{"list":"other","total":51,"rows":[{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"1810.02890","title":"HG-DAgger: Interactive Imitation Learning with Human Experts","created":"2018-10-05","cited_by_count":266},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260},{"id":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209},{"id":"2201.02610","title":"Embodied Hands: Modeling and Capturing Hands and Bodies Together","created":"2022-01-07","cited_by_count":181},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169},{"id":"1707.03374","title":"Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation","created":"2017-07-11","cited_by_count":167},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2303.14158","title":"BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects","created":"2023-03-24","cited_by_count":148},{"id":"2403.12910","title":"Yell At Your Robot: Improving On-the-Fly from Language Corrections","created":"2024-03-19","cited_by_count":124},{"id":"1912.04344","title":"Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations","created":"2019-12-09","cited_by_count":107},{"id":"1912.04443","title":"AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos","created":"2019-12-10","cited_by_count":105},{"id":"2311.16098","title":"On Bringing Robots Home","created":"2023-11-27","cited_by_count":101},{"id":"1807.08364","title":"EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning","created":"2018-07-22","cited_by_count":100},{"id":"1804.06534","title":"Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimation","created":"2018-04-18","cited_by_count":92},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87},{"id":"2201.12716","title":"You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration","created":"2022-01-30","cited_by_count":81},{"id":"1912.02400","title":"Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space","created":"2019-12-05","cited_by_count":78},{"id":"1610.05729","title":"Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm","created":"2016-10-18","cited_by_count":66},{"id":"1612.06699","title":"Unsupervised Perceptual Rewards for Imitation Learning","created":"2016-12-20","cited_by_count":65},{"id":"1506.03607","title":"P-CNN: Pose-based CNN Features for Action Recognition","created":"2015-06-11","cited_by_count":58},{"id":"1908.11587","title":"Copy-and-Paste Networks for Deep Video Inpainting","created":"2019-08-30","cited_by_count":58},{"id":"2403.12943","title":"Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers","created":"2024-03-19","cited_by_count":52},{"id":"1903.00640","title":"Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety","created":"2019-03-02","cited_by_count":49},{"id":"1907.05518","title":"Graph-Structured Visual Imitation","created":"2019-07-11","cited_by_count":43},{"id":"2107.08829","title":"Visual Adversarial Imitation Learning using Variational Models","created":"2021-07-16","cited_by_count":42},{"id":"1911.00232","title":"Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding","created":"2019-11-01","cited_by_count":37},{"id":"2211.13225","title":"Learning to Imitate Object Interactions from Internet Videos","created":"2022-11-23","cited_by_count":34},{"id":"2306.13818","title":"AR2-D2:Training a Robot Without a Robot","created":"2023-06-23","cited_by_count":27},{"id":"2108.05675","title":"Learning Visual Affordance Grounding from Demonstration Videos","created":"2021-08-12","cited_by_count":25},{"id":"2103.05079","title":"Domain-Robust Visual Imitation Learning with Mutual Information Constraints","created":"2021-03-08","cited_by_count":20},{"id":"2207.03395","title":"Unified Learning from Demonstrations, Corrections, and Preferences during Physical Human-Robot Interaction","created":"2022-07-07","cited_by_count":19},{"id":"2211.09019","title":"Learning Reward Functions for Robotic Manipulation by Observing Humans","created":"2022-11-16","cited_by_count":17},{"id":"2305.06289","title":"Learning Video-Conditioned Policies for Unseen Manipulation Tasks","created":"2023-05-10","cited_by_count":16},{"id":"2003.06066","title":"Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraft","created":"2020-03-12","cited_by_count":15},{"id":"2007.02701","title":"Scaling Imitation Learning in Minecraft","created":"2020-07-06","cited_by_count":12},{"id":"2402.07127","title":"Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulation","created":"2024-02-11","cited_by_count":11},{"id":"2011.06118","title":"I Know What You Meant: Learning Human Objectives by (Under)estimating Their Choice Set","created":"2020-11-11","cited_by_count":9},{"id":"2403.13281","title":"Waypoint-Based Reinforcement Learning for Robot Manipulation Tasks","created":"2024-03-20","cited_by_count":9},{"id":"2107.01995","title":"Here's What I've Learned: Asking Questions that Reveal Reward Learning","created":"2021-07-02","cited_by_count":8},{"id":"2211.02832","title":"Learning Fabric Manipulation in the Real World with Human Videos","created":"2022-11-05","cited_by_count":7},{"id":"2307.05959","title":"Giving Robots a Hand: Learning Generalizable Manipulation with Eye-in-Hand Human Video Demonstrations","created":"2023-07-12","cited_by_count":6},{"id":"2312.02312","title":"Visual Encoders for Data-Efficient Imitation Learning in Modern Video Games","created":"2023-12-04","cited_by_count":6},{"id":"2107.09650","title":"Learning to Share Autonomy Across Repeated Interaction","created":"2021-07-20","cited_by_count":5},{"id":"2205.09795","title":"SARI: Shared Autonomy across Repeated Interaction","created":"2022-05-19","cited_by_count":5},{"id":"2204.13613","title":"DoPose-6D dataset for object segmentation and 6D pose estimation","created":"2022-04-28","cited_by_count":4}],"next_cursor":null}