{"list":"other","total":85,"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"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":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"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":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2107.02791","title":"Depth-supervised NeRF: Fewer Views and Faster Training for Free","created":"2021-07-06","cited_by_count":735},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"2112.03288","title":"Dense Depth Priors for Neural Radiance Fields from Sparse Input Views","created":"2021-12-06","cited_by_count":302},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"1612.02649","title":"FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation","created":"2016-12-08","cited_by_count":243},{"id":"1907.12209","title":"Enforcing geometric constraints of virtual normal for depth prediction","created":"2019-07-29","cited_by_count":234},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"2003.01060","title":"D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry","created":"2020-03-02","cited_by_count":206},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"2001.08248","title":"How Much Position Information Do Convolutional Neural Networks Encode?","created":"2020-01-22","cited_by_count":172},{"id":"1803.03893","title":"Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction","created":"2018-03-11","cited_by_count":159},{"id":"2208.03543","title":"MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer","created":"2022-08-06","cited_by_count":136},{"id":"2203.14211","title":"DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation","created":"2022-03-27","cited_by_count":118},{"id":"2004.02307","title":"EfficientPS: Efficient Panoptic Segmentation","created":"2020-04-05","cited_by_count":111},{"id":"2001.03182","title":"CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency","created":"2020-01-09","cited_by_count":107},{"id":"1411.6387","title":"Deep Convolutional Neural Fields for Depth Estimation from a Single Image","created":"2014-11-24","cited_by_count":106},{"id":"1709.06841","title":"UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning","created":"2017-09-20","cited_by_count":95},{"id":"2210.09071","title":"Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention","created":"2022-10-17","cited_by_count":93},{"id":"1807.02570","title":"Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry","created":"2018-07-06","cited_by_count":85},{"id":"1905.07005","title":"How do neural networks see depth in single images?","created":"2019-05-16","cited_by_count":82},{"id":"2204.00822","title":"Semantic-Aware Domain Generalized Segmentation","created":"2022-04-02","cited_by_count":79},{"id":"1904.02028","title":"CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth","created":"2019-04-03","cited_by_count":75},{"id":"1904.11112","title":"Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes","created":"2019-04-25","cited_by_count":73},{"id":"2304.06334","title":"iDisc: Internal Discretization for Monocular Depth Estimation","created":"2023-04-13","cited_by_count":73},{"id":"1808.01454","title":"T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks","created":"2018-08-04","cited_by_count":70},{"id":"2110.09482","title":"Self-Supervised Monocular Depth Estimation with Internal Feature Fusion","created":"2021-10-18","cited_by_count":67},{"id":"2207.05501","title":"Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios","created":"2022-07-12","cited_by_count":65},{"id":"1904.01870","title":"Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation","created":"2019-04-03","cited_by_count":61},{"id":"2002.00569","title":"DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data","created":"2020-02-03","cited_by_count":61},{"id":"1803.01599","title":"AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation","created":"2018-03-05","cited_by_count":54},{"id":"2109.12484","title":"Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation","created":"2021-09-26","cited_by_count":48},{"id":"2011.00320","title":"Scene Flow from Point Clouds with or without Learning","created":"2020-10-31","cited_by_count":44},{"id":"2207.11984","title":"RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation","created":"2022-07-25","cited_by_count":36},{"id":"2105.07830","title":"Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation","created":"2021-05-17","cited_by_count":32},{"id":"2210.01612","title":"PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes","created":"2022-10-04","cited_by_count":32},{"id":"1906.11435","title":"DeepVIO: Self-supervised Deep Learning of Monocular Visual Inertial Odometry using 3D Geometric Constraints","created":"2019-06-27","cited_by_count":27},{"id":"1803.10039","title":"Learning Depth from Single Images with Deep Neural Network Embedding Focal Length","created":"2018-03-27","cited_by_count":25},{"id":"2006.04026","title":"SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation","created":"2020-06-07","cited_by_count":25},{"id":"2009.01579","title":"DESC: Domain Adaptation for Depth Estimation via Semantic Consistency","created":"2020-09-03","cited_by_count":25},{"id":"2103.12209","title":"Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision","created":"2021-03-22","cited_by_count":24},{"id":"2212.09068","title":"Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization","created":"2022-12-18","cited_by_count":22},{"id":"2007.14511","title":"$S^3$Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data","created":"2020-07-28","cited_by_count":12},{"id":"2106.02594","title":"Self-Supervised Learning of Domain Invariant Features for Depth Estimation","created":"2021-06-04","cited_by_count":9},{"id":"2109.03462","title":"Recalibrating the KITTI Dataset Camera Setup for Improved Odometry Accuracy","created":"2021-09-08","cited_by_count":9},{"id":"2208.00160","title":"Learning Feature Decomposition for Domain Adaptive Monocular Depth Estimation","created":"2022-07-30","cited_by_count":9}],"next_cursor":null}