{"list":"other","total":84,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"2102.05379","title":"Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions","created":"2021-02-10","cited_by_count":574},{"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":"1711.02281","title":"Non-Autoregressive Neural Machine Translation","created":"2017-11-07","cited_by_count":463},{"id":"2210.08933","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","created":"2022-10-17","cited_by_count":450},{"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":"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":"2211.15029","title":"DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models","created":"2022-11-28","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":"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":"2212.14704","title":"Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models","created":"2022-12-28","cited_by_count":151},{"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":"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":"2206.05564","title":"gDDIM: Generalized denoising diffusion implicit models","created":"2022-06-11","cited_by_count":125},{"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":"2108.08827","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","created":"2021-08-19","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":"1708.09585","title":"ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)","created":"2017-08-31","cited_by_count":105},{"id":"2008.07905","title":"Glancing Transformer for Non-Autoregressive Neural Machine Translation","created":"2020-08-18","cited_by_count":103},{"id":"1912.10205","title":"Decoupled Attention Network for Text Recognition","created":"2019-12-21","cited_by_count":102},{"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":"2205.00159","title":"SVTR: Scene Text Recognition with a Single Visual Model","created":"2022-04-30","cited_by_count":88},{"id":"2007.07542","title":"RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition","created":"2020-07-15","cited_by_count":85},{"id":"2105.08582","title":"Vision Transformer for Fast and Efficient Scene Text Recognition","created":"2021-05-18","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":"1910.02562","title":"MASTER: Multi-Aspect Non-local Network for Scene Text Recognition","created":"2019-10-07","cited_by_count":65},{"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":"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":"2208.00438","title":"Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition","created":"2022-07-31","cited_by_count":45},{"id":"2307.08723","title":"Revisiting Scene Text Recognition: A Data Perspective","created":"2023-07-17","cited_by_count":45},{"id":"1506.04395","title":"Reading Scene Text in Deep Convolutional Sequences","created":"2015-06-14","cited_by_count":44},{"id":"2109.04145","title":"PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition","created":"2021-09-09","cited_by_count":41},{"id":"2010.14233","title":"Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment","created":"2020-10-24","cited_by_count":37},{"id":"2209.03592","title":"Multi-Granularity Prediction for Scene Text Recognition","created":"2022-09-08","cited_by_count":36},{"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":"1901.03003","title":"A Multi-Object Rectified Attention Network for Scene Text Recognition","created":"2019-01-10","cited_by_count":30},{"id":"2005.04690","title":"Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning","created":"2020-05-10","cited_by_count":29},{"id":"2110.12826","title":"TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation","created":"2021-10-25","cited_by_count":26},{"id":"2005.07903","title":"Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition","created":"2020-05-16","cited_by_count":24},{"id":"2209.03594","title":"Levenshtein OCR","created":"2022-09-08","cited_by_count":24},{"id":"2211.11694","title":"Exploring Discrete Diffusion Models for Image Captioning","created":"2022-11-21","cited_by_count":16},{"id":"2010.09169","title":"Gaussian Constrained Attention Network for Scene Text Recognition","created":"2020-10-19","cited_by_count":11},{"id":"2207.10256","title":"SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition","created":"2022-07-21","cited_by_count":10},{"id":"2211.04963","title":"Pure Transformer with Integrated Experts for Scene Text Recognition","created":"2022-11-09","cited_by_count":9},{"id":"2305.16172","title":"Masked and Permuted Implicit Context Learning for Scene Text Recognition","created":"2023-05-25","cited_by_count":4}],"next_cursor":null}