2019-03-06","cited_by_count":52},{"id":"2003.10608","title":"UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World","created":"2020-03-24","cited_by_count":43},{"id":"1906.02371","title":"Omnidirectional Scene Text Detection with Sequential-free Box Discretization","created":"2019-06-06","cited_by_count":26},{"id":"1909.07808","title":"Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning","created":"2019-09-17","cited_by_count":20},{"id":"2007.00799","title":"Learning Surrogates via Deep Embedding","created":"2020-07-01","cited_by_count":11},{"id":"2007.03098","title":"Text Recognition -- Real World Data and Where to Find Them","created":"2020-07-06","cited_by_count":5},{"id":"1912.04561","title":"A Feasible Framework for Arbitrary-Shaped Scene Text Recognition","created":"2019-12-10","cited_by_count":3},{"id":"1912.09629","title":"Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection","created":"2019-12-20","cited_by_count":3},{"id":"1601.03128","title":"Enhancing Energy Minimization Framework for Scene Text Recognition with Top-Down Cues","created":"2016-01-13","cited_by_count":2},{"id":"1611.02788","title":"Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data","created":"2016-11-09","cited_by_count":1},{"id":"1707.06810","title":"Text Recognition in Scene Image and Video Frame using Color Channel Selection","created":"2017-07-21","cited_by_count":1}],"next_cursor":null}