{"total":36,"rows":[{"id":"2406.07113","title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2402.14327","title":"Subobject-level Image Tokenization","created":"2024-02-22","cited_by_count":21,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2407.18589","title":"HICEScore: A Hierarchical Metric for Image Captioning Evaluation","created":"2024-07-26","cited_by_count":12,"area":null},{"id":"2503.01646","title":"OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2503.07507","title":"PE3R: Perception-Efficient 3D Reconstruction","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2508.08240","title":"ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks","created":"2025-08-11","cited_by_count":9,"area":null},{"id":"2510.20238","title":"COS3D: Collaborative Open-Vocabulary 3D Segmentation","created":"2025-10-23","cited_by_count":9,"area":null},{"id":"2506.01304","title":"SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2403.09257","title":"WSI-SAM: Multi-resolution Segment Anything Model (SAM) for histopathology whole-slide images","created":"2024-03-14","cited_by_count":7,"area":null},{"id":"2505.11980","title":"AoP-SAM: Automation of Prompts for Efficient Segmentation","created":"2025-05-17","cited_by_count":7,"area":null},{"id":"2506.18807","title":"PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications","created":"2025-06-23","cited_by_count":6,"area":null},{"id":"2508.01150","title":"OpenGS-Fusion: Open-Vocabulary Dense Mapping with Hybrid 3D Gaussian Splatting for Refined Object-Level Understanding","created":"2025-08-02","cited_by_count":5,"area":null},{"id":"2511.15833","title":"EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3","created":"2025-11-19","cited_by_count":4,"area":null},{"id":"2408.12084","title":"Vision-Based Detection of Uncooperative Targets and Components on Small Satellites","created":"2024-08-22","cited_by_count":3,"area":null},{"id":"2504.02351","title":"Agglomerating Large Vision Encoders via Distillation for VFSS Segmentation","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2410.08926","title":"Zero-Shot Pupil Segmentation with SAM 2: A Case Study of Over 14 Million Images","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2507.08765","title":"Compress Any Segment Anything Model (SAM)","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2507.12123","title":"Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2511.19035","title":"Changes in Gaza: DINOv3-Powered Multi-Class Change Detection for Damage Assessment in Conflict Zones","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2511.22950","title":"RobotSeg: A Model and Dataset for Segmenting Robots in Image and Video","created":"2025-11-28","cited_by_count":1,"area":null},{"id":"2603.11917","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2606.08655","title":"PhysGraph: A Physics-aware 3D Scene Graph for Perception and Reasoning","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2403.10104","title":"CSDNet: Detect Salient Object in Depth-Thermal via A Lightweight Cross Shallow and Deep Perception Network","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2411.19289","title":"STAG-VIO: Stabilized Prompt-to-Geometry Interface for Robust Dynamic Visual--Inertial Odometry","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2503.10410","title":"RoCo-Sim: Enhancing Roadside Collaborative Perception through Foreground Simulation","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2507.15008","title":"FastSmoothSAM: A Fast Smooth Method For Segment Anything Model","created":"2025-07-20","cited_by_count":0,"area":null},{"id":"2512.22193","title":"Tiny-YOLOSAM: Fast Hybrid Image Segmentation","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2601.15123","title":"BREPS: Bounding-Box Robustness Evaluation of Promptable Segmentation","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.09632","title":"X-GS: An Extensible Framework for Perceiving and Thinking with 3D Gaussian Splatting","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.21166","title":"Training-Free Instance-Aware 3D Scene Reconstruction and Diffusion-Based View Synthesis from Sparse Images","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.07674","title":"Weight Group-wise Post-Training Quantization for Medical Foundation Model","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2606.15663","title":"OneFocus: Enabling Real-World X-ray Security Screening with a Unified Vision-Language Model","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2607.00124","title":"Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.01860","title":"DL-SLAM: Enabling High-Fidelity Gaussian Splatting SLAM in Dynamic Environments based on Dual-Level Probability","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2610.07569","title":"OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}