{"list":"other","total":60,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"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":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1904.08755","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","created":"2019-04-18","cited_by_count":1208},{"id":"1904.08889","title":"KPConv: Flexible and Deformable Convolution for Point Clouds","created":"2019-04-18","cited_by_count":1205},{"id":"1912.13192","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","created":"2019-12-31","cited_by_count":891},{"id":"1711.10275","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","created":"2017-11-28","cited_by_count":748},{"id":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"1911.10150","title":"PointPainting: Sequential Fusion for 3D Object Detection","created":"2019-11-22","cited_by_count":449},{"id":"2007.16100","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","created":"2020-07-31","cited_by_count":423},{"id":"2011.10033","title":"Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation","created":"2020-11-19","cited_by_count":389},{"id":"1611.05009","title":"OctNet: Learning Deep 3D Representations at High Resolutions","created":"2016-11-15","cited_by_count":342},{"id":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"id":"2003.14032","title":"PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation","created":"2020-03-31","cited_by_count":275},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"2003.03653","title":"SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving","created":"2020-03-07","cited_by_count":226},{"id":"2003.06537","title":"OccuSeg: Occupancy-aware 3D Instance Segmentation","created":"2020-03-14","cited_by_count":177},{"id":"1507.00448","title":"Cross Modal Distillation for Supervision Transfer","created":"2015-07-02","cited_by_count":175},{"id":"2004.01803","title":"SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation","created":"2020-04-03","cited_by_count":170},{"id":"2102.04530","title":"(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network","created":"2021-02-08","cited_by_count":164},{"id":"1704.03847","title":"Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark","created":"2017-04-12","cited_by_count":158},{"id":"1910.02923","title":"A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis","created":"2019-10-07","cited_by_count":151},{"id":"1609.05130","title":"SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks","created":"2016-09-16","cited_by_count":135},{"id":"1911.12676","title":"xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation","created":"2019-11-28","cited_by_count":129},{"id":"2002.09147","title":"SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances","created":"2020-02-21","cited_by_count":123},{"id":"1803.10409","title":"3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation","created":"2018-03-28","cited_by_count":118},{"id":"2007.08488","title":"Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds","created":"2020-07-16","cited_by_count":116},{"id":"1703.03365","title":"Learning Active Learning from Data","created":"2017-03-09","cited_by_count":101},{"id":"2003.12641","title":"Self-Supervised Learning for Domain Adaptation on Point-Clouds","created":"2020-03-29","cited_by_count":99},{"id":"2007.13138","title":"Virtual Multi-view Fusion for 3D Semantic Segmentation","created":"2020-07-26","cited_by_count":99},{"id":"1911.11789","title":"ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation","created":"2019-11-26","cited_by_count":96},{"id":"1705.03428","title":"Deep Projective 3D Semantic Segmentation","created":"2017-05-09","cited_by_count":81},{"id":"1608.07017","title":"Ambient Sound Provides Supervision for Visual Learning","created":"2016-08-25","cited_by_count":78},{"id":"1909.13603","title":"Multi-view PointNet for 3D Scene Understanding","created":"2019-09-30","cited_by_count":76},{"id":"1712.00032","title":"Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification","created":"2017-11-30","cited_by_count":65},{"id":"1910.11760","title":"Self-supervised Moving Vehicle Tracking with Stereo Sound","created":"2019-10-25","cited_by_count":63},{"id":"1904.00699","title":"JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields","created":"2019-04-01","cited_by_count":62},{"id":"1911.09168","title":"Active Learning for Deep Detection Neural Networks","created":"2019-11-20","cited_by_count":62},{"id":"2007.06888","title":"JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds","created":"2020-07-14","cited_by_count":62},{"id":"2004.04699","title":"Scalable Active Learning for Object Detection","created":"2020-04-09","cited_by_count":58},{"id":"1812.00020","title":"TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes","created":"2018-11-30","cited_by_count":45},{"id":"2101.07253","title":"Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation","created":"2021-01-18","cited_by_count":40},{"id":"2010.08705","title":"DEAL: Difficulty-aware Active Learning for Semantic Segmentation","created":"2020-10-17","cited_by_count":32},{"id":"1703.08866","title":"Multi-View Deep Learning for Consistent Semantic Mapping with RGB-D Cameras","created":"2017-03-26","cited_by_count":28},{"id":"2004.12498","title":"Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes","created":"2020-04-26","cited_by_count":27},{"id":"2003.13594","title":"Speech2Action: Cross-modal Supervision for Action Recognition","created":"2020-03-30","cited_by_count":26},{"id":"1901.09244","title":"DistInit: Learning Video Representations Without a Single Labeled Video","created":"2019-01-26","cited_by_count":21},{"id":"2005.14169","title":"Self-supervised Modal and View Invariant Feature Learning","created":"2020-05-28","cited_by_count":20},{"id":"2010.12239","title":"Domain Adaptation in LiDAR Semantic Segmentation by Aligning Class Distributions","created":"2020-10-23","cited_by_count":17}],"next_cursor":null}