{"list":"other","total":57,"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"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":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"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":"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":"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":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149},{"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":"1911.08670","title":"MMTM: Multimodal Transfer Module for CNN Fusion","created":"2019-11-20","cited_by_count":129},{"id":"1912.09641","title":"ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard","created":"2019-12-20","cited_by_count":128},{"id":"2005.10977","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2020-05-22","cited_by_count":119},{"id":"2007.09482","title":"Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting","created":"2020-07-18","cited_by_count":114},{"id":"2101.00529","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","created":"2021-01-02","cited_by_count":110},{"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":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97},{"id":"2105.03620","title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","created":"2021-05-08","cited_by_count":84},{"id":"2105.08582","title":"Vision Transformer for Fast and Efficient Scene Text Recognition","created":"2021-05-18","cited_by_count":81},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72},{"id":"2012.10873","title":"Sequence-to-Sequence Contrastive Learning for Text Recognition","created":"2020-12-20","cited_by_count":70},{"id":"2203.10209","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","created":"2022-03-19","cited_by_count":70},{"id":"2003.11288","title":"SCATTER: Selective Context Attentional Scene Text Recognizer","created":"2020-03-25","cited_by_count":69},{"id":"2110.01518","title":"Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics","created":"2021-10-04","cited_by_count":67},{"id":"2103.04400","title":"What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels","created":"2021-03-07","cited_by_count":63},{"id":"2012.04350","title":"MANGO: A Mask Attention Guided One-Stage Scene Text Spotter","created":"2020-12-08","cited_by_count":51},{"id":"2202.05508","title":"Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer","created":"2022-02-11","cited_by_count":41},{"id":"2005.03959","title":"On Vocabulary Reliance in Scene Text Recognition","created":"2020-05-08","cited_by_count":39},{"id":"2111.15263","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","created":"2021-11-30","cited_by_count":34},{"id":"2206.00311","title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining","created":"2022-06-01","cited_by_count":34},{"id":"2208.03364","title":"GLASS: Global to Local Attention for Scene-Text Spotting","created":"2022-08-05","cited_by_count":34},{"id":"2203.03911","title":"Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting","created":"2022-03-08","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":"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":"2205.03873","title":"Multimodal Semi-Supervised Learning for Text Recognition","created":"2022-05-08","cited_by_count":16},{"id":"2107.12081","title":"Towards the Unseen: Iterative Text Recognition by Distilling from Errors","created":"2021-07-26","cited_by_count":12},{"id":"2209.06717","title":"Out-of-Vocabulary Challenge Report","created":"2022-09-14","cited_by_count":11},{"id":"2012.12643","title":"On Calibration of Scene-Text Recognition Models","created":"2020-12-23","cited_by_count":9},{"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}