{"list":"other","total":52,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"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":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"1912.07372","title":"Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision","created":"2019-12-16","cited_by_count":700},{"id":"1701.04862","title":"Towards Principled Methods for Training Generative Adversarial Networks","created":"2017-01-17","cited_by_count":464},{"id":"1801.10130","title":"Spherical CNNs","created":"2018-01-30","cited_by_count":456},{"id":"1812.01024","title":"DeepVoxels: Learning Persistent 3D Feature Embeddings","created":"2018-12-03","cited_by_count":405},{"id":"1711.10006","title":"SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again","created":"2017-11-27","cited_by_count":243},{"id":"1703.10896","title":"BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth","created":"2017-03-31","cited_by_count":225},{"id":"1711.08848","title":"Real-Time Seamless Single Shot 6D Object Pose Prediction","created":"2017-11-24","cited_by_count":210},{"id":"1905.07259","title":"Texture Fields: Learning Texture Representations in Function Space","created":"2019-05-17","cited_by_count":210},{"id":"1611.02163","title":"Unrolled Generative Adversarial Networks","created":"2016-11-07","cited_by_count":208},{"id":"1704.06254","title":"Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency","created":"2017-04-20","cited_by_count":177},{"id":"1811.11606","title":"Escaping Plato's Cave: 3D Shape From Adversarial Rendering","created":"2018-11-28","cited_by_count":170},{"id":"1902.01275","title":"Implicit 3D Orientation Learning for 6D Object Detection from RGB Images","created":"2019-02-04","cited_by_count":170},{"id":"2005.08104","title":"Single-Stage Semantic Segmentation from Image Labels","created":"2020-05-16","cited_by_count":167},{"id":"2012.09988","title":"Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations","created":"2020-12-18","cited_by_count":155},{"id":"1804.01005","title":"Face Alignment in Full Pose Range: A 3D Total Solution","created":"2018-04-02","cited_by_count":148},{"id":"1503.03167","title":"Deep Convolutional Inverse Graphics Network","created":"2015-03-11","cited_by_count":121},{"id":"1612.05872","title":"3D Shape Induction from 2D Views of Multiple Objects","created":"2016-12-18","cited_by_count":121},{"id":"1806.07823","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","created":"2018-06-20","cited_by_count":114},{"id":"1612.00814","title":"Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision","created":"2016-12-01","cited_by_count":106},{"id":"1603.01249","title":"HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition","created":"2016-03-03","cited_by_count":104},{"id":"2008.08145","title":"Category Level Object Pose Estimation via Neural Analysis-by-Synthesis","created":"2020-08-18","cited_by_count":100},{"id":"1703.04670","title":"6-DoF Object Pose from Semantic Keypoints","created":"2017-03-14","cited_by_count":89},{"id":"1810.09381","title":"Unsupervised Learning of Shape and Pose with Differentiable Point Clouds","created":"2018-10-22","cited_by_count":89},{"id":"1807.03146","title":"Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning","created":"2018-07-05","cited_by_count":79},{"id":"1804.01110","title":"Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation","created":"2018-04-03","cited_by_count":73},{"id":"1807.04689","title":"Explorations in Homeomorphic Variational Auto-Encoding","created":"2018-07-12","cited_by_count":65},{"id":"1411.6067","title":"Viewpoints and Keypoints","created":"2014-11-22","cited_by_count":59},{"id":"1801.03910","title":"Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction","created":"2018-01-11","cited_by_count":52},{"id":"1805.03430","title":"Deep Directional Statistics: Pose Estimation with Uncertainty Quantification","created":"2018-05-09","cited_by_count":45},{"id":"1803.09331","title":"StarMap for Category-Agnostic Keypoint and Viewpoint Estimation","created":"2018-03-25","cited_by_count":42},{"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":"1710.07307","title":"Interpretable Transformations with Encoder-Decoder Networks","created":"2017-10-19","cited_by_count":34},{"id":"1803.11493","title":"3D Pose Estimation and 3D Model Retrieval for Objects in the Wild","created":"2018-03-30","cited_by_count":31},{"id":"1705.03951","title":"Learning 3D Object Categories by Looking Around Them","created":"2017-05-10","cited_by_count":26},{"id":"1904.06458","title":"Transformable Bottleneck Networks","created":"2019-04-13","cited_by_count":23},{"id":"2004.01793","title":"Self-Supervised Viewpoint Learning From Image Collections","created":"2020-04-03","cited_by_count":23},{"id":"1707.09695","title":"Recurrent 3D Pose Sequence Machines","created":"2017-07-31","cited_by_count":12},{"id":"1812.02716","title":"Cross-Domain 3D Equivariant Image Embeddings","created":"2018-12-06","cited_by_count":12},{"id":"2003.11303","title":"Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation","created":"2020-03-25","cited_by_count":7},{"id":"2104.01103","title":"Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation","created":"2021-04-02","cited_by_count":5},{"id":"1602.06822","title":"Understanding Visual Concepts with Continuation Learning","created":"2016-02-22","cited_by_count":4}],"next_cursor":null}