{"list":"other","total":63,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"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":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2004.02857","title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","created":"2020-04-06","cited_by_count":441},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2010.07954","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","created":"2020-10-15","cited_by_count":414},{"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":"1904.10151","title":"REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments","created":"2019-04-23","cited_by_count":333},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"1906.00817","title":"Zero-Shot Semantic Segmentation","created":"2019-06-03","cited_by_count":245},{"id":"2006.13171","title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","created":"2020-06-23","cited_by_count":244},{"id":"1702.03920","title":"Cognitive Mapping and Planning for Visual Navigation","created":"2017-02-13","cited_by_count":212},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191},{"id":"1804.04340","title":"Zero-Shot Object Detection","created":"2018-04-12","cited_by_count":189},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182},{"id":"2201.10029","title":"PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning","created":"2022-01-25","cited_by_count":150},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"1810.06543","title":"Visual Semantic Navigation using Scene Priors","created":"2018-10-15","cited_by_count":128},{"id":"2103.17138","title":"SOON: Scenario Oriented Object Navigation with Graph-based Exploration","created":"2021-03-31","cited_by_count":119},{"id":"1903.01959","title":"Learning Exploration Policies for Navigation","created":"2019-03-05","cited_by_count":116},{"id":"2008.01187","title":"PhraseCut: Language-based Image Segmentation in the Wild","created":"2020-08-03","cited_by_count":116},{"id":"2103.16544","title":"Visual Room Rearrangement","created":"2021-03-30","cited_by_count":102},{"id":"2012.03912","title":"MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation","created":"2020-12-07","cited_by_count":95},{"id":"1812.00971","title":"Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning","created":"2018-12-03","cited_by_count":93},{"id":"1804.04011","title":"QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAM","created":"2018-04-10","cited_by_count":86},{"id":"1807.07049","title":"Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias","created":"2018-07-18","cited_by_count":75},{"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":"1712.03931","title":"MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments","created":"2017-12-11","cited_by_count":66},{"id":"2101.05181","title":"Memory-Augmented Reinforcement Learning for Image-Goal Navigation","created":"2021-01-13","cited_by_count":66},{"id":"2110.09470","title":"No RL, No Simulation: Learning to Navigate without Navigating","created":"2021-10-18","cited_by_count":65},{"id":"2006.10034","title":"Semantic Visual Navigation by Watching YouTube Videos","created":"2020-06-17","cited_by_count":60},{"id":"2008.12760","title":"AllenAct: A Framework for Embodied AI Research","created":"2020-08-28","cited_by_count":54},{"id":"2106.04531","title":"RobustNav: Towards Benchmarking Robustness in Embodied Navigation","created":"2021-06-08","cited_by_count":54},{"id":"2108.06536","title":"Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation","created":"2021-08-14","cited_by_count":53},{"id":"1803.06049","title":"Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts","created":"2018-03-16","cited_by_count":48},{"id":"2012.04512","title":"SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation","created":"2020-12-08","cited_by_count":44},{"id":"2108.12517","title":"SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation","created":"2021-08-27","cited_by_count":41},{"id":"1801.07357","title":"CHALET: Cornell House Agent Learning Environment","created":"2018-01-23","cited_by_count":38},{"id":"2111.13119","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","created":"2021-11-25","cited_by_count":38},{"id":"1805.06157","title":"Zero-Shot Object Detection by Hybrid Region Embedding","created":"2018-05-16","cited_by_count":32},{"id":"1905.07512","title":"SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation","created":"2019-05-18","cited_by_count":29},{"id":"1803.07113","title":"Zero-Shot Detection","created":"2018-03-19","cited_by_count":27},{"id":"1507.02703","title":"Robot In a Room: Toward Perfect Object Recognition in Closed Environments","created":"2015-07-09","cited_by_count":6},{"id":"2201.00411","title":"The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents","created":"2022-01-02","cited_by_count":2}],"next_cursor":null}