{"list":"other","total":51,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"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":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279},{"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":"1911.08947","title":"Real-time Scene Text Detection with Differentiable Binarization","created":"2019-11-20","cited_by_count":214},{"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":"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":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171},{"id":"1909.07145","title":"ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)","created":"2019-09-16","cited_by_count":147},{"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":"1412.1842","title":"Reading Text in the Wild with Convolutional Neural Networks","created":"2014-12-04","cited_by_count":122},{"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":"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":"2108.09661","title":"From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network","created":"2021-08-22","cited_by_count":97},{"id":"2012.04638","title":"TAP: Text-Aware Pre-training for Text-VQA and Text-Caption","created":"2020-12-08","cited_by_count":95},{"id":"2012.10873","title":"Sequence-to-Sequence Contrastive Learning for Text Recognition","created":"2020-12-20","cited_by_count":70},{"id":"1912.12422","title":"TextScanner: Reading Characters in Order for Robust Scene Text Recognition","created":"2019-12-28","cited_by_count":68},{"id":"1809.06508","title":"Scene Text Recognition from Two-Dimensional Perspective","created":"2018-09-18","cited_by_count":57},{"id":"2112.15093","title":"Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study","created":"2021-12-30","cited_by_count":53},{"id":"2111.10023","title":"UFO: A UniFied TransfOrmer for Vision-Language Representation Learning","created":"2021-11-19","cited_by_count":46},{"id":"2109.04145","title":"PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition","created":"2021-09-09","cited_by_count":41},{"id":"1906.05708","title":"2D Attentional Irregular Scene Text Recognizer","created":"2019-06-13","cited_by_count":18},{"id":"2204.13867","title":"Vision-Language Pre-Training for Boosting Scene Text Detectors","created":"2022-04-29","cited_by_count":18},{"id":"2204.07714","title":"Pushing the Performance Limit of Scene Text Recognizer without Human Annotation","created":"2022-04-16","cited_by_count":7}],"next_cursor":null}