{"list":"other","total":109,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"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":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"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":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"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":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"1611.07759","title":"Multi-View 3D Object Detection Network for Autonomous Driving","created":"2016-11-23","cited_by_count":724},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1811.07246","title":"PointConv: Deep Convolutional Networks on 3D Point Clouds","created":"2018-11-17","cited_by_count":657},{"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":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2206.04670","title":"PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies","created":"2022-06-09","cited_by_count":436},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"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":"2210.05666","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","created":"2022-10-11","cited_by_count":388},{"id":"1711.09869","title":"Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs","created":"2017-11-27","cited_by_count":385},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"1610.07629","title":"A Learned Representation For Artistic Style","created":"2016-10-24","cited_by_count":341},{"id":"1905.03304","title":"Deep Closest Point: Learning Representations for Point Cloud Registration","created":"2019-05-08","cited_by_count":321},{"id":"2004.01658","title":"PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation","created":"2020-04-03","cited_by_count":321},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2011.10043","title":"Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning","created":"2020-11-19","cited_by_count":297},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"2204.07761","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","created":"2022-04-16","cited_by_count":246},{"id":"2003.00492","title":"PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling","created":"2020-03-01","cited_by_count":239},{"id":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"1701.02096","title":"Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis","created":"2017-01-09","cited_by_count":215},{"id":"2103.14635","title":"PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds","created":"2021-03-26","cited_by_count":211},{"id":"2012.09165","title":"Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts","created":"2020-12-16","cited_by_count":210},{"id":"2103.01988","title":"Self-supervised Pretraining of Visual Features in the Wild","created":"2021-03-02","cited_by_count":198},{"id":"2108.02035","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","created":"2021-08-04","cited_by_count":183},{"id":"1710.07563","title":"SEGCloud: Semantic Segmentation of 3D Point Clouds","created":"2017-10-20","cited_by_count":179},{"id":"1807.02443","title":"Tangent Convolutions for Dense Prediction in 3D","created":"2018-07-06","cited_by_count":173},{"id":"2203.14508","title":"Stratified Transformer for 3D Point Cloud Segmentation","created":"2022-03-28","cited_by_count":167},{"id":"2101.06742","title":"Deep Parametric Continuous Convolutional Neural Networks","created":"2021-01-17","cited_by_count":161},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161},{"id":"2207.04397","title":"2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds","created":"2022-07-10","cited_by_count":158},{"id":"1904.03375","title":"Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling","created":"2019-04-06","cited_by_count":151},{"id":"2210.07225","title":"Unified Vision and Language Prompt Learning","created":"2022-10-13","cited_by_count":148},{"id":"2202.06687","title":"Domain Adaptation via Prompt Learning","created":"2022-02-14","cited_by_count":128},{"id":"2303.05367","title":"Rethinking Range View Representation for LiDAR Segmentation","created":"2023-03-09","cited_by_count":128},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127},{"id":"2303.12766","title":"Spherical Transformer for LiDAR-based 3D Recognition","created":"2023-03-22","cited_by_count":125},{"id":"2206.02099","title":"Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation","created":"2022-06-05","cited_by_count":119},{"id":"1708.02551","title":"Semantic Instance Segmentation with a Discriminative Loss Function","created":"2017-08-08","cited_by_count":118},{"id":"1803.10409","title":"3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation","created":"2018-03-28","cited_by_count":118},{"id":"2304.06906","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","created":"2023-04-14","cited_by_count":113},{"id":"2305.03045","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","created":"2023-05-04","cited_by_count":109},{"id":"1608.07916","title":"Vehicle Detection from 3D Lidar Using Fully Convolutional Network","created":"2016-08-29","cited_by_count":107},{"id":"2112.04702","title":"Fast Point Transformer","created":"2021-12-09","cited_by_count":104},{"id":"1903.01177","title":"PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things","created":"2019-03-04","cited_by_count":98},{"id":"2304.04514","title":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment","created":"2023-04-10","cited_by_count":90},{"id":"1910.08207","title":"Unsupervised Multi-Task Feature Learning on Point Clouds","created":"2019-10-18","cited_by_count":89},{"id":"2105.08054","title":"Divide and Contrast: Self-supervised Learning from Uncurated Data","created":"2021-05-17","cited_by_count":85},{"id":"2106.11952","title":"Unsupervised Object-Level Representation Learning from Scene Images","created":"2021-06-22","cited_by_count":72},{"id":"2206.10555","title":"LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs","created":"2022-06-21","cited_by_count":72},{"id":"2011.13677","title":"Self-EMD: Self-Supervised Object Detection without ImageNet","created":"2020-11-27","cited_by_count":70},{"id":"2205.15288","title":"Self-Supervised Visual Representation Learning with Semantic Grouping","created":"2022-05-30","cited_by_count":70},{"id":"1909.10469","title":"Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation","created":"2019-09-23","cited_by_count":68},{"id":"2006.02598","title":"Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning","created":"2020-06-04","cited_by_count":68},{"id":"2008.06614","title":"Object Detection with a Unified Label Space from Multiple Datasets","created":"2020-08-15","cited_by_count":65},{"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":"2303.14191","title":"Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning","created":"2023-03-24","cited_by_count":56},{"id":"2203.09770","title":"Prototypical Verbalizer for Prompt-based Few-shot Tuning","created":"2022-03-18","cited_by_count":53}],"next_cursor":"100"}