{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"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":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305},{"id":"1907.04957","title":"Vision-and-Dialog Navigation","created":"2019-07-10","cited_by_count":250},{"id":"1810.08272","title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","created":"2018-10-18","cited_by_count":244},{"id":"2006.13171","title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","created":"2020-06-23","cited_by_count":244},{"id":"1811.12354","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","created":"2018-11-29","cited_by_count":239},{"id":"2002.10638","title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","created":"2020-02-25","cited_by_count":231},{"id":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"id":"1702.03920","title":"Cognitive Mapping and Planning for Visual Navigation","created":"2017-02-13","cited_by_count":212},{"id":"1605.02097","title":"ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning","created":"2016-05-06","cited_by_count":179},{"id":"1911.07883","title":"Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks","created":"2019-11-18","cited_by_count":179},{"id":"1712.03316","title":"IQA: Visual Question Answering in Interactive Environments","created":"2017-12-09","cited_by_count":155},{"id":"1810.06543","title":"Visual Semantic Navigation using Scene Priors","created":"2018-10-15","cited_by_count":128},{"id":"1609.06647","title":"Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge","created":"2016-09-21","cited_by_count":116},{"id":"1904.04196","title":"Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering","created":"2019-04-08","cited_by_count":115},{"id":"1801.02209","title":"Building Generalizable Agents with a Realistic and Rich 3D Environment","created":"2018-01-07","cited_by_count":109},{"id":"1809.00786","title":"Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction","created":"2018-09-04","cited_by_count":101},{"id":"1706.06551","title":"Grounded Language Learning in a Simulated 3D World","created":"2017-06-20","cited_by_count":100},{"id":"1909.01871","title":"Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning","created":"2019-09-04","cited_by_count":100},{"id":"1912.11684","title":"Look, Listen, and Act: Towards Audio-Visual Embodied Navigation","created":"2019-12-25","cited_by_count":96},{"id":"1805.06066","title":"Visual Representations for Semantic Target Driven Navigation","created":"2018-05-15","cited_by_count":89},{"id":"1612.03801","title":"DeepMind Lab","created":"2016-12-12","cited_by_count":74},{"id":"1706.07230","title":"Gated-Attention Architectures for Task-Oriented Language Grounding","created":"2017-06-22","cited_by_count":72},{"id":"1712.03931","title":"MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments","created":"2017-12-11","cited_by_count":66},{"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":"1810.11181","title":"Neural Modular Control for Embodied Question Answering","created":"2018-10-26","cited_by_count":56},{"id":"2008.12760","title":"AllenAct: A Framework for Embodied AI Research","created":"2020-08-28","cited_by_count":54},{"id":"1906.04158","title":"Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in A Triadic Interaction","created":"2019-06-10","cited_by_count":48},{"id":"1801.07357","title":"CHALET: Cornell House Agent Learning Environment","created":"2018-01-23","cited_by_count":38},{"id":"1812.02664","title":"Recursive Visual Attention in Visual Dialog","created":"2018-12-06","cited_by_count":34},{"id":"1802.01433","title":"Interactive Grounded Language Acquisition and Generalization in a 2D World","created":"2018-01-31","cited_by_count":21},{"id":"1711.11017","title":"HoME: a Household Multimodal Environment","created":"2017-11-29","cited_by_count":20},{"id":"2104.02841","title":"Learning Triadic Belief Dynamics in Nonverbal Communication from Videos","created":"2021-04-07","cited_by_count":17},{"id":"1904.01698","title":"VRGym: A Virtual Testbed for Physical and Interactive AI","created":"2019-04-02","cited_by_count":9},{"id":"2106.02003","title":"Individual vs. Joint Perception: a Pragmatic Model of Pointing as Communicative Smithian Helping","created":"2021-06-03","cited_by_count":3}],"next_cursor":null}