{"list":"other","total":51,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"1804.01654","title":"Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images","created":"2018-04-05","cited_by_count":651},{"id":"1604.00449","title":"3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction","created":"2016-04-02","cited_by_count":588},{"id":"1711.07566","title":"Neural 3D Mesh Renderer","created":"2017-11-20","cited_by_count":437},{"id":"1904.01786","title":"Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning","created":"2019-04-03","cited_by_count":420},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"1803.07549","title":"Learning Category-Specific Mesh Reconstruction from Image Collections","created":"2018-03-20","cited_by_count":317},{"id":"1807.03247","title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","created":"2018-07-09","cited_by_count":307},{"id":"1905.03678","title":"What Do Single-view 3D Reconstruction Networks Learn?","created":"2019-05-09","cited_by_count":260},{"id":"1504.07889","title":"Bilinear CNNs for Fine-grained Visual Recognition","created":"2015-04-29","cited_by_count":228},{"id":"1911.11130","title":"Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild","created":"2019-11-25","cited_by_count":180},{"id":"1704.06254","title":"Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency","created":"2017-04-20","cited_by_count":177},{"id":"2003.06473","title":"Self-supervised Single-view 3D Reconstruction via Semantic Consistency","created":"2020-03-13","cited_by_count":127},{"id":"1809.00287","title":"Learning to Navigate for Fine-grained Classification","created":"2018-09-02","cited_by_count":103},{"id":"1908.01491","title":"Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation","created":"2019-08-05","cited_by_count":103},{"id":"1903.06150","title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","created":"2019-03-14","cited_by_count":95},{"id":"2003.03836","title":"Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches","created":"2020-03-08","cited_by_count":92},{"id":"2007.10982","title":"Shape and Viewpoint without Keypoints","created":"2020-07-21","cited_by_count":92},{"id":"1810.09381","title":"Unsupervised Learning of Shape and Pose with Differentiable Point Clouds","created":"2018-10-22","cited_by_count":89},{"id":"1709.01889","title":"Polar Transformer Networks","created":"2017-09-06","cited_by_count":81},{"id":"1903.02827","title":"Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up","created":"2019-03-07","cited_by_count":66},{"id":"1907.10043","title":"Canonical Surface Mapping via Geometric Cycle Consistency","created":"2019-07-23","cited_by_count":63},{"id":"1909.04412","title":"Cross-X Learning for Fine-Grained Visual Categorization","created":"2019-09-10","cited_by_count":61},{"id":"1806.05372","title":"Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition","created":"2018-06-14","cited_by_count":58},{"id":"1806.06503","title":"Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance","created":"2018-06-18","cited_by_count":58},{"id":"1812.08967","title":"Densely Semantically Aligned Person Re-Identification","created":"2018-12-21","cited_by_count":58},{"id":"1809.03355","title":"Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks","created":"2018-09-10","cited_by_count":56},{"id":"2004.05021","title":"Parsing-based View-aware Embedding Network for Vehicle Re-Identification","created":"2020-04-10","cited_by_count":53},{"id":"1909.11378","title":"Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization","created":"2019-09-25","cited_by_count":51},{"id":"2012.03196","title":"Online Adaptation for Consistent Mesh Reconstruction in the Wild","created":"2020-12-06","cited_by_count":51},{"id":"1406.2952","title":"Bird Species Categorization Using Pose Normalized Deep Convolutional Nets","created":"2014-06-11","cited_by_count":50},{"id":"1905.03397","title":"A Dual-Path Model With Adaptive Attention For Vehicle Re-Identification","created":"2019-05-09","cited_by_count":34},{"id":"1806.09283","title":"RAM: A Region-Aware Deep Model for Vehicle Re-Identification","created":"2018-06-25","cited_by_count":30},{"id":"1612.03897","title":"Inverse Compositional Spatial Transformer Networks","created":"2016-12-12","cited_by_count":29},{"id":"2008.11423","title":"Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network","created":"2020-08-26","cited_by_count":26},{"id":"1703.10332","title":"Dynamic Computational Time for Visual Attention","created":"2017-03-30","cited_by_count":23},{"id":"2003.14142","title":"Look-into-Object: Self-supervised Structure Modeling for Object Recognition","created":"2020-03-31","cited_by_count":20},{"id":"2005.01939","title":"From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks","created":"2020-05-05","cited_by_count":18},{"id":"1801.09057","title":"Aligned to the Object, not to the Image: A Unified Pose-aligned Representation for Fine-grained Recognition","created":"2018-01-27","cited_by_count":10},{"id":"2003.11303","title":"Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation","created":"2020-03-25","cited_by_count":7},{"id":"2007.09433","title":"Volumetric Transformer Networks","created":"2020-07-18","cited_by_count":2}],"next_cursor":null}