{"list":"other","total":58,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2203.17054","title":"BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection","created":"2022-03-31","cited_by_count":341},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332},{"id":"2303.11926","title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","created":"2023-03-21","cited_by_count":315},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293},{"id":"2203.08195","title":"DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection","created":"2022-03-15","cited_by_count":224},{"id":"2303.03991","title":"OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception","created":"2023-03-07","cited_by_count":221},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209},{"id":"2211.07752","title":"Robot Operating System 2: Design, Architecture, and Uses In The Wild","created":"2022-11-14","cited_by_count":199},{"id":"2406.10454","title":"HumanPlus: Humanoid Shadowing and Imitation from Humans","created":"2024-06-15","cited_by_count":185},{"id":"2307.01492","title":"FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation","created":"2023-07-04","cited_by_count":165},{"id":"2407.01512","title":"Open-TeleVision: Teleoperation with Immersive Active Visual Feedback","created":"2024-07-01","cited_by_count":145},{"id":"2208.02797","title":"Vision-Centric BEV Perception: A Survey","created":"2022-08-04","cited_by_count":126},{"id":"2311.12058","title":"FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin","created":"2023-11-18","cited_by_count":103},{"id":"2308.16891","title":"GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields","created":"2023-08-31","cited_by_count":99},{"id":"2404.09502","title":"SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction","created":"2024-04-15","cited_by_count":96},{"id":"2406.10759","title":"Humanoid Parkour Learning","created":"2024-06-15","cited_by_count":96},{"id":"2502.13013","title":"HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit","created":"2025-02-18","cited_by_count":76},{"id":"2501.02116","title":"Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learning","created":"2025-01-03","cited_by_count":61},{"id":"2410.10803","title":"Generalizable Humanoid Manipulation with 3D Diffusion Policies","created":"2024-10-14","cited_by_count":52},{"id":"2412.07773","title":"Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control","created":"2024-12-10","cited_by_count":51},{"id":"2411.14386","title":"Learning Humanoid Locomotion with Perceptive Internal Model","created":"2024-11-21","cited_by_count":50},{"id":"2412.04380","title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","created":"2024-12-05","cited_by_count":45},{"id":"2309.14594","title":"Learning Vision-Based Bipedal Locomotion for Challenging Terrain","created":"2023-09-26","cited_by_count":42},{"id":"2506.09588","title":"Attention-Based Map Encoding for Learning Generalized Legged Locomotion","created":"2025-06-11","cited_by_count":40},{"id":"2403.01644","title":"OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction","created":"2024-03-03","cited_by_count":32},{"id":"2504.09540","title":"EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler","created":"2025-04-13","cited_by_count":27},{"id":"2505.11164","title":"Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuning","created":"2025-05-16","cited_by_count":26},{"id":"2408.13740","title":"PIE: Parkour with Implicit-Explicit Learning Framework for Legged Robots","created":"2024-08-25","cited_by_count":25},{"id":"2504.14604","title":"RoboOcc: Enhancing the Geometric and Semantic Scene Understanding for Robots","created":"2025-04-20","cited_by_count":15},{"id":"2403.05329","title":"OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction","created":"2024-03-08","cited_by_count":13},{"id":"2404.07950","title":"Reinforcement Learning with Generalizable Gaussian Splatting","created":"2024-03-18","cited_by_count":13},{"id":"2503.09010","title":"HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots","created":"2025-03-12","cited_by_count":13},{"id":"2503.00692","title":"Learning Perceptive Humanoid Locomotion over Challenging Terrain","created":"2025-03-02","cited_by_count":12},{"id":"2507.06747","title":"LOVON: Legged Open-Vocabulary Object Navigator","created":"2025-07-09","cited_by_count":11},{"id":"1304.1098","title":"Occupancy Grids: A Stochastic Spatial Representation for Active Robot Perception","created":"2013-03-27","cited_by_count":10},{"id":"2503.08299","title":"Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion","created":"2025-03-11","cited_by_count":10},{"id":"2505.05512","title":"Occupancy World Model for Robots","created":"2025-05-07","cited_by_count":8},{"id":"2505.19214","title":"Omni-Perception: Omnidirectional Collision Avoidance for Legged Locomotion in Dynamic Environments","created":"2025-05-25","cited_by_count":8},{"id":"2305.09933","title":"Impact of ROS 2 Node Composition in Robotic Systems","created":"2023-05-17","cited_by_count":7},{"id":"2406.02370","title":"Query-based Semantic Gaussian Field for Scene Representation in Reinforcement Learning","created":"2024-06-04","cited_by_count":6},{"id":"2309.15616","title":"Perception for Humanoid Robots","created":"2023-09-27","cited_by_count":5},{"id":"2412.00396","title":"ARMOR: Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning","created":"2024-11-30","cited_by_count":4},{"id":"2503.08338","title":"Trinity: A Modular Humanoid Robot AI System","created":"2025-03-11","cited_by_count":3},{"id":"2507.08303","title":"Keep on Going: Learning Robust Humanoid Motion Skills via Selective Adversarial Training","created":"2025-07-11","cited_by_count":1}],"next_cursor":null}