{"list":"other","total":53,"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":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"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":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"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":"1809.04356","title":"Deep learning for time series classification: a review","created":"2018-09-12","cited_by_count":576},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"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":"2009.11732","title":"A Unifying Review of Deep and Shallow Anomaly Detection","created":"2020-09-24","cited_by_count":425},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"2110.02642","title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy","created":"2021-10-06","cited_by_count":394},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2002.09291","title":"Transformer Hawkes Process","created":"2020-02-21","cited_by_count":235},{"id":"2002.12478","title":"Time Series Data Augmentation for Deep Learning: A Survey","created":"2020-02-27","cited_by_count":226},{"id":"2005.08514","title":"Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction","created":"2020-05-18","cited_by_count":218},{"id":"2201.07284","title":"TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data","created":"2022-01-18","cited_by_count":214},{"id":"2006.15595","title":"Rethinking Positional Encoding in Language Pre-training","created":"2020-06-28","cited_by_count":197},{"id":"2002.04236","title":"A review on outlier/anomaly detection in time series data","created":"2020-02-11","cited_by_count":189},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188},{"id":"1901.11117","title":"The Evolved Transformer","created":"2019-01-30","cited_by_count":180},{"id":"2001.02908","title":"Spatial-Temporal Transformer Networks for Traffic Flow Forecasting","created":"2020-01-09","cited_by_count":180},{"id":"2004.11886","title":"Lite Transformer with Long-Short Range Attention","created":"2020-04-24","cited_by_count":127},{"id":"1904.02874","title":"An Attentive Survey of Attention Models","created":"2019-04-05","cited_by_count":124},{"id":"2004.10240","title":"Deep Learning for Time Series Forecasting: Tutorial and Literature Survey","created":"2020-04-21","cited_by_count":117},{"id":"2104.03528","title":"Neural Temporal Point Processes: A Review","created":"2021-04-08","cited_by_count":114},{"id":"2104.03466","title":"Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT","created":"2021-04-08","cited_by_count":104},{"id":"1902.02181","title":"Attention in Natural Language Processing","created":"2019-02-04","cited_by_count":101},{"id":"2201.00044","title":"Transformer Embeddings of Irregularly Spaced Events and Their Participants","created":"2021-12-31","cited_by_count":93},{"id":"2106.09296","title":"Voice2Series: Reprogramming Acoustic Models for Time Series Classification","created":"2021-06-17","cited_by_count":91},{"id":"1910.10536","title":"Self-attention for raw optical Satellite Time Series Classification","created":"2019-10-23","cited_by_count":75},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63},{"id":"2103.14438","title":"Gated Transformer Networks for Multivariate Time Series Classification","created":"2021-03-26","cited_by_count":58},{"id":"1812.01767","title":"RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series","created":"2018-12-05","cited_by_count":54},{"id":"1808.07561","title":"Training Deeper Neural Machine Translation Models with Transparent Attention","created":"2018-08-22","cited_by_count":38},{"id":"2112.10251","title":"SSDNet: State Space Decomposition Neural Network for Time Series Forecasting","created":"2021-12-19","cited_by_count":15},{"id":"2109.08381","title":"From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba","created":"2021-09-17","cited_by_count":10},{"id":"2002.09535","title":"RobustPeriod: Time-Frequency Mining for Robust Multiple Periodicity Detection","created":"2020-02-21","cited_by_count":9}],"next_cursor":null}