{"list":"other","total":77,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"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":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1801.07791","title":"PointCNN: Convolution On $\\mathcal{X}$-Transformed Points","created":"2018-01-23","cited_by_count":764},{"id":"1711.10275","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","created":"2017-11-28","cited_by_count":748},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"1711.08488","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","created":"2017-11-22","cited_by_count":640},{"id":"1911.11236","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","created":"2019-11-25","cited_by_count":585},{"id":"1505.00880","title":"Multi-view Convolutional Neural Networks for 3D Shape Recognition","created":"2015-05-05","cited_by_count":565},{"id":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1907.03739","title":"Point-Voxel CNN for Efficient 3D Deep Learning","created":"2019-07-08","cited_by_count":343},{"id":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"1611.05009","title":"OctNet: Learning Deep 3D Representations at High Resolutions","created":"2016-11-15","cited_by_count":342},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1803.11527","title":"SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters","created":"2018-03-30","cited_by_count":261},{"id":"1806.01411","title":"FlowNet3D: Learning Scene Flow in 3D Point Clouds","created":"2018-06-04","cited_by_count":242},{"id":"1604.03265","title":"Volumetric and Multi-View CNNs for Object Classification on 3D Data","created":"2016-04-12","cited_by_count":240},{"id":"1904.12659","title":"Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2019-04-26","cited_by_count":228},{"id":"1906.01140","title":"Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds","created":"2019-06-04","cited_by_count":156},{"id":"1902.09130","title":"An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition","created":"2019-02-25","cited_by_count":151},{"id":"2103.05073","title":"Offboard 3D Object Detection from Point Cloud Sequences","created":"2021-03-08","cited_by_count":145},{"id":"1908.02486","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","created":"2019-08-07","cited_by_count":142},{"id":"2007.11142","title":"FLOT: Scene Flow on Point Clouds Guided by Optimal Transport","created":"2020-07-22","cited_by_count":129},{"id":"1803.10409","title":"3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation","created":"2018-03-28","cited_by_count":118},{"id":"1910.09165","title":"MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences","created":"2019-10-21","cited_by_count":117},{"id":"1906.05332","title":"HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds","created":"2019-06-12","cited_by_count":109},{"id":"1912.00497","title":"Just Go with the Flow: Self-Supervised Scene Flow Estimation","created":"2019-12-01","cited_by_count":98},{"id":"1804.07453","title":"View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition","created":"2018-04-20","cited_by_count":84},{"id":"2005.13888","title":"P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds","created":"2020-05-28","cited_by_count":84},{"id":"1711.11152","title":"Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition","created":"2017-11-29","cited_by_count":82},{"id":"2009.03137","title":"Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges","created":"2020-09-07","cited_by_count":80},{"id":"1903.01784","title":"Leveraging Shape Completion for 3D Siamese Tracking","created":"2019-03-05","cited_by_count":74},{"id":"2007.09933","title":"MotionSqueeze: Neural Motion Feature Learning for Video Understanding","created":"2020-07-20","cited_by_count":72},{"id":"2004.01389","title":"LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention","created":"2020-04-03","cited_by_count":65},{"id":"2104.04891","title":"SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds","created":"2021-04-11","cited_by_count":64},{"id":"1707.05740","title":"Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks","created":"2017-07-18","cited_by_count":62},{"id":"2102.08945","title":"Weakly Supervised Learning of Rigid 3D Scene Flow","created":"2021-02-17","cited_by_count":60},{"id":"1810.01455","title":"Representation Flow for Action Recognition","created":"2018-10-02","cited_by_count":51},{"id":"2008.02792","title":"CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations","created":"2020-08-06","cited_by_count":51},{"id":"2107.02389","title":"Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling","created":"2021-07-06","cited_by_count":51},{"id":"2201.04494","title":"SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds","created":"2022-01-12","cited_by_count":50},{"id":"2007.12392","title":"An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds","created":"2020-07-24","cited_by_count":45},{"id":"1804.00413","title":"End-to-End Learning of Motion Representation for Video Understanding","created":"2018-04-02","cited_by_count":43},{"id":"1907.13025","title":"SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition","created":"2019-07-30","cited_by_count":43},{"id":"2005.05501","title":"3DV: 3D Dynamic Voxel for Action Recognition in Depth Video","created":"2020-05-12","cited_by_count":41},{"id":"2009.10467","title":"Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion","created":"2020-09-22","cited_by_count":41},{"id":"1807.10037","title":"Motion Feature Network: Fixed Motion Filter for Action Recognition","created":"2018-07-26","cited_by_count":34},{"id":"2002.07442","title":"V4D:4D Convolutional Neural Networks for Video-level Representation Learning","created":"2020-02-18","cited_by_count":33},{"id":"1809.01844","title":"Unsupervised Learning of View-invariant Action Representations","created":"2018-09-06","cited_by_count":32},{"id":"1910.08287","title":"PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing","created":"2019-10-18","cited_by_count":32},{"id":"1812.06145","title":"Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training","created":"2018-12-14","cited_by_count":28},{"id":"1906.09023","title":"Backpropagation-Friendly Eigendecomposition","created":"2019-06-21","cited_by_count":27},{"id":"1907.08871","title":"Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention","created":"2019-07-20","cited_by_count":22},{"id":"2103.08271","title":"Learning Compositional Representation for 4D Captures with Neural ODE","created":"2021-03-15","cited_by_count":22},{"id":"2110.09783","title":"Spatial-Temporal Transformer for 3D Point Cloud Sequences","created":"2021-10-19","cited_by_count":22},{"id":"1804.01194","title":"Depth Pooling Based Large-scale 3D Action Recognition with Convolutional Neural Networks","created":"2018-03-17","cited_by_count":19},{"id":"1806.11269","title":"Action Recognition for Depth Video using Multi-view Dynamic Images","created":"2018-06-29","cited_by_count":18},{"id":"2001.06291","title":"Predicting the Physical Dynamics of Unseen 3D Objects","created":"2020-01-16","cited_by_count":6}],"next_cursor":null}