{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"1811.07246","title":"PointConv: Deep Convolutional Networks on 3D Point Clouds","created":"2018-11-17","cited_by_count":657},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"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":"1908.07442","title":"TabNet: Attentive Interpretable Tabular Learning","created":"2019-08-20","cited_by_count":648},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"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":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"id":"1806.01482","title":"SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints","created":"2018-06-05","cited_by_count":298},{"id":"1605.07725","title":"Adversarial Training Methods for Semi-Supervised Text Classification","created":"2016-05-25","cited_by_count":280},{"id":"2103.16607","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","created":"2021-03-30","cited_by_count":215},{"id":"1803.04249","title":"SO-Net: Self-Organizing Network for Point Cloud Analysis","created":"2018-03-12","cited_by_count":210},{"id":"2312.10115","title":"SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery","created":"2023-12-15","cited_by_count":205},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"1704.01222","title":"Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models","created":"2017-04-04","cited_by_count":142},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"2305.11487","title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","created":"2023-05-19","cited_by_count":115},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80},{"id":"2011.01843","title":"Tabular Transformers for Modeling Multivariate Time Series","created":"2020-11-03","cited_by_count":77},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64},{"id":"1909.09287","title":"Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds","created":"2019-09-20","cited_by_count":57},{"id":"2105.10196","title":"Multimodal Remote Sensing Benchmark Datasets for Land Cover Classification with A Shared and Specific Feature Learning Model","created":"2021-05-21","cited_by_count":43},{"id":"2204.04716","title":"TOV: The Original Vision Model for Optical Remote Sensing Image Understanding via Self-supervised Learning","created":"2022-04-10","cited_by_count":35},{"id":"2012.15688","title":"ERNIE-Doc: A Retrospective Long-Document Modeling Transformer","created":"2020-12-31","cited_by_count":31},{"id":"2002.01144","title":"Classification of Hyperspectral and LiDAR Data Using Coupled CNNs","created":"2020-02-04","cited_by_count":25},{"id":"2106.15762","title":"Curvature Graph Neural Network","created":"2021-06-30","cited_by_count":24},{"id":"2009.04007","title":"Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function","created":"2020-09-08","cited_by_count":23},{"id":"2210.08345","title":"Augmentation-Free Graph Contrastive Learning of Invariant-Discriminative Representations","created":"2022-10-15","cited_by_count":21},{"id":"2011.14992","title":"KST-GCN: A Knowledge-Driven Spatial-Temporal Graph Convolutional Network for Traffic Forecasting","created":"2020-11-26","cited_by_count":20},{"id":"2004.04491","title":"Multi-Granularity Canonical Appearance Pooling for Remote Sensing Scene Classification","created":"2020-04-09","cited_by_count":16},{"id":"2103.10368","title":"MSMatch: Semi-Supervised Multispectral Scene Classification with Few Labels","created":"2021-03-18","cited_by_count":12},{"id":"2210.16789","title":"STGC-GNNs: A GNN-based traffic prediction framework with a spatial-temporal Granger causality graph","created":"2022-10-30","cited_by_count":12},{"id":"2303.18210","title":"A Closer Look at Few-Shot 3D Point Cloud Classification","created":"2023-03-31","cited_by_count":10},{"id":"2011.05702","title":"Invariant Deep Compressible Covariance Pooling for Aerial Scene Categorization","created":"2020-11-11","cited_by_count":4},{"id":"2306.15868","title":"GraSS: Contrastive Learning with Gradient Guided Sampling Strategy for Remote Sensing Image Semantic Segmentation","created":"2023-06-28","cited_by_count":3}],"next_cursor":null}