{"list":"other","total":66,"rows":[{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"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":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","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":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"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":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"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":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"1903.04025","title":"Group-wise Correlation Stereo Network","created":"2019-03-10","cited_by_count":235},{"id":"1805.09806","title":"Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation","created":"2018-05-24","cited_by_count":222},{"id":"2004.15021","title":"Consistent Video Depth Estimation","created":"2020-04-30","cited_by_count":220},{"id":"2012.01411","title":"PatchmatchNet: Learned Multi-View Patchmatch Stereo","created":"2020-12-02","cited_by_count":207},{"id":"2003.01060","title":"D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry","created":"2020-03-02","cited_by_count":206},{"id":"2108.03272","title":"iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks","created":"2021-08-06","cited_by_count":194},{"id":"1911.07883","title":"Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks","created":"2019-11-18","cited_by_count":179},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175},{"id":"1904.04998","title":"Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras","created":"2019-04-10","cited_by_count":170},{"id":"1912.04799","title":"Learning Depth-Guided Convolutions for Monocular 3D Object Detection","created":"2019-12-10","cited_by_count":169},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156},{"id":"1712.03316","title":"IQA: Visual Question Answering in Interactive Environments","created":"2017-12-09","cited_by_count":155},{"id":"2110.07342","title":"FILM: Following Instructions in Language with Modular Methods","created":"2021-10-12","cited_by_count":121},{"id":"1908.01238","title":"Learning Guided Convolutional Network for Depth Completion","created":"2019-08-03","cited_by_count":111},{"id":"1910.06727","title":"Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints","created":"2019-10-15","cited_by_count":108},{"id":"1903.01602","title":"The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation","created":"2019-03-05","cited_by_count":105},{"id":"1706.06551","title":"Grounded Language Learning in a Simulated 3D World","created":"2017-06-20","cited_by_count":100},{"id":"1605.02305","title":"Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks","created":"2016-05-08","cited_by_count":91},{"id":"2107.05612","title":"A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution","created":"2021-07-12","cited_by_count":91},{"id":"2107.03438","title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","created":"2021-07-07","cited_by_count":89},{"id":"1712.01892","title":"Grounding Referring Expressions in Images by Variational Context","created":"2017-12-05","cited_by_count":82},{"id":"1903.02547","title":"Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation","created":"2019-03-06","cited_by_count":81},{"id":"2103.16381","title":"Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud","created":"2021-03-30","cited_by_count":81},{"id":"1812.06587","title":"Grounded Video Description","created":"2018-12-17","cited_by_count":78},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68},{"id":"1810.01849","title":"SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation","created":"2018-10-03","cited_by_count":64},{"id":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63},{"id":"2108.13643","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","created":"2021-08-31","cited_by_count":59},{"id":"2108.04927","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","created":"2021-08-10","cited_by_count":58},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","cited_by_count":55},{"id":"2106.03427","title":"Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring","created":"2021-06-07","cited_by_count":53},{"id":"2003.00403","title":"Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension","created":"2020-03-01","cited_by_count":50},{"id":"2107.12429","title":"MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments","created":"2021-07-26","cited_by_count":38},{"id":"2108.08574","title":"StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation","created":"2021-08-19","cited_by_count":36},{"id":"2106.00596","title":"Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks","created":"2021-06-01","cited_by_count":26},{"id":"2202.07028","title":"One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones","created":"2022-02-14","cited_by_count":26},{"id":"2303.04456","title":"RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes","created":"2023-03-08","cited_by_count":22},{"id":"1910.01210","title":"Embodied Language Grounding with 3D Visual Feature Representations","created":"2019-10-02","cited_by_count":20},{"id":"2109.04150","title":"Self-supervised Reinforcement Learning with Independently Controllable Subgoals","created":"2021-09-09","cited_by_count":16},{"id":"2304.03282","title":"Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention","created":"2023-04-06","cited_by_count":12},{"id":"2012.15814","title":"Language-Mediated, Object-Centric Representation Learning","created":"2020-12-31","cited_by_count":11},{"id":"2202.08806","title":"Grammar-Based Grounded Lexicon Learning","created":"2022-02-17","cited_by_count":11},{"id":"1903.09243","title":"Inferring Compact Representations for Efficient Natural Language Understanding of Robot Instructions","created":"2019-03-21","cited_by_count":9},{"id":"2109.02161","title":"Modular Framework for Visuomotor Language Grounding","created":"2021-09-05","cited_by_count":9},{"id":"1503.05079","title":"Learning Models for Following Natural Language Directions in Unknown Environments","created":"2015-03-17","cited_by_count":8}],"next_cursor":null}