{"list":"other","total":59,"rows":[{"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":"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"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":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"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":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245},{"id":"2003.01587","title":"Image Matching across Wide Baselines: From Paper to Practice","created":"2020-03-03","cited_by_count":225},{"id":"2303.18240","title":"Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?","created":"2023-03-31","cited_by_count":218},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"2005.12256","title":"Neural Topological SLAM for Visual Navigation","created":"2020-05-25","cited_by_count":195},{"id":"2202.11742","title":"Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation","created":"2022-02-23","cited_by_count":193},{"id":"2206.12403","title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","created":"2022-06-24","cited_by_count":178},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162},{"id":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156},{"id":"2201.10029","title":"PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning","created":"2022-01-25","cited_by_count":150},{"id":"1903.03878","title":"Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks","created":"2019-03-09","cited_by_count":107},{"id":"1909.06933","title":"Self-Supervised Correspondence in Visuomotor Policy Learning","created":"2019-09-16","cited_by_count":107},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"1702.08360","title":"Neural Map: Structured Memory for Deep Reinforcement Learning","created":"2017-02-27","cited_by_count":90},{"id":"2204.13226","title":"Offline Visual Representation Learning for Embodied Navigation","created":"2022-04-27","cited_by_count":75},{"id":"2003.00368","title":"The Marathon 2: A Navigation System","created":"2020-03-01","cited_by_count":70},{"id":"2303.07798","title":"OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav","created":"2023-03-14","cited_by_count":70},{"id":"2103.16317","title":"Deep Regression on Manifolds: A 3D Rotation Case Study","created":"2021-03-30","cited_by_count":67},{"id":"2202.02440","title":"Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation","created":"2022-02-05","cited_by_count":67},{"id":"2101.05181","title":"Memory-Augmented Reinforcement Learning for Image-Goal Navigation","created":"2021-01-13","cited_by_count":66},{"id":"2202.11271","title":"ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints","created":"2022-02-23","cited_by_count":58},{"id":"1810.11181","title":"Neural Modular Control for Embodied Question Answering","created":"2018-10-26","cited_by_count":56},{"id":"2211.15876","title":"Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instances","created":"2022-11-29","cited_by_count":55},{"id":"2106.04531","title":"RobustNav: Towards Benchmarking Robustness in Embodied Navigation","created":"2021-06-08","cited_by_count":54},{"id":"2105.09447","title":"VTNet: Visual Transformer Network for Object Goal Navigation","created":"2021-05-20","cited_by_count":51},{"id":"2304.01192","title":"Navigating to Objects Specified by Images","created":"2023-04-03","cited_by_count":51},{"id":"2106.03336","title":"Wide-Baseline Relative Camera Pose Estimation with Directional Learning","created":"2021-06-07","cited_by_count":49},{"id":"1702.01381","title":"Relative Camera Pose Estimation Using Convolutional Neural Networks","created":"2017-02-05","cited_by_count":47},{"id":"2205.15761","title":"Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark","created":"2022-05-31","cited_by_count":27},{"id":"2002.02286","title":"EgoMap: Projective mapping and structured egocentric memory for Deep RL","created":"2020-01-24","cited_by_count":23},{"id":"2210.05129","title":"Multi-Object Navigation with dynamically learned neural implicit representations","created":"2022-10-11","cited_by_count":21},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18},{"id":"2107.06011","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","created":"2021-07-13","cited_by_count":17},{"id":"2108.06105","title":"Image-Goal Navigation in Complex Environments via Modular Learning","created":"2021-08-13","cited_by_count":10},{"id":"2207.00052","title":"Visual Pre-training for Navigation: What Can We Learn from Noise?","created":"2022-06-30","cited_by_count":8},{"id":"2201.05816","title":"A Critical Analysis of Image-based Camera Pose Estimation Techniques","created":"2022-01-15","cited_by_count":7}],"next_cursor":null}