{"list":"other","total":59,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"2010.02803","title":"A Transformer-based Framework for Multivariate Time Series Representation Learning","created":"2020-10-06","cited_by_count":453},{"id":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"id":"2010.16061","title":"Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation","created":"2020-10-11","cited_by_count":425},{"id":"2106.14112","title":"Time-Series Representation Learning via Temporal and Contextual Contrasting","created":"2021-06-26","cited_by_count":345},{"id":"2104.14548","title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","created":"2021-04-29","cited_by_count":326},{"id":"1901.09005","title":"Revisiting Self-Supervised Visual Representation Learning","created":"2019-01-25","cited_by_count":251},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"2106.00750","title":"Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding","created":"2021-06-01","cited_by_count":224},{"id":"2006.07529","title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","created":"2020-06-13","cited_by_count":216},{"id":"1905.01235","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","created":"2019-05-03","cited_by_count":201},{"id":"1910.12638","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","created":"2019-10-25","cited_by_count":198},{"id":"2007.06028","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","created":"2020-07-12","cited_by_count":188},{"id":"1904.03240","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","created":"2019-04-05","cited_by_count":186},{"id":"2010.05731","title":"Probing Pretrained Language Models for Lexical Semantics","created":"2020-10-12","cited_by_count":156},{"id":"1706.00527","title":"Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks","created":"2017-06-02","cited_by_count":131},{"id":"2110.05025","title":"Self-supervised Learning is More Robust to Dataset Imbalance","created":"2021-10-11","cited_by_count":123},{"id":"1907.11879","title":"Multi-task Self-Supervised Learning for Human Activity Detection","created":"2019-07-27","cited_by_count":102},{"id":"2105.05837","title":"When Does Contrastive Visual Representation Learning Work?","created":"2021-05-12","cited_by_count":92},{"id":"1910.12607","title":"Generative Pre-Training for Speech with Autoregressive Predictive Coding","created":"2019-10-23","cited_by_count":82},{"id":"1904.13132","title":"A critical analysis of self-supervision, or what we can learn from a single image","created":"2019-04-30","cited_by_count":76},{"id":"2011.11542","title":"Exploring Contrastive Learning in Human Activity Recognition for Healthcare","created":"2020-11-23","cited_by_count":75},{"id":"2011.14097","title":"Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding","created":"2020-11-28","cited_by_count":58},{"id":"1803.09672","title":"On the Intrinsic Dimensionality of Image Representations","created":"2018-03-26","cited_by_count":57},{"id":"2012.05333","title":"Contrastive Predictive Coding for Human Activity Recognition","created":"2020-12-09","cited_by_count":55},{"id":"1802.07802","title":"Protecting Sensory Data against Sensitive Inferences","created":"2018-02-21","cited_by_count":45},{"id":"2007.13018","title":"Federated Self-Supervised Learning of Multi-Sensor Representations for Embedded Intelligence","created":"2020-07-25","cited_by_count":40},{"id":"2202.05998","title":"What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks?","created":"2022-02-12","cited_by_count":40},{"id":"2001.10603","title":"Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction","created":"2020-01-28","cited_by_count":38},{"id":"2102.06073","title":"SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data","created":"2021-02-11","cited_by_count":31},{"id":"2010.08377","title":"On the surprising similarities between supervised and self-supervised models","created":"2020-10-16","cited_by_count":29},{"id":"2010.11481","title":"Similarity Analysis of Self-Supervised Speech Representations","created":"2020-10-22","cited_by_count":26},{"id":"2004.05274","title":"Improved Speech Representations with Multi-Target Autoregressive Predictive Coding","created":"2020-04-11","cited_by_count":23},{"id":"2110.00528","title":"Do Self-Supervised and Supervised Methods Learn Similar Visual Representations?","created":"2021-10-01","cited_by_count":23},{"id":"2006.05675","title":"IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition","created":"2020-05-29","cited_by_count":22},{"id":"2202.00758","title":"ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition","created":"2022-02-01","cited_by_count":22},{"id":"2009.13233","title":"Sense and Learn: Self-Supervision for Omnipresent Sensors","created":"2020-09-28","cited_by_count":21},{"id":"2004.11992","title":"Extending and Analyzing Self-Supervised Learning Across Domains","created":"2020-04-24","cited_by_count":20},{"id":"2111.07089","title":"Evaluating Contrastive Learning on Wearable Timeseries for Downstream Clinical Outcomes","created":"2021-11-13","cited_by_count":8},{"id":"1907.11438","title":"LINSPECTOR WEB: A Multilingual Probing Suite for Word Representations","created":"2019-07-26","cited_by_count":5},{"id":"2012.03598","title":"Self-supervised Deep Learning for Reading Activity Classification","created":"2020-12-07","cited_by_count":1}],"next_cursor":null}