{"list":"other","total":79,"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"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":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"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":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"1901.09948","title":"Surrogate Gradient Learning in Spiking Neural Networks","created":"2019-01-28","cited_by_count":626},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"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":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"2102.04159","title":"Deep Residual Learning in Spiking Neural Networks","created":"2021-02-08","cited_by_count":331},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"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":"2109.12894","title":"Training Spiking Neural Networks Using Lessons From Deep Learning","created":"2021-09-27","cited_by_count":259},{"id":"1809.05793","title":"Direct Training for Spiking Neural Networks: Faster, Larger, Better","created":"2018-09-16","cited_by_count":233},{"id":"2202.11946","title":"Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting","created":"2022-02-24","cited_by_count":198},{"id":"1903.06530","title":"Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection","created":"2019-03-12","cited_by_count":177},{"id":"2310.16620","title":"SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence","created":"2023-10-25","cited_by_count":169},{"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":"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":"2108.00154","title":"CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention","created":"2021-07-31","cited_by_count":139},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132},{"id":"2303.04347","title":"Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks","created":"2023-03-08","cited_by_count":122},{"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":"2404.03663","title":"Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips","created":"2024-02-15","cited_by_count":103},{"id":"2301.03580","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","created":"2023-01-09","cited_by_count":94},{"id":"2205.00459","title":"Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation","created":"2022-05-01","cited_by_count":89},{"id":"2210.08344","title":"How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders","created":"2022-10-15","cited_by_count":86},{"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":"2407.20708","title":"Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection","created":"2024-07-30","cited_by_count":67},{"id":"2103.07372","title":"ACTION-Net: Multipath Excitation for Action Recognition","created":"2021-03-11","cited_by_count":63},{"id":"2011.06176","title":"LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing","created":"2020-11-12","cited_by_count":56},{"id":"2304.06793","title":"Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipeline","created":"2023-04-13","cited_by_count":52},{"id":"2210.04195","title":"Online Training Through Time for Spiking Neural Networks","created":"2022-10-09","cited_by_count":49},{"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":"2209.15159","title":"MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features","created":"2022-09-30","cited_by_count":44},{"id":"2304.01230","title":"SEENN: Towards Temporal Spiking Early-Exit Neural Networks","created":"2023-04-02","cited_by_count":41},{"id":"2304.12760","title":"Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies","created":"2023-04-25","cited_by_count":41},{"id":"2210.01208","title":"Masked Spiking Transformer","created":"2022-10-03","cited_by_count":39},{"id":"2302.14311","title":"Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks","created":"2023-02-28","cited_by_count":37},{"id":"2301.01146","title":"Rethinking Mobile Block for Efficient Attention-based Models","created":"2023-01-03","cited_by_count":36},{"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":"2401.02020","title":"Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket","created":"2024-01-04","cited_by_count":30},{"id":"2109.01905","title":"Spiking Neural Networks with Improved Inherent Recurrence Dynamics for Sequential Learning","created":"2021-09-04","cited_by_count":27},{"id":"2308.06582","title":"Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks","created":"2023-08-12","cited_by_count":26},{"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":"2403.00270","title":"Event-Driven Learning for Spiking Neural Networks","created":"2024-03-01","cited_by_count":15},{"id":"2205.07473","title":"Towards Lossless ANN-SNN Conversion under Ultra-Low Latency with Dual-Phase Optimization","created":"2022-05-16","cited_by_count":14},{"id":"2405.16466","title":"High-Performance Temporal Reversible Spiking Neural Networks with $O(L)$ Training Memory and $O(1)$ Inference Cost","created":"2024-05-26","cited_by_count":14},{"id":"2308.08227","title":"Inherent Redundancy in Spiking Neural Networks","created":"2023-08-16","cited_by_count":13},{"id":"2310.14576","title":"Tensor Decomposition Based Attention Module for Spiking Neural Networks","created":"2023-10-23","cited_by_count":8},{"id":"2312.07922","title":"Memory-Efficient Reversible Spiking Neural Networks","created":"2023-12-13","cited_by_count":6},{"id":"2407.20099","title":"RSC-SNN: Exploring the Trade-off Between Adversarial Robustness and Accuracy in Spiking Neural Networks via Randomized Smoothing Coding","created":"2024-07-29","cited_by_count":6},{"id":"2203.01158","title":"Rethinking Pretraining as a Bridge from ANNs to SNNs","created":"2022-03-02","cited_by_count":4},{"id":"2311.10802","title":"Is Conventional SNN Really Efficient? A Perspective from Network Quantization","created":"2023-11-17","cited_by_count":1}],"next_cursor":null}