{"list":"other","total":57,"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":"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"1712.02560","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2017-12-07","cited_by_count":683},{"id":"1605.06636","title":"Deep Transfer Learning with Joint Adaptation Networks","created":"2016-05-21","cited_by_count":612},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"id":"1901.00976","title":"Contrastive Adaptation Network for Unsupervised Domain Adaptation","created":"2019-01-04","cited_by_count":407},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"1603.04779","title":"Revisiting Batch Normalization For Practical Domain Adaptation","created":"2016-03-15","cited_by_count":288},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272},{"id":"1704.01705","title":"Generate To Adapt: Aligning Domains using Generative Adversarial Networks","created":"2017-04-06","cited_by_count":183},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"2109.06165","title":"CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation","created":"2021-09-13","cited_by_count":129},{"id":"1909.11825","title":"Unsupervised Domain Adaptation through Self-Supervision","created":"2019-09-26","cited_by_count":116},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"1907.12743","title":"Temporal Attentive Alignment for Large-Scale Video Domain Adaptation","created":"2019-07-30","cited_by_count":100},{"id":"2103.13915","title":"An Image is Worth 16x16 Words, What is a Video Worth?","created":"2021-03-25","cited_by_count":87},{"id":"2012.06399","title":"Spatial Temporal Transformer Network for Skeleton-based Action Recognition","created":"2020-12-11","cited_by_count":77},{"id":"1704.08082","title":"AutoDIAL: Automatic DomaIn Alignment Layers","created":"2017-04-26","cited_by_count":75},{"id":"1903.03215","title":"Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss","created":"2019-03-07","cited_by_count":67},{"id":"1912.10405","title":"Adversarial Cross-Domain Action Recognition with Co-Attention","created":"2019-12-22","cited_by_count":51},{"id":"1711.08561","title":"Adversarial Feature Augmentation for Unsupervised Domain Adaptation","created":"2017-11-23","cited_by_count":48},{"id":"2102.05775","title":"AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition","created":"2021-02-10","cited_by_count":48},{"id":"2108.11974","title":"Learning Cross-modal Contrastive Features for Video Domain Adaptation","created":"2021-08-26","cited_by_count":47},{"id":"1805.01386","title":"Boosting Domain Adaptation by Discovering Latent Domains","created":"2018-05-03","cited_by_count":46},{"id":"2101.03904","title":"Trear: Transformer-based RGB-D Egocentric Action Recognition","created":"2021-01-05","cited_by_count":39},{"id":"2105.14138","title":"Transformer-Based Source-Free Domain Adaptation","created":"2021-05-28","cited_by_count":30},{"id":"2006.10297","title":"Joint Contrastive Learning for Unsupervised Domain Adaptation","created":"2020-06-18","cited_by_count":25},{"id":"2003.08264","title":"Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels","created":"2020-03-18","cited_by_count":24},{"id":"2107.00606","title":"Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition","created":"2021-07-01","cited_by_count":24},{"id":"2106.05058","title":"Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition","created":"2021-06-09","cited_by_count":11},{"id":"1906.05199","title":"Tackling Partial Domain Adaptation with Self-Supervision","created":"2019-06-12","cited_by_count":9},{"id":"2006.08247","title":"Learn to cycle: Time-consistent feature discovery for action recognition","created":"2020-06-15","cited_by_count":8},{"id":"2007.10321","title":"Hierarchical Contrastive Motion Learning for Video Action Recognition","created":"2020-07-20","cited_by_count":8}],"next_cursor":null}