{"list":"other","total":59,"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"id":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271},{"id":"1608.00525","title":"Modeling Context Between Objects for Referring Expression Understanding","created":"2016-08-01","cited_by_count":251},{"id":"2212.08333","title":"AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains","created":"2022-12-16","cited_by_count":208},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"1707.00683","title":"Modulating early visual processing by language","created":"2017-07-02","cited_by_count":167},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"2011.09584","title":"ACRONYM: A Large-Scale Grasp Dataset Based on Simulation","created":"2020-11-18","cited_by_count":117},{"id":"2105.01839","title":"Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation","created":"2021-05-05","cited_by_count":111},{"id":"1912.04344","title":"Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations","created":"2019-12-09","cited_by_count":107},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102},{"id":"2309.07970","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","created":"2023-09-14","cited_by_count":91},{"id":"2311.08526","title":"GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer","created":"2023-11-14","cited_by_count":88},{"id":"1803.11469","title":"Jacquard: A Large Scale Dataset for Robotic Grasp Detection","created":"2018-03-30","cited_by_count":87},{"id":"2108.02388","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","created":"2021-08-05","cited_by_count":86},{"id":"2205.00272","title":"Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning","created":"2022-04-30","cited_by_count":69},{"id":"1806.03831","title":"Interactive Visual Grounding of Referring Expressions for Human-Robot Interaction","created":"2018-06-11","cited_by_count":56},{"id":"2107.05287","title":"End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB","created":"2021-07-12","cited_by_count":44},{"id":"2308.00640","title":"VL-Grasp: a 6-Dof Interactive Grasp Policy for Language-Oriented Objects in Cluttered Indoor Scenes","created":"2023-08-01","cited_by_count":42},{"id":"2203.15125","title":"Text2Pos: Text-to-Point-Cloud Cross-Modal Localization","created":"2022-03-28","cited_by_count":40},{"id":"2404.10220","title":"Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V","created":"2024-04-16","cited_by_count":40},{"id":"2103.02184","title":"RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Images","created":"2021-03-03","cited_by_count":39},{"id":"2308.14575","title":"Referring Image Segmentation Using Text Supervision","created":"2023-08-28","cited_by_count":35},{"id":"2302.12610","title":"A Joint Modeling of Vision-Language-Action for Target-oriented Grasping in Clutter","created":"2023-02-24","cited_by_count":34},{"id":"2103.07894","title":"Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images","created":"2021-03-14","cited_by_count":33},{"id":"2108.11092","title":"INVIGORATE: Interactive Visual Grounding and Grasping in Clutter","created":"2021-08-25","cited_by_count":32},{"id":"2007.13124","title":"GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision","created":"2020-07-26","cited_by_count":28},{"id":"2406.09489","title":"Language-driven Grasp Detection","created":"2024-06-13","cited_by_count":26},{"id":"2402.08546","title":"Grounding LLMs For Robot Task Planning Using Closed-loop State Feedback","created":"2024-02-13","cited_by_count":25},{"id":"2104.00492","title":"A Joint Network for Grasp Detection Conditioned on Natural Language Commands","created":"2021-04-01","cited_by_count":23},{"id":"2311.05779","title":"Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter","created":"2023-11-09","cited_by_count":22},{"id":"2312.15715","title":"UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces","created":"2023-12-25","cited_by_count":22},{"id":"2310.05239","title":"Lan-grasp: Using Large Language Models for Semantic Object Grasping and Placement","created":"2023-10-08","cited_by_count":16},{"id":"2312.08611","title":"UniTeam: Open Vocabulary Mobile Manipulation Challenge","created":"2023-12-14","cited_by_count":15},{"id":"2302.14355","title":"Task-Oriented Grasp Prediction with Visual-Language Inputs","created":"2023-02-28","cited_by_count":14},{"id":"2307.08597","title":"Multimodal Diffusion Segmentation Model for Object Segmentation from Manipulation Instructions","created":"2023-07-17","cited_by_count":7},{"id":"2010.06544","title":"Real-Time Deep Learning Approach to Visual Servo Control and Grasp Detection for Autonomous Robotic Manipulation","created":"2020-10-13","cited_by_count":4},{"id":"2206.11141","title":"Hybrid Physical Metric For 6-DoF Grasp Pose Detection","created":"2022-06-22","cited_by_count":4}],"next_cursor":null}