{"list":"other","total":69,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"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":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"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":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1312.6203","title":"Spectral Networks and Locally Connected Networks on Graphs","created":"2013-12-21","cited_by_count":1102},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","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":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1806.03536","title":"Representation Learning on Graphs with Jumping Knowledge Networks","created":"2018-06-09","cited_by_count":877},{"id":"1907.10903","title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification","created":"2019-07-25","cited_by_count":680},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"1611.08402","title":"Geometric deep learning on graphs and manifolds using mixture model CNNs","created":"2016-11-25","cited_by_count":468},{"id":"1905.00067","title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","created":"2019-04-30","cited_by_count":443},{"id":"1911.05485","title":"Diffusion Improves Graph Learning","created":"2019-10-28","cited_by_count":414},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"1605.05273","title":"Learning Convolutional Neural Networks for Graphs","created":"2016-05-17","cited_by_count":314},{"id":"1909.12223","title":"PairNorm: Tackling Oversmoothing in GNNs","created":"2019-09-26","cited_by_count":297},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"1511.02136","title":"Diffusion-Convolutional Neural Networks","created":"2015-11-06","cited_by_count":268},{"id":"1506.05163","title":"Deep Convolutional Networks on Graph-Structured Data","created":"2015-06-16","cited_by_count":246},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216},{"id":"2006.13009","title":"Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings","created":"2020-06-21","cited_by_count":214},{"id":"1705.07664","title":"CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters","created":"2017-05-22","cited_by_count":203},{"id":"2206.00272","title":"Vision GNN: An Image is Worth Graph of Nodes","created":"2022-06-01","cited_by_count":186},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"1809.05343","title":"Adaptive Sampling Towards Fast Graph Representation Learning","created":"2018-09-14","cited_by_count":180},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"1801.03226","title":"Adaptive Graph Convolutional Neural Networks","created":"2018-01-10","cited_by_count":155},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155},{"id":"2108.00154","title":"CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention","created":"2021-07-31","cited_by_count":139},{"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":"1810.10220","title":"DSFD: Dual Shot Face Detector","created":"2018-10-24","cited_by_count":116},{"id":"1805.11724","title":"Rethinking Knowledge Graph Propagation for Zero-Shot Learning","created":"2018-05-29","cited_by_count":87},{"id":"1912.07872","title":"Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification","created":"2019-12-17","cited_by_count":79},{"id":"2003.14247","title":"DPGN: Distribution Propagation Graph Network for Few-shot Learning","created":"2020-03-31","cited_by_count":79},{"id":"2203.06398","title":"SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection","created":"2022-03-12","cited_by_count":74},{"id":"1908.06955","title":"Dynamic Graph Message Passing Networks","created":"2019-08-19","cited_by_count":62},{"id":"1908.04942","title":"Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation","created":"2019-08-14","cited_by_count":57},{"id":"2006.12087","title":"Progressive Graph Learning for Open-Set Domain Adaptation","created":"2020-06-22","cited_by_count":56},{"id":"2007.09690","title":"Class-wise Dynamic Graph Convolution for Semantic Segmentation","created":"2020-07-19","cited_by_count":44},{"id":"2102.08098","title":"GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training","created":"2021-02-16","cited_by_count":44},{"id":"1908.00059","title":"GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension","created":"2019-07-31","cited_by_count":41},{"id":"2203.13006","title":"Compound Domain Generalization via Meta-Knowledge Encoding","created":"2022-03-24","cited_by_count":40},{"id":"2104.00808","title":"Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation","created":"2021-04-01","cited_by_count":37},{"id":"2106.01401","title":"Container: Context Aggregation Network","created":"2021-06-02","cited_by_count":37},{"id":"2206.09325","title":"EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm","created":"2022-06-19","cited_by_count":27},{"id":"2004.06272","title":"Bidirectional Graph Reasoning Network for Panoptic Segmentation","created":"2020-04-14","cited_by_count":26},{"id":"2108.00580","title":"GraphFPN: Graph Feature Pyramid Network for Object Detection","created":"2021-08-02","cited_by_count":25},{"id":"2105.15089","title":"Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model","created":"2021-05-31","cited_by_count":20},{"id":"2102.02038","title":"Isometric Propagation Network for Generalized Zero-shot Learning","created":"2021-02-03","cited_by_count":18},{"id":"2301.01156","title":"Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation","created":"2023-01-03","cited_by_count":12},{"id":"2201.10781","title":"ASFD: Automatic and Scalable Face Detector","created":"2022-01-26","cited_by_count":9}],"next_cursor":null}