{"total":31,"rows":[{"id":"2210.09729","title":"HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes","created":"2022-10-18","cited_by_count":158,"area":null},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133,"area":null},{"id":"2405.07784","title":"Generating Human Motion in 3D Scenes from Text Descriptions","created":"2024-05-13","cited_by_count":49,"area":null},{"id":"2310.03779","title":"HandMeThat: Human-Robot Communication in Physical and Social Environments","created":"2023-10-05","cited_by_count":20,"area":null},{"id":"2502.00392","title":"RefDrone: A Challenging Benchmark for Referring Expression Comprehension in Drone Scenes","created":"2025-02-01","cited_by_count":19,"area":null},{"id":"2306.00503","title":"MEWL: Few-shot multimodal word learning with referential uncertainty","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2210.05668","title":"Understanding Embodied Reference with Touch-Line Transformer","created":"2022-10-11","cited_by_count":16,"area":null},{"id":"2303.13186","title":"ScanERU: Interactive 3D Visual Grounding based on Embodied Reference Understanding","created":"2023-03-23","cited_by_count":12,"area":null},{"id":"2309.01073","title":"Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding","created":"2023-09-03","cited_by_count":11,"area":null},{"id":"2304.08492","title":"STRAP: Structured Object Affordance Segmentation with Point Supervision","created":"2023-04-17","cited_by_count":10,"area":null},{"id":"2407.03967","title":"Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2504.09623","title":"Ges3ViG: Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding","created":"2025-04-13","cited_by_count":8,"area":null},{"id":"2208.11122","title":"Distance-Aware Occlusion Detection with Focused Attention","created":"2022-08-23","cited_by_count":6,"area":null},{"id":"2311.00556","title":"ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2409.20548","title":"Robi Butler: Multimodal Remote Interaction with a Household Robot Assistant","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2210.10020","title":"ULN: Towards Underspecified Vision-and-Language Navigation","created":"2022-10-18","cited_by_count":5,"area":null},{"id":"2602.08914","title":"Gesturing Toward Abstraction: Multimodal Convention Formation in Collaborative Physical Tasks","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2309.03483","title":"DetermiNet: A Large-Scale Diagnostic Dataset for Complex Visually-Grounded Referencing using Determiners","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2503.19240","title":"Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2509.12507","title":"Learning to Generate Pointing Gestures in Situated Embodied Conversational Agents","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2411.08451","title":"AD-DINO: Attention-Dynamic DINO for Distance-Aware Embodied Reference Understanding","created":"2024-11-13","cited_by_count":2,"area":null},{"id":"2503.00071","title":"I see what you mean: Co-Speech Gestures for Reference Resolution in Multimodal Dialogue","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2508.13901","title":"Multimodal Data Storage and Retrieval for Embodied AI: A Survey","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2603.26646","title":"Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2605.21796","title":"MM-Conv: A Multimodal Dataset and Benchmark for Context-Aware Grounding in 3D Dialogue","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2510.08278","title":"A Multimodal Depth-Aware Method For Embodied Reference Understanding","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2608.08915","title":"Investigating Multimodal Informativity under Different Partner Visibility Conditions in Video-Mediated Dialogue","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2507.21888","title":"CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2603.07966","title":"Listening with the Eyes: Benchmarking Egocentric Co-Speech Grounding across Space and Time","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2605.24622","title":"PoseRefer: Pathway-Local Parameters for Semantically Grounded Reference Resolution","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.24498","title":"VistaRef: Boosting Visual Spatial Orientation Awareness for Pointing-to-Object Detection","created":"2026-06-23","cited_by_count":0,"area":null}],"next_cursor":null}