{"list":"other","total":64,"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":"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1901.09948","title":"Surrogate Gradient Learning in Spiking Neural Networks","created":"2019-01-28","cited_by_count":626},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"1706.02609","title":"Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks","created":"2017-06-08","cited_by_count":406},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"2102.04159","title":"Deep Residual Learning in Spiking Neural Networks","created":"2021-02-08","cited_by_count":331},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"2011.05280","title":"Going Deeper With Directly-Trained Larger Spiking Neural Networks","created":"2020-10-29","cited_by_count":278},{"id":"2209.15425","title":"Spikformer: When Spiking Neural Network Meets Transformer","created":"2022-09-29","cited_by_count":271},{"id":"1903.06530","title":"Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection","created":"2019-03-12","cited_by_count":177},{"id":"2108.01390","title":"Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer","created":"2021-08-03","cited_by_count":177},{"id":"2307.01694","title":"Spike-driven Transformer","created":"2023-07-04","cited_by_count":146},{"id":"2005.01807","title":"Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation","created":"2020-05-04","cited_by_count":144},{"id":"2103.00476","title":"Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks","created":"2021-02-28","cited_by_count":139},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132},{"id":"2103.12593","title":"Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks","created":"2021-03-12","cited_by_count":115},{"id":"2209.13929","title":"Attention Spiking Neural Networks","created":"2022-09-28","cited_by_count":107},{"id":"2107.11711","title":"Temporal-wise Attention Spiking Neural Networks for Event Streams Classification","created":"2021-07-25","cited_by_count":106},{"id":"2112.08954","title":"Advancing Spiking Neural Networks towards Deep Residual Learning","created":"2021-12-15","cited_by_count":79},{"id":"2307.11411","title":"Deep Directly-Trained Spiking Neural Networks for Object Detection","created":"2023-07-21","cited_by_count":77},{"id":"2306.06189","title":"FasterViT: Fast Vision Transformers with Hierarchical Attention","created":"2023-06-09","cited_by_count":65},{"id":"2103.07372","title":"ACTION-Net: Multipath Excitation for Action Recognition","created":"2021-03-11","cited_by_count":63},{"id":"2110.07742","title":"Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentation","created":"2021-10-14","cited_by_count":55},{"id":"2209.07484","title":"Hydra Attention: Efficient Attention with Many Heads","created":"2022-09-15","cited_by_count":55},{"id":"2007.01204","title":"Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks","created":"2020-07-02","cited_by_count":47},{"id":"2211.09648","title":"HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors","created":"2022-11-17","cited_by_count":47},{"id":"2305.19868","title":"Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN","created":"2023-05-31","cited_by_count":46},{"id":"2107.03992","title":"A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware","created":"2021-07-08","cited_by_count":32},{"id":"2106.01288","title":"Bottom-up and top-down approaches for the design of neuromorphic processing systems: Tradeoffs and synergies between natural and artificial intelligence","created":"2021-06-02","cited_by_count":21},{"id":"2302.01194","title":"Complex Dynamic Neurons Improved Spiking Transformer Network for Efficient Automatic Speech Recognition","created":"2023-02-02","cited_by_count":20},{"id":"2207.02702","title":"Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentation","created":"2022-07-06","cited_by_count":15},{"id":"2103.08392","title":"The SpiNNaker 2 Processing Element Architecture for Hybrid Digital Neuromorphic Computing","created":"2021-03-15","cited_by_count":14},{"id":"2304.05659","title":"RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer","created":"2023-04-12","cited_by_count":13},{"id":"2308.08227","title":"Inherent Redundancy in Spiking Neural Networks","created":"2023-08-16","cited_by_count":13},{"id":"2008.09342","title":"Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs","created":"2020-08-21","cited_by_count":12},{"id":"2303.11860","title":"Online Transformers with Spiking Neurons for Fast Prosthetic Hand Control","created":"2023-03-21","cited_by_count":5},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2}],"next_cursor":null}