{"total":15,"rows":[{"id":"2308.16825","title":"Coarse-to-Fine Amodal Segmentation with Shape Prior","created":"2023-08-31","cited_by_count":29,"area":null},{"id":"2312.00690","title":"Open-vocabulary object 6D pose estimation","created":"2023-12-01","cited_by_count":29,"area":null},{"id":"2402.15726","title":"CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge","created":"2024-02-24","cited_by_count":16,"area":null},{"id":"2406.16384","title":"High-resolution open-vocabulary object 6D pose estimation","created":"2024-06-24","cited_by_count":10,"area":null},{"id":"2308.15962","title":"WALL-E: Embodied Robotic WAiter Load Lifting with Large Language Model","created":"2023-08-30","cited_by_count":6,"area":null},{"id":"2408.07975","title":"Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models","created":"2024-08-15","cited_by_count":6,"area":null},{"id":"2504.11230","title":"CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image","created":"2025-04-15","cited_by_count":5,"area":null},{"id":"2412.02140","title":"SparseGrasp: Robotic Grasping via 3D Semantic Gaussian Splatting from Sparse Multi-View RGB Images","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2506.05719","title":"You Only Estimate Once: Unified, One-stage, Real-Time Category-level Articulated Object 6D Pose Estimation for Robotic Grasping","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2407.19877","title":"Language-driven Grasp Detection with Mask-guided Attention","created":"2024-07-29","cited_by_count":2,"area":null},{"id":"2408.03238","title":"LAC-Net: Linear-Fusion Attention-Guided Convolutional Network for Accurate Robotic Grasping Under the Occlusion","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2510.11687","title":"Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2405.19949","title":"Hyper-Transformer for Amodal Completion","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2507.00339","title":"Training for X-Ray Vision: Amodal Segmentation, Amodal Content Completion, and View-Invariant Object Representation from Multi-Camera Video","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2512.21065","title":"Language-Guided Grasp Detection with Coarse-to-Fine Learning for Robotic Manipulation","created":"2025-12-24","cited_by_count":1,"area":null}],"next_cursor":null}