{"list":"other","total":53,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2005.12256","title":"Neural Topological SLAM for Visual Navigation","created":"2020-05-25","cited_by_count":195},{"id":"1709.08429","title":"DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks","created":"2017-09-25","cited_by_count":175},{"id":"2001.05049","title":"DeepFactors: Real-Time Probabilistic Dense Monocular SLAM","created":"2020-01-14","cited_by_count":117},{"id":"1801.02209","title":"Building Generalizable Agents with a Realistic and Rich 3D Environment","created":"2018-01-07","cited_by_count":109},{"id":"1910.14442","title":"Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environments","created":"2019-10-30","cited_by_count":90},{"id":"1807.07049","title":"Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias","created":"2018-07-18","cited_by_count":75},{"id":"1712.03931","title":"MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments","created":"2017-12-11","cited_by_count":66},{"id":"1804.08366","title":"VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry","created":"2018-04-23","cited_by_count":61},{"id":"1803.03642","title":"Deep Auxiliary Learning for Visual Localization and Odometry","created":"2018-03-09","cited_by_count":59},{"id":"2111.12993","title":"PolyViT: Co-training Vision Transformers on Images, Videos and Audio","created":"2021-11-25","cited_by_count":58},{"id":"1909.09803","title":"Visual Odometry Revisited: What Should Be Learnt?","created":"2019-09-21","cited_by_count":57},{"id":"1906.08236","title":"PyRobot: An Open-source Robotics Framework for Research and Benchmarking","created":"2019-06-19","cited_by_count":39},{"id":"2206.00997","title":"Is Mapping Necessary for Realistic PointGoal Navigation?","created":"2022-06-02","cited_by_count":35},{"id":"2105.07593","title":"Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation","created":"2021-05-17","cited_by_count":34},{"id":"2009.03231","title":"Integrating Egocentric Localization for More Realistic Point-Goal Navigation Agents","created":"2020-09-07","cited_by_count":27},{"id":"2108.11550","title":"The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation","created":"2021-08-26","cited_by_count":27},{"id":"1912.06321","title":"Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?","created":"2019-12-13","cited_by_count":26},{"id":"1901.10915","title":"Benchmarking Classic and Learned Navigation in Complex 3D Environments","created":"2019-01-30","cited_by_count":24},{"id":"1908.08031","title":"MuSHR: A Low-Cost, Open-Source Robotic Racecar for Education and Research","created":"2019-08-21","cited_by_count":18},{"id":"2107.08751","title":"Adversarial Continual Learning for Multi-Domain Hippocampal Segmentation","created":"2021-07-19","cited_by_count":14},{"id":"2105.09899","title":"DeepAVO: Efficient Pose Refining with Feature Distilling for Deep Visual Odometry","created":"2021-05-20","cited_by_count":6},{"id":"1907.11770","title":"To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual Environments","created":"2019-07-26","cited_by_count":5},{"id":"1612.00380","title":"Playing Doom with SLAM-Augmented Deep Reinforcement Learning","created":"2016-12-01","cited_by_count":4}],"next_cursor":null}