{"list":"other","total":94,"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":"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1312.6203","title":"Spectral Networks and Locally Connected Networks on Graphs","created":"2013-12-21","cited_by_count":1102},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"1511.05493","title":"Gated Graph Sequence Neural Networks","created":"2015-11-17","cited_by_count":796},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1905.05178","title":"Graph U-Nets","created":"2019-05-11","cited_by_count":492},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1908.01000","title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","created":"2019-07-31","cited_by_count":441},{"id":"1711.09869","title":"Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs","created":"2017-11-27","cited_by_count":385},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"2104.14548","title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","created":"2021-04-29","cited_by_count":326},{"id":"1605.05273","title":"Learning Convolutional Neural Networks for Graphs","created":"2016-05-17","cited_by_count":314},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"1511.02136","title":"Diffusion-Convolutional Neural Networks","created":"2015-11-06","cited_by_count":268},{"id":"2104.05704","title":"Escaping the Big Data Paradigm with Compact Transformers","created":"2021-04-12","cited_by_count":264},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"1506.05163","title":"Deep Convolutional Networks on Graph-Structured Data","created":"2015-06-16","cited_by_count":246},{"id":"1511.05298","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","created":"2015-11-17","cited_by_count":234},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"1901.01343","title":"Graph Neural Networks with convolutional ARMA filters","created":"2019-01-05","cited_by_count":185},{"id":"2104.12533","title":"Visformer: The Vision-friendly Transformer","created":"2021-04-26","cited_by_count":137},{"id":"2003.10477","title":"Distilling Knowledge from Graph Convolutional Networks","created":"2020-03-23","cited_by_count":129},{"id":"2106.02689","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","created":"2021-06-04","cited_by_count":127},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126},{"id":"2112.13492","title":"Vision Transformer for Small-Size Datasets","created":"2021-12-27","cited_by_count":122},{"id":"2104.07788","title":"PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models","created":"2021-04-15","cited_by_count":118},{"id":"1710.10370","title":"Topology Adaptive Graph Convolutional Networks","created":"2017-10-28","cited_by_count":113},{"id":"2109.01116","title":"An Empirical Study of Graph Contrastive Learning","created":"2021-09-02","cited_by_count":113},{"id":"2204.04879","title":"How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision","created":"2022-04-11","cited_by_count":102},{"id":"1803.03735","title":"Attention-based Graph Neural Network for Semi-supervised Learning","created":"2018-03-10","cited_by_count":101},{"id":"2107.08391","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","created":"2021-07-18","cited_by_count":101},{"id":"1904.00597","title":"Learning Combinatorial Embedding Networks for Deep Graph Matching","created":"2019-04-01","cited_by_count":99},{"id":"2105.12723","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","created":"2021-05-26","cited_by_count":97},{"id":"2202.03580","title":"Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited","created":"2022-02-04","cited_by_count":87},{"id":"2106.02466","title":"Graph Barlow Twins: A self-supervised representation learning framework for graphs","created":"2021-06-04","cited_by_count":85},{"id":"1909.04977","title":"CARS: Continuous Evolution for Efficient Neural Architecture Search","created":"2019-09-11","cited_by_count":79},{"id":"2108.13341","title":"Hire-MLP: Vision MLP via Hierarchical Rearrangement","created":"2021-08-30","cited_by_count":66},{"id":"2202.12015","title":"Learning to Merge Tokens in Vision Transformers","created":"2022-02-24","cited_by_count":65},{"id":"2111.12294","title":"An Image Patch is a Wave: Phase-Aware Vision MLP","created":"2021-11-24","cited_by_count":61},{"id":"2207.11681","title":"Learning Graph Neural Networks for Image Style Transfer","created":"2022-07-24","cited_by_count":29},{"id":"1904.04849","title":"Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks","created":"2019-04-09","cited_by_count":20},{"id":"2005.05815","title":"One-Shot Recognition of Manufacturing Defects in Steel Surfaces","created":"2020-05-12","cited_by_count":13},{"id":"2003.05271","title":"Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs","created":"2020-03-11","cited_by_count":6}],"next_cursor":null}