{"list":"other","total":113,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"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":"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":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"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":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"2007.15651","title":"Contrastive Learning for Unpaired Image-to-Image Translation","created":"2020-07-30","cited_by_count":639},{"id":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"1908.04616","title":"Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data","created":"2019-08-13","cited_by_count":532},{"id":"1906.12340","title":"Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty","created":"2019-06-28","cited_by_count":514},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"1905.03670","title":"S4L: Self-Supervised Semi-Supervised Learning","created":"2019-05-09","cited_by_count":335},{"id":"2006.10511","title":"Contrastive learning of global and local features for medical image segmentation with limited annotations","created":"2020-06-18","cited_by_count":309},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"2205.14401","title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","created":"2022-05-28","cited_by_count":264},{"id":"1806.01411","title":"FlowNet3D: Learning Scene Flow in 3D Point Clouds","created":"2018-06-04","cited_by_count":242},{"id":"1705.09634","title":"Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration","created":"2017-05-26","cited_by_count":223},{"id":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218},{"id":"2101.02691","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud","created":"2021-01-07","cited_by_count":217},{"id":"2012.09165","title":"Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts","created":"2020-12-16","cited_by_count":210},{"id":"2203.00680","title":"CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding","created":"2022-03-01","cited_by_count":198},{"id":"2304.03284","title":"SegGPT: Segmenting Everything In Context","created":"2023-04-06","cited_by_count":194},{"id":"2010.01089","title":"Unsupervised Point Cloud Pre-Training via Occlusion Completion","created":"2020-10-02","cited_by_count":186},{"id":"2109.00179","title":"Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds","created":"2021-09-01","cited_by_count":180},{"id":"2103.05346","title":"ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection","created":"2021-03-09","cited_by_count":159},{"id":"2203.11183","title":"Masked Discrimination for Self-Supervised Learning on Point Clouds","created":"2022-03-21","cited_by_count":155},{"id":"2005.08139","title":"Train in Germany, Test in The USA: Making 3D Object Detectors Generalize","created":"2020-05-17","cited_by_count":151},{"id":"2212.06785","title":"Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders","created":"2022-12-13","cited_by_count":144},{"id":"2110.02210","title":"Mix3D: Out-of-Context Data Augmentation for 3D Scenes","created":"2021-10-05","cited_by_count":126},{"id":"2002.09147","title":"SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances","created":"2020-02-21","cited_by_count":123},{"id":"2212.08320","title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","created":"2022-12-16","cited_by_count":122},{"id":"2003.10955","title":"MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask","created":"2020-03-24","cited_by_count":117},{"id":"2004.05224","title":"Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review","created":"2020-04-10","cited_by_count":108},{"id":"2003.06754","title":"MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps","created":"2020-03-15","cited_by_count":100},{"id":"2003.12641","title":"Self-Supervised Learning for Domain Adaptation on Point-Clouds","created":"2020-03-29","cited_by_count":99},{"id":"1912.00497","title":"Just Go with the Flow: Self-Supervised Scene Flow Estimation","created":"2019-12-01","cited_by_count":98},{"id":"1910.08207","title":"Unsupervised Multi-Task Feature Learning on Point Clouds","created":"2019-10-18","cited_by_count":89},{"id":"1901.04596","title":"AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data","created":"2019-01-14","cited_by_count":77},{"id":"2208.02812","title":"P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting","created":"2022-08-04","cited_by_count":74},{"id":"2008.00305","title":"Self-supervised Learning of Point Clouds via Orientation Estimation","created":"2020-08-01","cited_by_count":72},{"id":"2011.10147","title":"FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation","created":"2020-11-19","cited_by_count":71},{"id":"2203.07004","title":"Rethinking Minimal Sufficient Representation in Contrastive Learning","created":"2022-03-14","cited_by_count":69},{"id":"2212.05867","title":"ALSO: Automotive Lidar Self-supervision by Occupancy estimation","created":"2022-12-12","cited_by_count":68},{"id":"2009.14168","title":"Self-Supervised Few-Shot Learning on Point Clouds","created":"2020-09-29","cited_by_count":66},{"id":"2104.07689","title":"Dual Contrastive Learning for Unsupervised Image-to-Image Translation","created":"2021-04-15","cited_by_count":66},{"id":"2108.06682","title":"ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection","created":"2021-08-15","cited_by_count":57},{"id":"2212.03010","title":"GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds","created":"2022-12-06","cited_by_count":57},{"id":"2112.04680","title":"SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations","created":"2021-12-09","cited_by_count":55},{"id":"2112.02990","title":"4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding","created":"2021-12-06","cited_by_count":54},{"id":"2301.00157","title":"Ponder: Point Cloud Pre-training via Neural Rendering","created":"2022-12-31","cited_by_count":50},{"id":"2201.00785","title":"Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning","created":"2022-01-03","cited_by_count":46},{"id":"2011.00320","title":"Scene Flow from Point Clouds with or without Learning","created":"2020-10-31","cited_by_count":44},{"id":"2207.12654","title":"ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection","created":"2022-07-26","cited_by_count":43},{"id":"2110.04076","title":"Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks","created":"2021-09-28","cited_by_count":42},{"id":"2009.10467","title":"Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion","created":"2020-09-22","cited_by_count":41},{"id":"2105.08248","title":"Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk","created":"2021-05-18","cited_by_count":39},{"id":"2111.11631","title":"Self-Regulated Learning for Egocentric Video Activity Anticipation","created":"2021-11-23","cited_by_count":32},{"id":"1705.08781","title":"Dynamic Occupancy Grid Prediction for Urban Autonomous Driving: A Deep Learning Approach with Fully Automatic Labeling","created":"2017-05-24","cited_by_count":30},{"id":"2012.04718","title":"Canonical Capsules: Self-Supervised Capsules in Canonical Pose","created":"2020-12-08","cited_by_count":30},{"id":"2207.01545","title":"Masked Autoencoders in 3D Point Cloud Representation Learning","created":"2022-07-04","cited_by_count":30},{"id":"2204.03642","title":"Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction","created":"2022-04-07","cited_by_count":26},{"id":"2210.04458","title":"OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds","created":"2022-10-10","cited_by_count":25},{"id":"2303.01212","title":"Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review","created":"2023-03-02","cited_by_count":25},{"id":"2207.04997","title":"A Closer Look at Invariances in Self-supervised Pre-training for 3D Vision","created":"2022-07-11","cited_by_count":24},{"id":"2111.15363","title":"Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding","created":"2021-11-30","cited_by_count":22},{"id":"2206.14971","title":"Boosting 3D Object Detection by Simulating Multimodality on Point Clouds","created":"2022-06-30","cited_by_count":22},{"id":"2212.05758","title":"BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios","created":"2022-12-12","cited_by_count":21},{"id":"1904.06116","title":"PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation","created":"2019-04-12","cited_by_count":20},{"id":"2209.07951","title":"SeqOT: A Spatial-Temporal Transformer Network for Place Recognition Using Sequential LiDAR Data","created":"2022-09-16","cited_by_count":20},{"id":"2212.07207","title":"MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds","created":"2022-12-14","cited_by_count":20},{"id":"2004.05749","title":"Self-supervised Feature Learning by Cross-modality and Cross-view Correspondences","created":"2020-04-13","cited_by_count":19},{"id":"2202.04241","title":"Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning","created":"2022-02-09","cited_by_count":19},{"id":"2205.00705","title":"3D Object Detection with a Self-supervised Lidar Scene Flow Backbone","created":"2022-05-02","cited_by_count":19},{"id":"2212.08892","title":"Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis","created":"2022-12-17","cited_by_count":19},{"id":"2212.04098","title":"EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder","created":"2022-12-08","cited_by_count":18},{"id":"2204.00989","title":"POS-BERT: Point Cloud One-Stage BERT Pre-Training","created":"2022-04-03","cited_by_count":16},{"id":"2206.04028","title":"CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving","created":"2022-06-08","cited_by_count":15},{"id":"2207.03111","title":"Masked Surfel Prediction for Self-Supervised Point Cloud Learning","created":"2022-07-07","cited_by_count":15},{"id":"2011.10812","title":"MoNet: Motion-based Point Cloud Prediction Network","created":"2020-11-21","cited_by_count":14},{"id":"2011.09045","title":"Double-Prong ConvLSTM for Spatiotemporal Occupancy Prediction in Dynamic Environments","created":"2020-11-18","cited_by_count":13},{"id":"2104.04724","title":"Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds","created":"2021-04-10","cited_by_count":11},{"id":"2201.08215","title":"CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning","created":"2022-01-20","cited_by_count":9},{"id":"2202.02543","title":"Unsupervised Point Cloud Pre-Training via Contrasting and Clustering","created":"2022-02-05","cited_by_count":9},{"id":"2211.06841","title":"Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning","created":"2022-11-13","cited_by_count":9}],"next_cursor":"100"}