{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"2104.06490","title":"DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort","created":"2021-04-13","cited_by_count":264},{"id":"1911.12861","title":"SEAN: Image Synthesis with Semantic Region-Adaptive Normalization","created":"2019-11-28","cited_by_count":253},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"2001.08248","title":"How Much Position Information Do Convolutional Neural Networks Encode?","created":"2020-01-22","cited_by_count":172},{"id":"2003.07064","title":"On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location","created":"2020-03-16","cited_by_count":142},{"id":"2003.06473","title":"Self-supervised Single-view 3D Reconstruction via Semantic Consistency","created":"2020-03-13","cited_by_count":127},{"id":"1806.07823","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","created":"2018-06-20","cited_by_count":114},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"1905.01298","title":"SCOPS: Self-Supervised Co-Part Segmentation","created":"2019-05-03","cited_by_count":100},{"id":"1906.07889","title":"Unsupervised Learning of Object Structure and Dynamics from Videos","created":"2019-06-19","cited_by_count":92},{"id":"1807.03146","title":"Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning","created":"2018-07-05","cited_by_count":79},{"id":"2005.10411","title":"Interpretable and Accurate Fine-grained Recognition via Region Grouping","created":"2020-05-21","cited_by_count":75},{"id":"1905.13539","title":"Unsupervised Object Segmentation by Redrawing","created":"2019-05-27","cited_by_count":74},{"id":"1804.01110","title":"Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation","created":"2018-04-03","cited_by_count":73},{"id":"1804.04412","title":"Unsupervised Discovery of Object Landmarks as Structural Representations","created":"2018-04-12","cited_by_count":73},{"id":"1901.03360","title":"Unsupervised Moving Object Detection via Contextual Information Separation","created":"2019-01-10","cited_by_count":72},{"id":"2012.05217","title":"Positional Encoding as Spatial Inductive Bias in GANs","created":"2020-12-09","cited_by_count":69},{"id":"1903.06946","title":"Unsupervised Part-Based Disentangling of Object Shape and Appearance","created":"2019-03-16","cited_by_count":67},{"id":"1705.02193","title":"Unsupervised learning of object landmarks by factorized spatial embeddings","created":"2017-05-05","cited_by_count":64},{"id":"1806.10206","title":"Deep Feature Factorization For Concept Discovery","created":"2018-06-26","cited_by_count":64},{"id":"1811.11155","title":"FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery","created":"2018-11-27","cited_by_count":58},{"id":"1905.12663","title":"Emergence of Object Segmentation in Perturbed Generative Models","created":"2019-05-29","cited_by_count":57},{"id":"2006.04988","title":"Object Segmentation Without Labels with Large-Scale Generative Models","created":"2020-06-08","cited_by_count":52},{"id":"1807.00966","title":"Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors","created":"2018-07-03","cited_by_count":49},{"id":"2010.02178","title":"Mind the Pad -- CNNs can Develop Blind Spots","created":"2020-10-05","cited_by_count":41},{"id":"1904.09571","title":"TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation","created":"2019-04-21","cited_by_count":40},{"id":"1910.02027","title":"Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction","created":"2019-10-04","cited_by_count":36},{"id":"2105.12405","title":"Unsupervised Part Segmentation through Disentangling Appearance and Shape","created":"2021-05-26","cited_by_count":29},{"id":"2004.03234","title":"Motion-supervised Co-Part Segmentation","created":"2020-04-07","cited_by_count":28},{"id":"2012.07287","title":"Information-Theoretic Segmentation by Inpainting Error Maximization","created":"2020-12-14","cited_by_count":22},{"id":"1903.05684","title":"Neural Scene Decomposition for Multi-Person Motion Capture","created":"2019-03-13","cited_by_count":21},{"id":"2106.05897","title":"Unsupervised Co-part Segmentation through Assembly","created":"2021-06-10","cited_by_count":12},{"id":"2004.03623","title":"PatchVAE: Learning Local Latent Codes for Recognition","created":"2020-04-07","cited_by_count":10},{"id":"2005.03463","title":"How Can CNNs Use Image Position for Segmentation?","created":"2020-05-07","cited_by_count":8},{"id":"2007.01053","title":"Unsupervised Landmark Learning from Unpaired Data","created":"2020-06-29","cited_by_count":7},{"id":"2012.05119","title":"Human Detection and Segmentation via Multi-view Consensus","created":"2020-12-09","cited_by_count":2}],"next_cursor":null}