{"list":"other","total":63,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"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":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"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":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"1901.09948","title":"Surrogate Gradient Learning in Spiking Neural Networks","created":"2019-01-28","cited_by_count":626},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"1706.02609","title":"Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks","created":"2017-06-08","cited_by_count":406},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354},{"id":"2007.05785","title":"Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks","created":"2020-07-11","cited_by_count":345},{"id":"2102.04159","title":"Deep Residual Learning in Spiking Neural Networks","created":"2021-02-08","cited_by_count":331},{"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":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"1809.05793","title":"Direct Training for Spiking Neural Networks: Faster, Larger, Better","created":"2018-09-16","cited_by_count":233},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213},{"id":"2202.11946","title":"Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting","created":"2022-02-24","cited_by_count":198},{"id":"1803.09574","title":"Long short-term memory and learning-to-learn in networks of spiking neurons","created":"2018-03-26","cited_by_count":181},{"id":"2203.00555","title":"DeepNet: Scaling Transformers to 1,000 Layers","created":"2022-03-01","cited_by_count":178},{"id":"1806.05393","title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks","created":"2018-06-14","cited_by_count":176},{"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":"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":"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":"2302.13939","title":"SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks","created":"2023-02-27","cited_by_count":88},{"id":"2112.08954","title":"Advancing Spiking Neural Networks towards Deep Residual Learning","created":"2021-12-15","cited_by_count":79},{"id":"2303.15446","title":"SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications","created":"2023-03-27","cited_by_count":66},{"id":"2110.11417","title":"HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise","created":"2021-10-06","cited_by_count":65},{"id":"2210.13768","title":"GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks","created":"2022-10-25","cited_by_count":63},{"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":"1911.00822","title":"Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization","created":"2019-11-03","cited_by_count":45},{"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":"2006.03226","title":"Brain-inspired global-local learning incorporated with neuromorphic computing","created":"2020-06-05","cited_by_count":28},{"id":"2203.03952","title":"ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer","created":"2022-03-08","cited_by_count":28},{"id":"2203.07006","title":"Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions","created":"2022-03-14","cited_by_count":27},{"id":"2301.11929","title":"Training Full Spike Neural Networks via Auxiliary Accumulation Pathway","created":"2023-01-27","cited_by_count":26},{"id":"2005.07903","title":"Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition","created":"2020-05-16","cited_by_count":24},{"id":"2207.01580","title":"Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks","created":"2022-07-04","cited_by_count":24},{"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":"2211.10686","title":"Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Network","created":"2022-11-19","cited_by_count":19},{"id":"2110.05929","title":"One Timestep is All You Need: Training Spiking Neural Networks with Ultra Low Latency","created":"2021-10-01","cited_by_count":17},{"id":"2303.09681","title":"Highly Efficient 3D Human Pose Tracking from Events with Spiking Spatiotemporal Transformer","created":"2023-03-16","cited_by_count":10},{"id":"2001.00254","title":"A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks","created":"2020-01-01","cited_by_count":9},{"id":"2303.11860","title":"Online Transformers with Spiking Neurons for Fast Prosthetic Hand Control","created":"2023-03-21","cited_by_count":5},{"id":"2305.12148","title":"Probabilistic Modeling: Proving the Lottery Ticket Hypothesis in Spiking Neural Network","created":"2023-05-20","cited_by_count":3}],"next_cursor":null}