{"list":"other","total":75,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2103.14024","title":"PlenOctrees for Real-time Rendering of Neural Radiance Fields","created":"2021-03-25","cited_by_count":905},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2002.10099","title":"Implicit Geometric Regularization for Learning Shapes","created":"2020-02-24","cited_by_count":710},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"2402.10885","title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","created":"2024-02-16","cited_by_count":282},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245},{"id":"2303.18240","title":"Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?","created":"2023-03-31","cited_by_count":218},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169},{"id":"2306.06362","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","created":"2023-06-10","cited_by_count":167},{"id":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166},{"id":"2302.12766","title":"Language-Driven Representation Learning for Robotics","created":"2023-02-24","cited_by_count":165},{"id":"2403.07788","title":"DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation","created":"2024-03-12","cited_by_count":160},{"id":"2406.08545","title":"RVT-2: Learning Precise Manipulation from Few Demonstrations","created":"2024-06-12","cited_by_count":137},{"id":"2403.03954","title":"3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations","created":"2024-03-06","cited_by_count":116},{"id":"2204.02296","title":"iSDF: Real-Time Neural Signed Distance Fields for Robot Perception","created":"2022-04-05","cited_by_count":109},{"id":"2403.13064","title":"SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model","created":"2024-03-19","cited_by_count":96},{"id":"2310.08370","title":"UniPAD: A Universal Pre-training Paradigm for Autonomous Driving","created":"2023-10-12","cited_by_count":73},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71},{"id":"2206.14735","title":"GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction","created":"2022-06-29","cited_by_count":61},{"id":"2407.20179","title":"Theia: Distilling Diverse Vision Foundation Models for Robot Learning","created":"2024-07-29","cited_by_count":61},{"id":"2309.15596","title":"PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation","created":"2023-09-27","cited_by_count":56},{"id":"2310.08586","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","created":"2023-10-12","cited_by_count":56},{"id":"2306.09109","title":"NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations","created":"2023-06-15","cited_by_count":53},{"id":"2301.00157","title":"Ponder: Point Cloud Pre-training via Neural Rendering","created":"2022-12-31","cited_by_count":50},{"id":"2402.02500","title":"Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning","created":"2024-02-04","cited_by_count":45},{"id":"2404.12281","title":"RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effective","created":"2024-04-18","cited_by_count":41},{"id":"2103.02184","title":"RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Images","created":"2021-03-03","cited_by_count":39},{"id":"2406.12095","title":"DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features","created":"2024-06-17","cited_by_count":33},{"id":"2008.03596","title":"TriFinger: An Open-Source Robot for Learning Dexterity","created":"2020-08-08","cited_by_count":31},{"id":"2304.04591","title":"For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal","created":"2023-04-10","cited_by_count":22},{"id":"2403.05304","title":"Spatiotemporal Predictive Pre-training for Robotic Motor Control","created":"2024-03-08","cited_by_count":22},{"id":"2404.01300","title":"NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields","created":"2024-04-01","cited_by_count":20},{"id":"2403.11817","title":"HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation","created":"2024-03-18","cited_by_count":11},{"id":"2210.05135","title":"X-NeRF: Explicit Neural Radiance Field for Multi-Scene 360$^{\\circ} $ Insufficient RGB-D Views","created":"2022-10-11","cited_by_count":10},{"id":"2302.06148","title":"CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets","created":"2023-02-13","cited_by_count":8}],"next_cursor":null}