{"total":352,"rows":[{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929,"area":"wm"},{"id":"2312.00732","title":"Gaussian Grouping: Segment and Edit Anything in 3D Scenes","created":"2023-12-01","cited_by_count":393,"area":null},{"id":"2312.03275","title":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","created":"2023-12-06","cited_by_count":205,"area":"mllm"},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197,"area":null},{"id":"2312.00863","title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","created":"2023-12-01","cited_by_count":188,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2311.15707","title":"SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation","created":"2023-11-27","cited_by_count":117,"area":null},{"id":"2310.15308","title":"SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding","created":"2023-10-23","cited_by_count":111,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2309.09979","title":"General In-Hand Object Rotation with Vision and Touch","created":"2023-09-18","cited_by_count":99,"area":null},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81,"area":null},{"id":"2401.02955","title":"Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively","created":"2024-01-05","cited_by_count":75,"area":null},{"id":"2406.20076","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","created":"2024-06-28","cited_by_count":65,"area":"mllm"},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61,"area":"mllm"},{"id":"2408.04579","title":"SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More","created":"2024-08-08","cited_by_count":60,"area":null},{"id":"2309.01429","title":"Adapting Segment Anything Model for Change Detection in HR Remote Sensing Images","created":"2023-09-04","cited_by_count":56,"area":null},{"id":"2411.07231","title":"Watermark Anything with Localized Messages","created":"2024-11-11","cited_by_count":53,"area":null},{"id":"2404.08767","title":"LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning","created":"2024-04-12","cited_by_count":52,"area":"lr"},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51,"area":null},{"id":"2407.12276","title":"VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation","created":"2024-07-17","cited_by_count":50,"area":"mllm"},{"id":"2501.02341","title":"UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility","created":"2025-01-04","cited_by_count":49,"area":"agents"},{"id":"2407.00983","title":"FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models","created":"2024-07-01","cited_by_count":47,"area":null},{"id":"2407.12899","title":"DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion","created":"2024-07-17","cited_by_count":47,"area":"diffusion"},{"id":"2407.07520","title":"IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection","created":"2024-07-10","cited_by_count":46,"area":null},{"id":"2311.17707","title":"SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation","created":"2023-11-29","cited_by_count":44,"area":null},{"id":"2312.09579","title":"MobileSAMv2: Faster Segment Anything to Everything","created":"2023-12-15","cited_by_count":42,"area":null},{"id":"2312.06660","title":"EdgeSAM: Prompt-In-the-Loop Distillation for SAM","created":"2023-12-11","cited_by_count":41,"area":null},{"id":"2404.01862","title":"Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model","created":"2024-04-02","cited_by_count":35,"area":"diffusion"},{"id":"2411.10086","title":"CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation","created":"2024-11-15","cited_by_count":34,"area":null},{"id":"2312.13789","title":"TinySAM: Pushing the Envelope for Efficient Segment Anything Model","created":"2023-12-21","cited_by_count":33,"area":"distill"},{"id":"2404.09957","title":"How to build the best medical image segmentation algorithm using foundation models: a comprehensive empirical study with Segment Anything Model","created":"2024-04-15","cited_by_count":32,"area":null},{"id":"2405.03144","title":"PTQ4SAM: Post-Training Quantization for Segment Anything","created":"2024-05-06","cited_by_count":32,"area":null},{"id":"2409.17874","title":"DarkSAM: Fooling Segment Anything Model to Segment Nothing","created":"2024-09-26","cited_by_count":32,"area":null},{"id":"2312.09128","title":"Tokenize Anything via Prompting","created":"2023-12-14","cited_by_count":31,"area":null},{"id":"2411.03670","title":"Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?","created":"2024-11-06","cited_by_count":31,"area":null},{"id":"2401.17857","title":"SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition","created":"2024-01-31","cited_by_count":30,"area":null},{"id":"2401.17904","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","created":"2024-01-31","cited_by_count":30,"area":null},{"id":"2404.12389","title":"Moving Object Segmentation: All You Need Is SAM (and Flow)","created":"2024-04-18","cited_by_count":30,"area":null},{"id":"2312.13469","title":"Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation","created":"2023-12-20","cited_by_count":28,"area":null},{"id":"2512.11130","title":"Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching","created":"2025-12-11","cited_by_count":28,"area":"distill"},{"id":"2402.03631","title":"CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model","created":"2024-02-06","cited_by_count":27,"area":null},{"id":"2312.06462","title":"Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation","created":"2023-12-11","cited_by_count":26,"area":null},{"id":"2405.18424","title":"3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting","created":"2024-05-28","cited_by_count":25,"area":null},{"id":"2409.13401","title":"PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images","created":"2024-09-20","cited_by_count":24,"area":null},{"id":"2404.00741","title":"Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts","created":"2024-03-31","cited_by_count":22,"area":null},{"id":"2411.17030","title":"g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks","created":"2024-11-26","cited_by_count":22,"area":null},{"id":"2311.10986","title":"EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge","created":"2023-11-18","cited_by_count":21,"area":null},{"id":"2402.14327","title":"Subobject-level Image Tokenization","created":"2024-02-22","cited_by_count":21,"area":null},{"id":"2411.18933","title":"Efficient Track Anything","created":"2024-11-28","cited_by_count":21,"area":null},{"id":"2501.07256","title":"EdgeTAM: On-Device Track Anything Model","created":"2025-01-13","cited_by_count":21,"area":null},{"id":"2501.12931","title":"DynamicEarth: How Far are We from Open-Vocabulary Change Detection?","created":"2025-01-22","cited_by_count":21,"area":null},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20,"area":null},{"id":"2401.03907","title":"RoboFusion: Towards Robust Multi-Modal 3D Object Detection via SAM","created":"2024-01-08","cited_by_count":20,"area":null},{"id":"2403.09027","title":"VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework","created":"2024-03-14","cited_by_count":20,"area":"agents"},{"id":"2310.13026","title":"Weakly-Supervised Semantic Segmentation with Image-Level Labels: from Traditional Models to Foundation Models","created":"2023-10-19","cited_by_count":19,"area":null},{"id":"2311.15939","title":"Unleashing the Power of Prompt-driven Nucleus Instance Segmentation","created":"2023-11-27","cited_by_count":19,"area":null},{"id":"2509.01708","title":"Articulated Object Estimation in the Wild","created":"2025-09-01","cited_by_count":19,"area":null},{"id":"2311.14262","title":"ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation","created":"2023-11-24","cited_by_count":18,"area":null},{"id":"2402.02352","title":"Region-Based Representations Revisited","created":"2024-02-04","cited_by_count":18,"area":null},{"id":"2406.19369","title":"Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model","created":"2024-06-27","cited_by_count":18,"area":"ssm"},{"id":"2312.05760","title":"RepViT-SAM: Towards Real-Time Segmenting Anything","created":"2023-12-10","cited_by_count":17,"area":null},{"id":"2405.17859","title":"Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation","created":"2024-05-28","cited_by_count":17,"area":null},{"id":"2409.06214","title":"Towards Generalizable Scene Change Detection","created":"2024-09-10","cited_by_count":17,"area":null},{"id":"2506.01558","title":"SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes","created":"2025-06-02","cited_by_count":17,"area":null},{"id":"2401.16741","title":"MESA: Matching Everything by Segmenting Anything","created":"2024-01-30","cited_by_count":16,"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":"2410.05963","title":"Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts","created":"2024-10-08","cited_by_count":16,"area":null},{"id":"2307.16586","title":"SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model","created":"2023-07-31","cited_by_count":15,"area":null},{"id":"2401.02317","title":"BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model","created":"2024-01-04","cited_by_count":15,"area":null},{"id":"2401.12974","title":"SegmentAnyBone: A Universal Model that Segments Any Bone at Any Location on MRI","created":"2024-01-23","cited_by_count":14,"area":null},{"id":"2403.09827","title":"FastSAM3D: An Efficient Segment Anything Model for 3D Volumetric Medical Images","created":"2024-03-14","cited_by_count":14,"area":null},{"id":"2502.04981","title":"AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting","created":"2025-02-07","cited_by_count":14,"area":"mllm"},{"id":"2503.02304","title":"A Token-level Text Image Foundation Model for Document Understanding","created":"2025-03-04","cited_by_count":14,"area":"mllm"},{"id":"2307.07757","title":"Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments","created":"2023-07-15","cited_by_count":13,"area":null},{"id":"2310.10010","title":"Black-box Targeted Adversarial Attack on Segment Anything (SAM)","created":"2023-10-16","cited_by_count":13,"area":null},{"id":"2405.19899","title":"Open-Set Domain Adaptation for Semantic Segmentation","created":"2024-05-30","cited_by_count":13,"area":null},{"id":"2407.11464","title":"Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes","created":"2024-07-16","cited_by_count":13,"area":null},{"id":"2308.12231","title":"SPPNet: A Single-Point Prompt Network for Nuclei Image Segmentation","created":"2023-08-23","cited_by_count":12,"area":null},{"id":"2309.16967","title":"nnSAM: Plug-and-play Segment Anything Model Improves nnUNet Performance","created":"2023-09-29","cited_by_count":12,"area":null},{"id":"2312.17116","title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","created":"2023-12-28","cited_by_count":12,"area":null},{"id":"2401.08604","title":"SAM4UDASS: When SAM Meets Unsupervised Domain Adaptive Semantic Segmentation in Intelligent Vehicles","created":"2023-11-22","cited_by_count":12,"area":null},{"id":"2404.18083","title":"Online,Target-Free LiDAR-Camera Extrinsic Calibration via Cross-Modal Mask Matching","created":"2024-04-28","cited_by_count":12,"area":null},{"id":"2408.09085","title":"Segment Anything with Multiple Modalities","created":"2024-08-17","cited_by_count":12,"area":null},{"id":"2508.04190","title":"RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation","created":"2025-08-06","cited_by_count":12,"area":null},{"id":"2401.13699","title":"Generative AI-Driven Human Digital Twin in IoT-Healthcare: A Comprehensive Survey","created":"2024-01-22","cited_by_count":11,"area":null},{"id":"2403.08125","title":"Q-SLAM: Quadric Representations for Monocular SLAM","created":"2024-03-12","cited_by_count":11,"area":null},{"id":"2407.14153","title":"De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation","created":"2024-07-19","cited_by_count":11,"area":null},{"id":"2412.01539","title":"The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs","created":"2024-12-02","cited_by_count":11,"area":null},{"id":"2504.06827","title":"IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2602.16356","title":"Articulated 3D Scene Graphs for Open-World Mobile Manipulation","created":"2026-02-18","cited_by_count":11,"area":null},{"id":"2402.17133","title":"SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution","created":"2024-02-27","cited_by_count":10,"area":"diffusion"},{"id":"2405.02004","title":"M${^2}$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation","created":"2024-05-03","cited_by_count":10,"area":null},{"id":"2505.23692","title":"Mobi-$\\pi$: Mobilizing Your Robot Learning Policy","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2403.06403","title":"PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models","created":"2024-03-11","cited_by_count":9,"area":null},{"id":"2403.09620","title":"PosSAM: Panoptic Open-vocabulary Segment Anything","created":"2024-03-14","cited_by_count":9,"area":null},{"id":"2404.08255","title":"Practical Region-level Attack against Segment Anything Models","created":"2024-04-12","cited_by_count":9,"area":null},{"id":"2407.06939","title":"Towards Open-World Mobile Manipulation in Homes: Lessons from the Neurips 2023 HomeRobot Open Vocabulary Mobile Manipulation Challenge","created":"2024-07-09","cited_by_count":9,"area":null},{"id":"2502.14584","title":"Vision Foundation Models in Medical Image Analysis: Advances and Challenges","created":"2025-02-20","cited_by_count":9,"area":null},{"id":"2507.02798","title":"No time to train! Training-Free Reference-Based Instance Segmentation","created":"2025-07-03","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}],"next_cursor":"100"}