{"list":"other","total":57,"rows":[{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1912.11035","title":"CNN-generated images are surprisingly easy to spot... for now","created":"2019-12-23","cited_by_count":847},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"1806.03589","title":"Free-Form Image Inpainting with Gated Convolution","created":"2018-06-10","cited_by_count":594},{"id":"1801.07892","title":"Generative Image Inpainting with Contextual Attention","created":"2018-01-24","cited_by_count":580},{"id":"2007.09355","title":"Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues","created":"2020-07-18","cited_by_count":523},{"id":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"2108.05054","title":"Rethinking Coarse-to-Fine Approach in Single Image Deblurring","created":"2021-08-11","cited_by_count":326},{"id":"2003.06792","title":"Learning Enriched Features for Real Image Restoration and Enhancement","created":"2020-03-15","cited_by_count":312},{"id":"1606.02147","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","created":"2016-06-07","cited_by_count":291},{"id":"2103.01856","title":"Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain","created":"2021-03-02","cited_by_count":244},{"id":"2003.07761","title":"CycleISP: Real Image Restoration via Improved Data Synthesis","created":"2020-03-17","cited_by_count":213},{"id":"2002.12416","title":"Learning in the Frequency Domain","created":"2020-02-27","cited_by_count":198},{"id":"2004.03333","title":"Binary Neural Networks: A Survey","created":"2020-03-31","cited_by_count":190},{"id":"1805.04953","title":"Learning Rich Features for Image Manipulation Detection","created":"2018-05-13","cited_by_count":154},{"id":"1904.05049","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","created":"2019-04-10","cited_by_count":140},{"id":"1911.06465","title":"Fourier Spectrum Discrepancies in Deep Network Generated Images","created":"2019-11-15","cited_by_count":139},{"id":"2103.09096","title":"Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection","created":"2021-03-16","cited_by_count":134},{"id":"1905.05169","title":"Zoom To Learn, Learn To Zoom","created":"2019-05-13","cited_by_count":115},{"id":"2104.06832","title":"Image Manipulation Detection by Multi-View Multi-Scale Supervision","created":"2021-04-14","cited_by_count":111},{"id":"2103.15061","title":"Invertible Image Signal Processing","created":"2021-03-28","cited_by_count":94},{"id":"2009.00726","title":"SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization","created":"2020-09-01","cited_by_count":92},{"id":"1801.06724","title":"DeepISP: Towards Learning an End-to-End Image Processing Pipeline","created":"2018-01-20","cited_by_count":88},{"id":"2203.00867","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","created":"2022-03-02","cited_by_count":83},{"id":"2108.12947","title":"Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization","created":"2021-08-30","cited_by_count":78},{"id":"2103.17195","title":"A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection","created":"2021-03-31","cited_by_count":68},{"id":"1709.02016","title":"Image Splicing Localization Using A Multi-Task Fully Convolutional Network (MFCN)","created":"2017-09-06","cited_by_count":64},{"id":"1905.02423","title":"LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation","created":"2019-05-07","cited_by_count":50},{"id":"2009.09869","title":"FakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance Tracking","created":"2020-09-21","cited_by_count":46},{"id":"1908.01481","title":"CameraNet: A Two-Stage Framework for Effective Camera ISP Learning","created":"2019-08-05","cited_by_count":38},{"id":"2203.15880","title":"Proactive Image Manipulation Detection","created":"2022-03-29","cited_by_count":35},{"id":"2110.14196","title":"From Image to Imuge: Immunized Image Generation","created":"2021-10-27","cited_by_count":11},{"id":"2106.00660","title":"Markpainting: Adversarial Machine Learning meets Inpainting","created":"2021-06-01","cited_by_count":9},{"id":"2112.09219","title":"All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelines","created":"2021-12-16","cited_by_count":5}],"next_cursor":null}