{"list":"other","total":64,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"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":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"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":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"2101.02692","title":"Where2Act: From Pixels to Actions for Articulated 3D Objects","created":"2021-01-07","cited_by_count":182},{"id":"2104.03304","title":"Hand-Object Contact Consistency Reasoning for Human Grasps Generation","created":"2021-04-07","cited_by_count":160},{"id":"1912.11913","title":"Category-Level Articulated Object Pose Estimation","created":"2019-12-26","cited_by_count":159},{"id":"2011.01975","title":"Rearrangement: A Challenge for Embodied AI","created":"2020-11-03","cited_by_count":155},{"id":"1606.07419","title":"Learning to Poke by Poking: Experiential Learning of Intuitive Physics","created":"2016-06-23","cited_by_count":154},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"1904.06830","title":"ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging","created":"2019-04-15","cited_by_count":147},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"1709.07326","title":"AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection","created":"2017-09-21","cited_by_count":128},{"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":"2012.00924","title":"CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction","created":"2020-12-02","cited_by_count":128},{"id":"1301.3592","title":"Deep Learning for Detecting Robotic Grasps","created":"2013-01-16","cited_by_count":116},{"id":"1903.01959","title":"Learning Exploration Policies for Navigation","created":"2019-03-05","cited_by_count":116},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"1909.10159","title":"Self-supervised 6D Object Pose Estimation for Robot Manipulation","created":"2019-09-23","cited_by_count":101},{"id":"2009.01439","title":"Learning Dexterous Grasping with Object-Centric Visual Affordances","created":"2020-09-03","cited_by_count":85},{"id":"2103.16130","title":"Active Learning for Deep Object Detection via Probabilistic Modeling","created":"2021-03-30","cited_by_count":79},{"id":"1604.03670","title":"Interactive Perception: Leveraging Action in Perception and Perception in Action","created":"2016-04-13","cited_by_count":78},{"id":"1412.3128","title":"Real-Time Grasp Detection Using Convolutional Neural Networks","created":"2014-12-09","cited_by_count":76},{"id":"1903.05690","title":"Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments","created":"2019-03-13","cited_by_count":72},{"id":"2008.09241","title":"Learning Affordance Landscapes for Interaction Exploration in 3D Environments","created":"2020-08-21","cited_by_count":65},{"id":"1906.03853","title":"DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions","created":"2019-06-10","cited_by_count":63},{"id":"2004.09044","title":"Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense","created":"2020-04-20","cited_by_count":62},{"id":"2001.02192","title":"An Exploration of Embodied Visual Exploration","created":"2020-01-07","cited_by_count":58},{"id":"1812.10972","title":"Reasoning About Physical Interactions with Object-Oriented Prediction and Planning","created":"2018-12-28","cited_by_count":51},{"id":"1910.13675","title":"Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly","created":"2019-10-30","cited_by_count":51},{"id":"1910.14218","title":"S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes","created":"2019-10-31","cited_by_count":51},{"id":"2106.15087","title":"O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning","created":"2021-06-29","cited_by_count":46},{"id":"2006.09367","title":"Semantic Curiosity for Active Visual Learning","created":"2020-06-16","cited_by_count":45},{"id":"2105.01047","title":"Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery","created":"2021-05-03","cited_by_count":45},{"id":"1511.06015","title":"Active Object Localization with Deep Reinforcement Learning","created":"2015-11-18","cited_by_count":42},{"id":"2003.12045","title":"Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects","created":"2020-03-26","cited_by_count":40},{"id":"1604.01360","title":"The Curious Robot: Learning Visual Representations via Physical Interactions","created":"2016-04-05","cited_by_count":38},{"id":"1609.09025","title":"Learning to Push by Grasping: Using multiple tasks for effective learning","created":"2016-09-28","cited_by_count":37},{"id":"1910.11669","title":"Learning Task-Oriented Grasping from Human Activity Datasets","created":"2019-10-25","cited_by_count":32},{"id":"1906.02729","title":"3D-RelNet: Joint Object and Relational Network for 3D Prediction","created":"2019-06-06","cited_by_count":28},{"id":"1603.05600","title":"\"What happens if...\" Learning to Predict the Effect of Forces in Images","created":"2016-03-17","cited_by_count":23},{"id":"2109.01097","title":"The Functional Correspondence Problem","created":"2021-09-02","cited_by_count":20},{"id":"1806.08354","title":"Learning Instance Segmentation by Interaction","created":"2018-06-21","cited_by_count":18},{"id":"2006.09306","title":"Learning About Objects by Learning to Interact with Them","created":"2020-06-16","cited_by_count":14},{"id":"2005.09484","title":"Self-supervised Transfer Learning for Instance Segmentation through Physical Interaction","created":"2020-05-19","cited_by_count":13},{"id":"1605.01679","title":"Learning Action Maps of Large Environments via First-Person Vision","created":"2016-05-05","cited_by_count":11},{"id":"2109.08817","title":"Learning to Regrasp by Learning to Place","created":"2021-09-18","cited_by_count":11},{"id":"1604.00066","title":"To Fall Or Not To Fall: A Visual Approach to Physical Stability Prediction","created":"2016-03-31","cited_by_count":10},{"id":"1904.04404","title":"Embodied Visual Recognition","created":"2019-04-09","cited_by_count":9},{"id":"2006.15520","title":"Predictive and Generative Neural Networks for Object Functionality","created":"2020-06-28","cited_by_count":9},{"id":"2005.04464","title":"FAME: 3D Shape Generation via Functionality-Aware Model Evolution","created":"2020-05-09","cited_by_count":8},{"id":"2012.00057","title":"Move to See Better: Self-Improving Embodied Object Detection","created":"2020-11-30","cited_by_count":7},{"id":"1806.10457","title":"Physics-based Scene-level Reasoning for Object Pose Estimation in Clutter","created":"2018-06-25","cited_by_count":5}],"next_cursor":null}