{"list":"other","total":80,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2208.09392","title":"Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise","created":"2022-08-19","cited_by_count":276},{"id":"1701.02096","title":"Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis","created":"2017-01-09","cited_by_count":215},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"2005.10821","title":"Hierarchical Multi-Scale Attention for Semantic Segmentation","created":"2020-05-21","cited_by_count":183},{"id":"1901.03784","title":"UPSNet: A Unified Panoptic Segmentation Network","created":"2019-01-12","cited_by_count":175},{"id":"2007.06936","title":"Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance","created":"2020-07-14","cited_by_count":148},{"id":"2002.12319","title":"Semantically-Guided Representation Learning for Self-Supervised Monocular Depth","created":"2020-02-27","cited_by_count":134},{"id":"2109.09881","title":"Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation","created":"2021-09-20","cited_by_count":116},{"id":"2103.05445","title":"Pixel-wise Anomaly Detection in Complex Driving Scenes","created":"2021-03-09","cited_by_count":109},{"id":"1910.06809","title":"Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis","created":"2019-10-15","cited_by_count":108},{"id":"2003.08823","title":"Conditional Gaussian Distribution Learning for Open Set Recognition","created":"2020-03-19","cited_by_count":104},{"id":"2001.02613","title":"Don't Forget The Past: Recurrent Depth Estimation from Monocular Video","created":"2020-01-08","cited_by_count":71},{"id":"2104.02745","title":"InverseForm: A Loss Function for Structured Boundary-Aware Segmentation","created":"2021-04-06","cited_by_count":65},{"id":"2003.04614","title":"Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation","created":"2020-03-10","cited_by_count":62},{"id":"1807.10201","title":"A Style-Aware Content Loss for Real-time HD Style Transfer","created":"2018-07-26","cited_by_count":58},{"id":"1711.08506","title":"W-Net: A Deep Model for Fully Unsupervised Image Segmentation","created":"2017-11-22","cited_by_count":57},{"id":"2111.14893","title":"Learning Multiple Dense Prediction Tasks from Partially Annotated Data","created":"2021-11-29","cited_by_count":42},{"id":"1902.02767","title":"Hybrid Models with Deep and Invertible Features","created":"2019-02-07","cited_by_count":41},{"id":"2210.06778","title":"X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentation","created":"2022-10-13","cited_by_count":38},{"id":"1904.05404","title":"Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres","created":"2019-04-10","cited_by_count":37},{"id":"2012.06980","title":"GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation","created":"2020-12-13","cited_by_count":36},{"id":"1808.00529","title":"Open Category Detection with PAC Guarantees","created":"2018-08-01","cited_by_count":35},{"id":"2007.09264","title":"Surface Normal Estimation of Tilted Images via Spatial Rectifier","created":"2020-07-17","cited_by_count":34},{"id":"2108.07682","title":"Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision","created":"2021-08-17","cited_by_count":31},{"id":"2110.12369","title":"AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation","created":"2021-10-24","cited_by_count":31},{"id":"2211.09807","title":"Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information","created":"2022-11-17","cited_by_count":31},{"id":"1606.06582","title":"Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification","created":"2016-06-21","cited_by_count":18},{"id":"2110.12385","title":"Perceptual Consistency in Video Segmentation","created":"2021-10-24","cited_by_count":12},{"id":"2110.12516","title":"X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation","created":"2021-10-24","cited_by_count":12},{"id":"2111.02333","title":"HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation","created":"2021-11-03","cited_by_count":12},{"id":"2003.01360","title":"DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular Videos","created":"2020-03-03","cited_by_count":10},{"id":"2204.05370","title":"Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentation","created":"2022-04-11","cited_by_count":9},{"id":"2209.11350","title":"Oracle Analysis of Representations for Deep Open Set Detection","created":"2022-09-22","cited_by_count":3}],"next_cursor":null}