{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"1908.06963","title":"Resolving 3D Human Pose Ambiguities with 3D Scene Constraints","created":"2019-08-20","cited_by_count":295},{"id":"2204.06950","title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions","created":"2022-04-14","cited_by_count":249},{"id":"2211.11610","title":"Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering","created":"2022-11-21","cited_by_count":217},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"2007.03672","title":"Long-term Human Motion Prediction with Scene Context","created":"2020-07-07","cited_by_count":192},{"id":"2206.09553","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","created":"2022-06-20","cited_by_count":180},{"id":"1612.03153","title":"Panoptic Studio: A Massively Multiview System for Social Interaction Capture","created":"2016-12-09","cited_by_count":173},{"id":"1912.04799","title":"Learning Depth-Guided Convolutions for Monocular 3D Object Detection","created":"2019-12-10","cited_by_count":169},{"id":"2012.11581","title":"Populating 3D Scenes by Learning Human-Scene Interaction","created":"2020-12-21","cited_by_count":164},{"id":"2012.09793","title":"SceneFormer: Indoor Scene Generation with Transformers","created":"2020-12-17","cited_by_count":158},{"id":"2103.17265","title":"Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors","created":"2021-03-31","cited_by_count":137},{"id":"1904.11621","title":"Meta-Sim: Learning to Generate Synthetic Datasets","created":"2019-04-25","cited_by_count":128},{"id":"2211.11208","title":"Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars","created":"2022-11-21","cited_by_count":124},{"id":"1811.12463","title":"Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models","created":"2018-11-29","cited_by_count":106},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103},{"id":"1810.10093","title":"Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data","created":"2018-10-23","cited_by_count":94},{"id":"2007.10872","title":"Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking","created":"2020-07-21","cited_by_count":81},{"id":"1808.08473","title":"Human-centric Indoor Scene Synthesis Using Stochastic Grammar","created":"2018-08-25","cited_by_count":74},{"id":"2110.07588","title":"Playing for 3D Human Recovery","created":"2021-10-14","cited_by_count":64},{"id":"1808.02084","title":"Deep Generative Modeling for Scene Synthesis via Hybrid Representations","created":"2018-08-06","cited_by_count":63},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56},{"id":"1907.11308","title":"SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation","created":"2019-07-25","cited_by_count":55},{"id":"2007.11744","title":"End-to-End Optimization of Scene Layout","created":"2020-07-23","cited_by_count":52},{"id":"1810.04703","title":"Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time","created":"2018-10-10","cited_by_count":47},{"id":"1912.03001","title":"Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation","created":"2019-12-06","cited_by_count":44},{"id":"1807.09193","title":"GRAINS: Generative Recursive Autoencoders for INdoor Scenes","created":"2018-07-24","cited_by_count":38},{"id":"2212.02469","title":"One-shot Implicit Animatable Avatars with Model-based Priors","created":"2022-12-05","cited_by_count":38},{"id":"1505.06289","title":"Text to 3D Scene Generation with Rich Lexical Grounding","created":"2015-05-23","cited_by_count":36},{"id":"2112.12867","title":"HSPACE: Synthetic Parametric Humans Animated in Complex Environments","created":"2021-12-23","cited_by_count":29},{"id":"2112.03030","title":"Pose2Room: Understanding 3D Scenes from Human Activities","created":"2021-12-01","cited_by_count":22},{"id":"1703.00050","title":"SceneSeer: 3D Scene Design with Natural Language","created":"2017-02-28","cited_by_count":21},{"id":"2002.05316","title":"SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud","created":"2020-02-13","cited_by_count":16},{"id":"2205.14657","title":"COFS: Controllable Furniture layout Synthesis","created":"2022-05-29","cited_by_count":14},{"id":"2009.12395","title":"SceneGen: Generative Contextual Scene Augmentation using Scene Graph Priors","created":"2020-09-25","cited_by_count":11},{"id":"2002.00328","title":"Fast 3D Indoor Scene Synthesis with Discrete and Exact Layout Pattern Extraction","created":"2020-02-02","cited_by_count":7},{"id":"1806.07889","title":"iMapper: Interaction-guided Joint Scene and Human Motion Mapping from Monocular Videos","created":"2018-06-20","cited_by_count":6},{"id":"2103.00262","title":"Walk2Map: Extracting Floor Plans from Indoor Walk Trajectories","created":"2021-02-27","cited_by_count":4},{"id":"2008.01323","title":"Structural Plan of Indoor Scenes with Personalized Preferences","created":"2020-08-04","cited_by_count":3}],"next_cursor":null}