{"list":"other","total":56,"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":"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1809.00219","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","created":"2018-09-01","cited_by_count":1254},{"id":"1501.00092","title":"Image Super-Resolution Using Deep Convolutional Networks","created":"2014-12-31","cited_by_count":1224},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"1802.08797","title":"Residual Dense Network for Image Super-Resolution","created":"2018-02-24","cited_by_count":799},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"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":"1704.03915","title":"Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution","created":"2017-04-12","cited_by_count":453},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"1904.00523","title":"Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model","created":"2019-04-01","cited_by_count":403},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"2303.14389","title":"MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer","created":"2023-03-25","cited_by_count":262},{"id":"2303.09472","title":"DiffIR: Efficient Diffusion Model for Image Restoration","created":"2023-03-16","cited_by_count":255},{"id":"2112.02475","title":"Deblurring via Stochastic Refinement","created":"2021-12-05","cited_by_count":249},{"id":"1612.01697","title":"Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment","created":"2016-12-06","cited_by_count":225},{"id":"2303.16491","title":"Implicit Diffusion Models for Continuous Super-Resolution","created":"2023-03-29","cited_by_count":218},{"id":"2304.01247","title":"Generative Diffusion Prior for Unified Image Restoration and Enhancement","created":"2023-04-03","cited_by_count":199},{"id":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149},{"id":"2204.04627","title":"Stripformer: Strip Transformer for Fast Image Deblurring","created":"2022-04-10","cited_by_count":140},{"id":"2003.12294","title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","created":"2020-03-27","cited_by_count":131},{"id":"1905.05169","title":"Zoom To Learn, Learn To Zoom","created":"2019-05-13","cited_by_count":115},{"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":"2212.01789","title":"Multiscale Structure Guided Diffusion for Image Deblurring","created":"2022-12-04","cited_by_count":77},{"id":"2005.03341","title":"Scene Text Image Super-Resolution in the Wild","created":"2020-05-07","cited_by_count":63},{"id":"1702.00783","title":"Pixel Recursive Super Resolution","created":"2017-02-02","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":"2106.15368","title":"Text Prior Guided Scene Text Image Super-resolution","created":"2021-06-29","cited_by_count":37},{"id":"2305.03892","title":"DocDiff: Document Enhancement via Residual Diffusion Models","created":"2023-05-06","cited_by_count":37},{"id":"2203.09388","title":"A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution","created":"2022-03-17","cited_by_count":35},{"id":"1901.03003","title":"A Multi-Object Rectified Attention Network for Scene Text Recognition","created":"2019-01-10","cited_by_count":30},{"id":"2112.08171","title":"Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution","created":"2021-12-13","cited_by_count":28},{"id":"2204.14044","title":"C3-STISR: Scene Text Image Super-resolution with Triple Clues","created":"2022-04-29","cited_by_count":26},{"id":"2005.09496","title":"RoadText-1K: Text Detection & Recognition Dataset for Driving Videos","created":"2020-05-19","cited_by_count":25},{"id":"2307.08996","title":"Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond","created":"2023-07-18","cited_by_count":18},{"id":"2302.10414","title":"Improving Scene Text Image Super-resolution via Dual Prior Modulation Network","created":"2023-02-21","cited_by_count":15},{"id":"2311.09759","title":"Scene Text Image Super-resolution based on Text-conditional Diffusion Models","created":"2023-11-16","cited_by_count":15},{"id":"2206.07662","title":"SP-ViT: Learning 2D Spatial Priors for Vision Transformers","created":"2022-06-15","cited_by_count":12},{"id":"2308.06743","title":"TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolution","created":"2023-08-13","cited_by_count":10},{"id":"2307.09749","title":"Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement","created":"2023-07-19","cited_by_count":8},{"id":"2309.08919","title":"Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution","created":"2023-09-16","cited_by_count":5}],"next_cursor":null}