{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1709.04875","title":"Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting","created":"2017-09-14","cited_by_count":1136},{"id":"1312.6203","title":"Spectral Networks and Locally Connected Networks on Graphs","created":"2013-12-21","cited_by_count":1102},{"id":"1704.04110","title":"DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks","created":"2017-04-13","cited_by_count":1013},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"1906.00121","title":"Graph WaveNet for Deep Spatial-Temporal Graph Modeling","created":"2019-05-31","cited_by_count":829},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1912.09363","title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","created":"2019-12-19","cited_by_count":761},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1907.00235","title":"Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting","created":"2019-06-29","cited_by_count":607},{"id":"2005.11650","title":"Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks","created":"2020-05-24","cited_by_count":566},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2007.02842","title":"Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting","created":"2020-07-06","cited_by_count":530},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2004.13408","title":"Time Series Forecasting With Deep Learning: A Survey","created":"2020-04-28","cited_by_count":459},{"id":"2010.02803","title":"A Transformer-based Framework for Multivariate Time Series Representation Learning","created":"2020-10-06","cited_by_count":453},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1911.08415","title":"GMAN: A Graph Multi-Attention Network for Traffic Prediction","created":"2019-11-11","cited_by_count":434},{"id":"1605.05273","title":"Learning Convolutional Neural Networks for Graphs","created":"2016-05-17","cited_by_count":314},{"id":"2105.06643","title":"Monash Time Series Forecasting Archive","created":"2021-05-14","cited_by_count":267},{"id":"1704.02971","title":"A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction","created":"2017-04-07","cited_by_count":245},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"1907.05321","title":"Time2Vec: Learning a Vector Representation of Time","created":"2019-07-11","cited_by_count":213},{"id":"2012.09641","title":"Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting","created":"2020-12-15","cited_by_count":213},{"id":"2004.08249","title":"Understanding the Difficulty of Training Transformers","created":"2020-04-17","cited_by_count":210},{"id":"2001.02908","title":"Spatial-Temporal Transformer Networks for Traffic Flow Forecasting","created":"2020-01-09","cited_by_count":180},{"id":"1910.05895","title":"Transformers without Tears: Improving the Normalization of Self-Attention","created":"2019-10-14","cited_by_count":153},{"id":"1809.04206","title":"Temporal Pattern Attention for Multivariate Time Series Forecasting","created":"2018-09-12","cited_by_count":125},{"id":"1703.04691","title":"Conditional Time Series Forecasting with Convolutional Neural Networks","created":"2017-03-14","cited_by_count":123},{"id":"2104.07788","title":"PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models","created":"2021-04-15","cited_by_count":118},{"id":"1910.10781","title":"Hierarchical Transformers for Long Document Classification","created":"2019-10-23","cited_by_count":104},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102},{"id":"2008.07404","title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","created":"2020-08-17","cited_by_count":98},{"id":"1902.09113","title":"Star-Transformer","created":"2019-02-25","cited_by_count":94},{"id":"2002.02887","title":"Meta-learning framework with applications to zero-shot time-series forecasting","created":"2020-02-07","cited_by_count":70},{"id":"2105.04371","title":"Poolingformer: Long Document Modeling with Pooling Attention","created":"2021-05-10","cited_by_count":60},{"id":"1905.11744","title":"Evaluating time series forecasting models: An empirical study on performance estimation methods","created":"2019-05-28","cited_by_count":53},{"id":"1911.04070","title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","created":"2019-11-11","cited_by_count":38},{"id":"2004.13342","title":"Scheduled DropHead: A Regularization Method for Transformer Models","created":"2020-04-28","cited_by_count":28},{"id":"2011.02266","title":"Optimizing Transformer for Low-Resource Neural Machine Translation","created":"2020-11-04","cited_by_count":24},{"id":"2105.03801","title":"Long-Span Summarization via Local Attention and Content Selection","created":"2021-05-08","cited_by_count":24},{"id":"2008.04882","title":"Spatiotemporal Attention for Multivariate Time Series Prediction and Interpretation","created":"2020-08-11","cited_by_count":18},{"id":"2009.14379","title":"Few-shot Learning for Time-series Forecasting","created":"2020-09-30","cited_by_count":16},{"id":"2104.04946","title":"UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost","created":"2021-04-11","cited_by_count":11},{"id":"1811.08600","title":"Contextualized Non-local Neural Networks for Sequence Learning","created":"2018-11-21","cited_by_count":7}],"next_cursor":null}