{"list":"other","total":62,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"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":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"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":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"1912.13192","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","created":"2019-12-31","cited_by_count":891},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"1711.08488","title":"Frustum PointNets for 3D Object Detection from RGB-D Data","created":"2017-11-22","cited_by_count":640},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"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":"1805.10123","title":"TADAM: Task dependent adaptive metric for improved few-shot learning","created":"2018-05-23","cited_by_count":408},{"id":"1805.08136","title":"Meta-learning with differentiable closed-form solvers","created":"2018-05-21","cited_by_count":397},{"id":"2007.00224","title":"Debiased Contrastive Learning","created":"2020-07-01","cited_by_count":356},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"id":"1712.02294","title":"Joint 3D Proposal Generation and Object Detection from View Aggregation","created":"2017-12-06","cited_by_count":326},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"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":"2012.10992","title":"Deep Continuous Fusion for Multi-Sensor 3D Object Detection","created":"2020-12-20","cited_by_count":263},{"id":"1812.07003","title":"3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans","created":"2018-12-17","cited_by_count":217},{"id":"2101.02691","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud","created":"2021-01-07","cited_by_count":217},{"id":"2104.00678","title":"Group-Free 3D Object Detection via Transformers","created":"2021-04-01","cited_by_count":215},{"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":"1711.10871","title":"PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation","created":"2017-11-29","cited_by_count":170},{"id":"2106.01178","title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","created":"2021-06-02","cited_by_count":157},{"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":"2006.05682","title":"H3DNet: 3D Object Detection Using Hybrid Geometric Primitives","created":"2020-06-10","cited_by_count":123},{"id":"1511.02300","title":"Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images","created":"2015-11-07","cited_by_count":111},{"id":"2011.09315","title":"End-to-End Object Detection with Adaptive Clustering Transformer","created":"2020-11-18","cited_by_count":109},{"id":"2205.14204","title":"Multimodal Masked Autoencoders Learn Transferable Representations","created":"2022-05-27","cited_by_count":109},{"id":"1912.05163","title":"TANet: Robust 3D Object Detection from Point Clouds with Triple Attention","created":"2019-12-11","cited_by_count":108},{"id":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","cited_by_count":105},{"id":"2209.14169","title":"CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention","created":"2022-09-28","cited_by_count":103},{"id":"2112.00322","title":"FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection","created":"2021-12-01","cited_by_count":97},{"id":"2006.12356","title":"Generative Sparse Detection Networks for 3D Single-shot Object Detection","created":"2020-06-22","cited_by_count":69},{"id":"2207.01077","title":"Can Language Understand Depth?","created":"2022-07-03","cited_by_count":69},{"id":"2104.11225","title":"Pri3D: Can 3D Priors Help 2D Representation Learning?","created":"2021-04-22","cited_by_count":61},{"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":"2107.14724","title":"Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation","created":"2021-07-30","cited_by_count":46},{"id":"2012.13089","title":"P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding","created":"2020-12-24","cited_by_count":41},{"id":"2101.07253","title":"Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation","created":"2021-01-18","cited_by_count":40},{"id":"2212.13979","title":"TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning","created":"2022-12-28","cited_by_count":37},{"id":"2105.14734","title":"Dual-stream Network for Visual Recognition","created":"2021-05-31","cited_by_count":33},{"id":"2204.00989","title":"POS-BERT: Point Cloud One-Stage BERT Pre-Training","created":"2022-04-03","cited_by_count":16},{"id":"2303.05475","title":"Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking","created":"2023-03-09","cited_by_count":12},{"id":"2207.10589","title":"Boosting 3D Object Detection via Object-Focused Image Fusion","created":"2022-07-21","cited_by_count":11},{"id":"2210.11470","title":"i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?","created":"2022-10-20","cited_by_count":8}],"next_cursor":null}