{"list":"other","total":67,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2301.10241","title":"K-Planes: Explicit Radiance Fields in Space, Time, and Appearance","created":"2023-01-24","cited_by_count":746},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2012.15838","title":"Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans","created":"2020-12-31","cited_by_count":634},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2012.12247","title":"Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video","created":"2020-12-22","cited_by_count":471},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"1708.03852","title":"VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator","created":"2017-08-13","cited_by_count":423},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"2011.12950","title":"Space-time Neural Irradiance Fields for Free-Viewpoint Video","created":"2020-11-25","cited_by_count":414},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371},{"id":"2205.15285","title":"Fast Dynamic Radiance Fields with Time-Aware Neural Voxels","created":"2022-05-30","cited_by_count":346},{"id":"2011.10379","title":"Neural Scene Graphs for Dynamic Scenes","created":"2020-11-20","cited_by_count":298},{"id":"2012.09790","title":"Neural Radiance Flow for 4D View Synthesis and Video Processing","created":"2020-12-17","cited_by_count":270},{"id":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243},{"id":"2109.01847","title":"Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering","created":"2021-09-04","cited_by_count":228},{"id":"2211.11082","title":"DynIBaR: Neural Dynamic Image-Based Rendering","created":"2022-11-20","cited_by_count":224},{"id":"2210.13445","title":"Monocular Dynamic View Synthesis: A Reality Check","created":"2022-10-24","cited_by_count":200},{"id":"2209.03494","title":"Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations","created":"2022-09-07","cited_by_count":196},{"id":"2007.03672","title":"Long-term Human Motion Prediction with Scene Context","created":"2020-07-07","cited_by_count":192},{"id":"2212.09802","title":"Panoptic Lifting for 3D Scene Understanding with Neural Fields","created":"2022-12-19","cited_by_count":174},{"id":"2108.06428","title":"FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration","created":"2021-08-13","cited_by_count":169},{"id":"2004.01294","title":"Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Camera","created":"2020-04-02","cited_by_count":166},{"id":"2202.08614","title":"Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-time","created":"2022-02-17","cited_by_count":165},{"id":"2109.07448","title":"Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering","created":"2021-09-15","cited_by_count":158},{"id":"2203.15224","title":"Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation","created":"2022-03-29","cited_by_count":152},{"id":"2210.15947","title":"NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields","created":"2022-10-28","cited_by_count":152},{"id":"2210.09782","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","created":"2022-10-18","cited_by_count":148},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"2205.15838","title":"D$^2$NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video","created":"2022-05-31","cited_by_count":137},{"id":"2111.13260","title":"NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes","created":"2021-11-25","cited_by_count":119},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"2205.15723","title":"DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes","created":"2022-05-31","cited_by_count":103},{"id":"2107.07905","title":"Unsupervised Discovery of Object Radiance Fields","created":"2021-07-16","cited_by_count":101},{"id":"2105.05994","title":"Neural Trajectory Fields for Dynamic Novel View Synthesis","created":"2021-05-12","cited_by_count":86},{"id":"2101.01602","title":"STaR: Self-supervised Tracking and Reconstruction of Rigid Objects in Motion with Neural Rendering","created":"2020-12-22","cited_by_count":76},{"id":"2008.08324","title":"FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration","created":"2020-08-19","cited_by_count":73},{"id":"2209.08776","title":"NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes","created":"2022-09-19","cited_by_count":71},{"id":"2208.07227","title":"DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images","created":"2022-08-15","cited_by_count":69},{"id":"2110.09936","title":"NeuralDiff: Segmenting 3D objects that move in egocentric videos","created":"2021-10-19","cited_by_count":57},{"id":"2104.08418","title":"FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling","created":"2021-04-17","cited_by_count":47},{"id":"2303.03361","title":"Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision","created":"2023-03-06","cited_by_count":44},{"id":"2206.07698","title":"Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesis","created":"2022-06-15","cited_by_count":43},{"id":"2207.01583","title":"LaTeRF: Label and Text Driven Object Radiance Fields","created":"2022-07-04","cited_by_count":38},{"id":"2301.02217","title":"EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding","created":"2023-01-05","cited_by_count":32},{"id":"1904.06250","title":"Generative Hybrid Representations for Activity Forecasting with No-Regret Learning","created":"2019-04-12","cited_by_count":18},{"id":"2207.11232","title":"Neural Groundplans: Persistent Neural Scene Representations from a Single Image","created":"2022-07-22","cited_by_count":17},{"id":"1805.07663","title":"An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark","created":"2018-05-19","cited_by_count":16},{"id":"2303.01526","title":"Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition","created":"2023-03-02","cited_by_count":13},{"id":"1708.04814","title":"GSLAM: Initialization-robust Monocular Visual SLAM via Global Structure-from-Motion","created":"2017-08-16","cited_by_count":4}],"next_cursor":null}