{"list":"other","total":101,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"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":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1504.06375","title":"Holistically-Nested Edge Detection","created":"2015-04-24","cited_by_count":592},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"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":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"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":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"id":"1907.10326","title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","created":"2019-07-24","cited_by_count":382},{"id":"1505.04366","title":"Learning Deconvolution Network for Semantic Segmentation","created":"2015-05-17","cited_by_count":365},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"1803.08904","title":"Context Encoding for Semantic Segmentation","created":"2018-03-23","cited_by_count":290},{"id":"1901.02985","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","created":"2019-01-10","cited_by_count":260},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"id":"2101.11939","title":"Exploring Cross-Image Pixel Contrast for Semantic Segmentation","created":"2021-01-28","cited_by_count":242},{"id":"1503.01640","title":"BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation","created":"2015-03-05","cited_by_count":238},{"id":"1907.12209","title":"Enforcing geometric constraints of virtual normal for depth prediction","created":"2019-07-29","cited_by_count":234},{"id":"1805.04409","title":"PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing","created":"2018-05-11","cited_by_count":224},{"id":"1805.09806","title":"Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation","created":"2018-05-24","cited_by_count":222},{"id":"1502.03240","title":"Conditional Random Fields as Recurrent Neural Networks","created":"2015-02-11","cited_by_count":214},{"id":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"1511.03339","title":"Attention to Scale: Scale-aware Semantic Image Segmentation","created":"2015-11-10","cited_by_count":169},{"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":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"1805.10180","title":"Pyramid Attention Network for Semantic Segmentation","created":"2018-05-25","cited_by_count":149},{"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":"1906.03525","title":"Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation","created":"2019-06-08","cited_by_count":142},{"id":"1809.00916","title":"OCNet: Object Context Network for Scene Parsing","created":"2018-09-04","cited_by_count":140},{"id":"2007.10603","title":"Feature-metric Loss for Self-supervised Learning of Depth and Egomotion","created":"2020-07-21","cited_by_count":140},{"id":"1811.12814","title":"Graph-Based Global Reasoning Networks","created":"2018-11-30","cited_by_count":120},{"id":"1708.01471","title":"Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering","created":"2017-08-04","cited_by_count":117},{"id":"2003.13951","title":"Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume","created":"2020-03-31","cited_by_count":116},{"id":"1411.6387","title":"Deep Convolutional Neural Fields for Depth Estimation from a Single Image","created":"2014-11-24","cited_by_count":106},{"id":"1904.06807","title":"Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation","created":"2019-04-15","cited_by_count":97},{"id":"1702.00887","title":"Structured Attention Networks","created":"2017-02-03","cited_by_count":95},{"id":"2004.02760","title":"Guiding Monocular Depth Estimation Using Depth-Attention Volume","created":"2020-04-06","cited_by_count":82},{"id":"2007.09278","title":"XingGAN for Person Image Generation","created":"2020-07-17","cited_by_count":81},{"id":"2003.10401","title":"Learning Dynamic Routing for Semantic Segmentation","created":"2020-03-23","cited_by_count":79},{"id":"1803.11029","title":"Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation","created":"2018-03-29","cited_by_count":78},{"id":"1911.11897","title":"AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks","created":"2019-11-27","cited_by_count":77},{"id":"1909.09408","title":"ACFNet: Attentional Class Feature Network for Semantic Segmentation","created":"2019-09-20","cited_by_count":75},{"id":"1912.12215","title":"Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation","created":"2019-12-27","cited_by_count":75},{"id":"1704.02157","title":"Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation","created":"2017-04-07","cited_by_count":70},{"id":"2003.05128","title":"Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks","created":"2020-03-11","cited_by_count":70},{"id":"1411.6447","title":"The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification","created":"2014-11-24","cited_by_count":67},{"id":"1908.06955","title":"Dynamic Graph Message Passing Networks","created":"2019-08-19","cited_by_count":62},{"id":"1909.02651","title":"Semantic Correlation Promoted Shape-Variant Context for Segmentation","created":"2019-09-05","cited_by_count":61},{"id":"1909.03402","title":"Squeeze-and-Attention Networks for Semantic Segmentation","created":"2019-09-08","cited_by_count":61},{"id":"2003.13446","title":"DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning","created":"2020-03-30","cited_by_count":60},{"id":"1909.06121","title":"Dual Graph Convolutional Network for Semantic Segmentation","created":"2019-09-13","cited_by_count":59},{"id":"1912.09021","title":"AANet: Attribute Attention Network for Person Re-Identifications","created":"2019-12-19","cited_by_count":56},{"id":"1803.10335","title":"Adaptive Affinity Fields for Semantic Segmentation","created":"2018-03-27","cited_by_count":48},{"id":"2003.10211","title":"Spatial Pyramid Based Graph Reasoning for Semantic Segmentation","created":"2020-03-23","cited_by_count":47},{"id":"1509.02634","title":"Semantic Image Segmentation via Deep Parsing Network","created":"2015-09-09","cited_by_count":44},{"id":"2007.09690","title":"Class-wise Dynamic Graph Convolution for Semantic Segmentation","created":"2020-07-19","cited_by_count":44},{"id":"1412.1283","title":"Convolutional Feature Masking for Joint Object and Stuff Segmentation","created":"2014-12-03","cited_by_count":41},{"id":"2004.10681","title":"Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction","created":"2020-04-22","cited_by_count":41},{"id":"2008.13024","title":"Dual Attention GANs for Semantic Image Synthesis","created":"2020-08-29","cited_by_count":41},{"id":"2006.01469","title":"Channel Attention based Iterative Residual Learning for Depth Map Super-Resolution","created":"2020-06-02","cited_by_count":40},{"id":"1903.12296","title":"Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation","created":"2019-03-28","cited_by_count":39},{"id":"1505.07293","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling","created":"2015-05-27","cited_by_count":37},{"id":"2008.06581","title":"Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention","created":"2020-08-14","cited_by_count":37},{"id":"2001.06804","title":"Learning Compositional Neural Information Fusion for Human Parsing","created":"2020-01-19","cited_by_count":36},{"id":"1612.07429","title":"Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks","created":"2016-12-22","cited_by_count":35},{"id":"1604.01347","title":"Marr Revisited: 2D-3D Alignment via Surface Normal Prediction","created":"2016-04-05","cited_by_count":34},{"id":"1704.02431","title":"Learning Cross-Modal Deep Representations for Robust Pedestrian Detection","created":"2017-04-08","cited_by_count":34},{"id":"1801.00524","title":"Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction","created":"2018-01-01","cited_by_count":30},{"id":"1908.02590","title":"Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoders","created":"2019-08-07","cited_by_count":27},{"id":"1511.08119","title":"Higher Order Conditional Random Fields in Deep Neural Networks","created":"2015-11-25","cited_by_count":26},{"id":"1903.12305","title":"FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image","created":"2019-03-29","cited_by_count":26},{"id":"1908.07070","title":"UprightNet: Geometry-Aware Camera Orientation Estimation from Single Images","created":"2019-08-19","cited_by_count":26},{"id":"1906.05739","title":"Generating and Exploiting Probabilistic Monocular Depth Estimates","created":"2019-06-13","cited_by_count":18},{"id":"1702.06506","title":"PixelNet: Representation of the pixels, by the pixels, and for the pixels","created":"2017-02-21","cited_by_count":17},{"id":"1907.01826","title":"Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation","created":"2019-07-03","cited_by_count":14},{"id":"2004.08055","title":"Self-Learning with Rectification Strategy for Human Parsing","created":"2020-04-17","cited_by_count":12},{"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":"1909.04366","title":"Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection","created":"2019-09-10","cited_by_count":11},{"id":"1912.10647","title":"Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement","created":"2019-12-23","cited_by_count":11},{"id":"1911.08877","title":"Improving Semantic Segmentation of Aerial Images Using Patch-based Attention","created":"2019-11-20","cited_by_count":9},{"id":"2101.02843","title":"Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction","created":"2021-01-08","cited_by_count":8},{"id":"2007.09858","title":"Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism","created":"2020-07-20","cited_by_count":6},{"id":"2102.04144","title":"Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement","created":"2021-02-08","cited_by_count":6},{"id":"1908.05794","title":"Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation","created":"2019-08-15","cited_by_count":5},{"id":"1909.03140","title":"Geometry-Aware Video Object Detection for Static Cameras","created":"2019-09-06","cited_by_count":5}],"next_cursor":"100"}