{"list":"other","total":120,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"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":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1906.05113","title":"A Survey of Autonomous Driving: Common Practices and Emerging Technologies","created":"2019-06-12","cited_by_count":379},{"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":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"1612.07828","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","created":"2016-12-22","cited_by_count":288},{"id":"1807.00412","title":"Learning to Drive in a Day","created":"2018-07-01","cited_by_count":273},{"id":"1905.06113","title":"Human Motion Trajectory Prediction: A Survey","created":"2019-05-15","cited_by_count":232},{"id":"1704.07809","title":"Hand Keypoint Detection in Single Images using Multiview Bootstrapping","created":"2017-04-25","cited_by_count":231},{"id":"1904.12659","title":"Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2019-04-26","cited_by_count":228},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"1702.03920","title":"Cognitive Mapping and Planning for Visual Navigation","created":"2017-02-13","cited_by_count":212},{"id":"2005.12256","title":"Neural Topological SLAM for Visual Navigation","created":"2020-05-25","cited_by_count":195},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"2007.03672","title":"Long-term Human Motion Prediction with Scene Context","created":"2020-07-07","cited_by_count":192},{"id":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"id":"1710.04689","title":"Social Attention: Modeling Attention in Human Crowds","created":"2017-10-12","cited_by_count":186},{"id":"1809.08835","title":"Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning","created":"2018-09-24","cited_by_count":175},{"id":"1612.03153","title":"Panoptic Studio: A Massively Multiview System for Social Interaction Capture","created":"2016-12-09","cited_by_count":173},{"id":"1712.03316","title":"IQA: Visual Question Answering in Interactive Environments","created":"2017-12-09","cited_by_count":155},{"id":"1902.09130","title":"An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition","created":"2019-02-25","cited_by_count":151},{"id":"1607.07043","title":"Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition","created":"2016-07-24","cited_by_count":143},{"id":"1703.08862","title":"Socially Aware Motion Planning with Deep Reinforcement Learning","created":"2017-03-26","cited_by_count":136},{"id":"1405.2941","title":"Cross-view Action Modeling, Learning and Recognition","created":"2014-05-12","cited_by_count":134},{"id":"2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","created":"2020-10-19","cited_by_count":133},{"id":"1406.2984","title":"Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation","created":"2014-06-11","cited_by_count":129},{"id":"1702.05374","title":"Domain Adaptation for Visual Applications: A Comprehensive Survey","created":"2017-02-17","cited_by_count":128},{"id":"1704.00159","title":"Compositional Human Pose Regression","created":"2017-04-01","cited_by_count":124},{"id":"1708.01566","title":"Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes","created":"2017-08-04","cited_by_count":122},{"id":"1507.06550","title":"Human Pose Estimation with Iterative Error Feedback","created":"2015-07-23","cited_by_count":121},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"2008.09285","title":"Occupancy Anticipation for Efficient Exploration and Navigation","created":"2020-08-21","cited_by_count":106},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"1804.00168","title":"Learning to Navigate in Cities Without a Map","created":"2018-03-31","cited_by_count":104},{"id":"1904.03461","title":"Embodied Question Answering in Photorealistic Environments with Point Cloud Perception","created":"2019-04-06","cited_by_count":103},{"id":"1603.02729","title":"Revisiting Active Perception","created":"2016-03-08","cited_by_count":94},{"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":"1803.08319","title":"Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World","created":"2018-03-22","cited_by_count":82},{"id":"1707.04818","title":"RED: Reinforced Encoder-Decoder Networks for Action Anticipation","created":"2017-07-16","cited_by_count":78},{"id":"2006.05768","title":"Deep Drone Acrobatics","created":"2020-06-10","cited_by_count":75},{"id":"1702.07432","title":"Multi-Context Attention for Human Pose Estimation","created":"2017-02-24","cited_by_count":66},{"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":"2006.10034","title":"Semantic Visual Navigation by Watching YouTube Videos","created":"2020-06-17","cited_by_count":60},{"id":"1506.02897","title":"Flowing ConvNets for Human Pose Estimation in Videos","created":"2015-06-09","cited_by_count":55},{"id":"1605.04988","title":"Going Deeper into Action Recognition: A Survey","created":"2016-05-16","cited_by_count":55},{"id":"1910.11322","title":"TexturePose: Supervising Human Mesh Estimation with Texture Consistency","created":"2019-10-24","cited_by_count":53},{"id":"1912.00915","title":"Just Ask:An Interactive Learning Framework for Vision and Language Navigation","created":"2019-12-02","cited_by_count":53},{"id":"1710.02322","title":"Human Pose Regression by Combining Indirect Part Detection and Contextual Information","created":"2017-10-06","cited_by_count":52},{"id":"1710.02543","title":"Socially Compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation Learning","created":"2017-10-06","cited_by_count":52},{"id":"1609.01743","title":"Human pose estimation via Convolutional Part Heatmap Regression","created":"2016-09-06","cited_by_count":51},{"id":"1702.08272","title":"A Dataset for Developing and Benchmarking Active Vision","created":"2017-02-27","cited_by_count":50},{"id":"2006.09367","title":"Semantic Curiosity for Active Visual Learning","created":"2020-06-16","cited_by_count":45},{"id":"1509.05016","title":"Recurrent Neural Networks for Driver Activity Anticipation via Sensory-Fusion Architecture","created":"2015-09-16","cited_by_count":42},{"id":"1612.07796","title":"First-Person Activity Forecasting with Online Inverse Reinforcement Learning","created":"2016-12-22","cited_by_count":40},{"id":"1709.00507","title":"Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks","created":"2017-09-01","cited_by_count":38},{"id":"1708.00489","title":"Active Learning for Convolutional Neural Networks: A Core-Set Approach","created":"2017-08-01","cited_by_count":36},{"id":"2008.02004","title":"Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes","created":"2020-08-05","cited_by_count":31},{"id":"2005.12813","title":"AlphaPilot: Autonomous Drone Racing","created":"2020-05-26","cited_by_count":30},{"id":"1511.07041","title":"SceneNet: Understanding Real World Indoor Scenes With Synthetic Data","created":"2015-11-22","cited_by_count":29},{"id":"1912.06321","title":"Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?","created":"2019-12-13","cited_by_count":26},{"id":"1709.08528","title":"A Data-driven Model for Interaction-aware Pedestrian Motion Prediction in Object Cluttered Environments","created":"2017-09-25","cited_by_count":24},{"id":"1901.10915","title":"Benchmarking Classic and Learned Navigation in Complex 3D Environments","created":"2019-01-30","cited_by_count":24},{"id":"2009.05429","title":"Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments","created":"2020-09-11","cited_by_count":21},{"id":"1504.05524","title":"A robust and efficient video representation for action recognition","created":"2015-04-21","cited_by_count":20},{"id":"2004.00116","title":"APPLD: Adaptive Planner Parameter Learning from Demonstration","created":"2020-03-31","cited_by_count":20},{"id":"2009.04300","title":"SEAN: Social Environment for Autonomous Navigation","created":"2020-09-09","cited_by_count":18},{"id":"2003.01062","title":"ProxEmo: Gait-based Emotion Learning and Multi-view Proxemic Fusion for Socially-Aware Robot Navigation","created":"2020-03-02","cited_by_count":17}],"next_cursor":"100"}