{"list":"other","total":57,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"1706.02515","title":"Self-Normalizing Neural Networks","created":"2017-06-08","cited_by_count":598},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"1603.02199","title":"Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection","created":"2016-03-07","cited_by_count":316},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248},{"id":"2008.05659","title":"What Should Not Be Contrastive in Contrastive Learning","created":"2020-08-13","cited_by_count":226},{"id":"1509.06825","title":"Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours","created":"2015-09-23","cited_by_count":209},{"id":"1606.07419","title":"Learning to Poke by Poking: Experiential Learning of Intuitive Physics","created":"2016-06-23","cited_by_count":154},{"id":"2112.01511","title":"The Surprising Effectiveness of Representation Learning for Visual Imitation","created":"2021-12-02","cited_by_count":154},{"id":"1509.06113","title":"Deep Spatial Autoencoders for Visuomotor Learning","created":"2015-09-21","cited_by_count":153},{"id":"2111.11429","title":"Benchmarking Detection Transfer Learning with Vision Transformers","created":"2021-11-22","cited_by_count":131},{"id":"1803.09956","title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","created":"2018-03-27","cited_by_count":128},{"id":"2106.12534","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","created":"2021-06-23","cited_by_count":122},{"id":"1909.06933","title":"Self-Supervised Correspondence in Visuomotor Policy Learning","created":"2019-09-16","cited_by_count":107},{"id":"2105.14829","title":"Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation","created":"2021-05-31","cited_by_count":85},{"id":"2203.13251","title":"Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation","created":"2022-03-24","cited_by_count":78},{"id":"1707.02267","title":"Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task","created":"2017-07-07","cited_by_count":66},{"id":"1612.06699","title":"Unsupervised Perceptual Rewards for Imitation Learning","created":"2016-12-20","cited_by_count":65},{"id":"2107.00646","title":"Learning to See before Learning to Act: Visual Pre-training for Manipulation","created":"2021-07-01","cited_by_count":51},{"id":"2004.04336","title":"MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion","created":"2020-04-09","cited_by_count":46},{"id":"1604.01360","title":"The Curious Robot: Learning Visual Representations via Physical Interactions","created":"2016-04-05","cited_by_count":38},{"id":"1609.03759","title":"3D Simulation for Robot Arm Control with Deep Q-Learning","created":"2016-09-13","cited_by_count":21},{"id":"2202.11092","title":"ReorientBot: Learning Object Reorientation for Specific-Posed Placement","created":"2022-02-22","cited_by_count":10}],"next_cursor":null}