{"total":234,"rows":[{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863,"area":null},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415,"area":null},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352,"area":null},{"id":"2305.03048","title":"Personalize Segment Anything Model with One Shot","created":"2023-05-04","cited_by_count":250,"area":null},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197,"area":null},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188,"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":"2501.09898","title":"FoundationStereo: Zero-Shot Stereo Matching","created":"2025-01-17","cited_by_count":173,"area":null},{"id":"2309.01918","title":"RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking","created":"2023-09-05","cited_by_count":169,"area":null},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161,"area":"diffusion"},{"id":"2409.12961","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","created":"2024-09-19","cited_by_count":159,"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":"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":"2308.08746","title":"SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation","created":"2023-08-17","cited_by_count":104,"area":null},{"id":"2406.18717","title":"Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos","created":"2024-06-26","cited_by_count":97,"area":null},{"id":"2401.08399","title":"TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding","created":"2024-01-16","cited_by_count":88,"area":null},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81,"area":null},{"id":"2307.00855","title":"Review of Large Vision Models and Visual Prompt Engineering","created":"2023-07-03","cited_by_count":77,"area":null},{"id":"2402.17726","title":"VRP-SAM: SAM with Visual Reference Prompt","created":"2024-02-27","cited_by_count":75,"area":null},{"id":"2308.00675","title":"Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models","created":"2023-08-01","cited_by_count":68,"area":null},{"id":"2305.08196","title":"A Comprehensive Survey on Segment Anything Model for Vision and Beyond","created":"2023-05-14","cited_by_count":64,"area":null},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61,"area":"mllm"},{"id":"2407.20179","title":"Theia: Distilling Diverse Vision Foundation Models for Robot Learning","created":"2024-07-29","cited_by_count":61,"area":null},{"id":"2402.02385","title":"A Survey on Robotics with Foundation Models: toward Embodied AI","created":"2024-02-04","cited_by_count":56,"area":null},{"id":"2406.04221","title":"Matching Anything by Segmenting Anything","created":"2024-06-06","cited_by_count":50,"area":null},{"id":"2408.07931","title":"Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning","created":"2024-08-15","cited_by_count":47,"area":null},{"id":"2306.06211","title":"A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering","created":"2023-05-12","cited_by_count":45,"area":null},{"id":"2404.11151","title":"REACTO: Reconstructing Articulated Objects from a Single Video","created":"2024-04-17","cited_by_count":45,"area":null},{"id":"2407.07111","title":"Diffusion Model-Based Video Editing: A Survey","created":"2024-06-26","cited_by_count":44,"area":"diffusion"},{"id":"2412.09982","title":"SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video","created":"2024-12-13","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":"2404.07977","title":"Gaga: Group Any Gaussians via 3D-aware Memory Bank","created":"2024-04-11","cited_by_count":41,"area":null},{"id":"2312.02216","title":"DragVideo: Interactive Drag-style Video Editing","created":"2023-12-03","cited_by_count":40,"area":null},{"id":"2306.04121","title":"Matte Anything: Interactive Natural Image Matting with Segment Anything Models","created":"2023-06-07","cited_by_count":39,"area":null},{"id":"2406.09627","title":"RobustSAM: Segment Anything Robustly on Degraded Images","created":"2024-06-13","cited_by_count":36,"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":"2306.07713","title":"Robustness of SAM: Segment Anything Under Corruptions and Beyond","created":"2023-06-13","cited_by_count":31,"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":"2310.10513","title":"Unifying Image Processing as Visual Prompting Question Answering","created":"2023-10-16","cited_by_count":29,"area":null},{"id":"2312.01623","title":"Universal Segmentation at Arbitrary Granularity with Language Instruction","created":"2023-12-04","cited_by_count":29,"area":null},{"id":"2401.08083","title":"UV-SAM: Adapting Segment Anything Model for Urban Village Identification","created":"2024-01-16","cited_by_count":29,"area":null},{"id":"2403.16370","title":"GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation","created":"2024-03-25","cited_by_count":28,"area":null},{"id":"2305.16835","title":"OpenVIS: Open-vocabulary Video Instance Segmentation","created":"2023-05-26","cited_by_count":25,"area":null},{"id":"2307.00997","title":"RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation","created":"2023-07-03","cited_by_count":25,"area":null},{"id":"2412.20977","title":"UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI","created":"2024-12-30","cited_by_count":25,"area":null},{"id":"2401.08045","title":"Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities","created":"2024-01-16","cited_by_count":24,"area":"driving"},{"id":"2410.17249","title":"SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes","created":"2024-10-22","cited_by_count":24,"area":null},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24,"area":null},{"id":"2404.09857","title":"Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL","created":"2024-04-15","cited_by_count":23,"area":"offlinerl"},{"id":"2504.06210","title":"HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation","created":"2025-04-08","cited_by_count":22,"area":null},{"id":"2408.00754","title":"Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model","created":"2024-08-01","cited_by_count":21,"area":"lr"},{"id":"2411.18933","title":"Efficient Track Anything","created":"2024-11-28","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":"2502.06756","title":"SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2311.04414","title":"Learning the What and How of Annotation in Video Object Segmentation","created":"2023-11-08","cited_by_count":19,"area":null},{"id":"2312.06316","title":"SemiSAM: Enhancing Semi-Supervised Medical Image Segmentation via SAM-Assisted Consistency Regularization","created":"2023-12-11","cited_by_count":19,"area":null},{"id":"2503.15835","title":"BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting","created":"2025-03-20","cited_by_count":19,"area":null},{"id":"2408.16768","title":"SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners","created":"2024-08-29","cited_by_count":18,"area":null},{"id":"2409.00951","title":"Semantically Controllable Augmentations for Generalizable Robot Learning","created":"2024-09-02","cited_by_count":18,"area":null},{"id":"2407.15350","title":"WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding","created":"2024-07-22","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":"2504.04519","title":"SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation","created":"2025-04-06","cited_by_count":17,"area":null},{"id":"2312.15895","title":"Semantic-aware SAM for Point-Prompted Instance Segmentation","created":"2023-12-26","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":"2310.10912","title":"Towards Training-free Open-world Segmentation via Image Prompt Foundation Models","created":"2023-10-17","cited_by_count":15,"area":null},{"id":"2502.10040","title":"Diffusion Trajectory-guided Policy for Long-horizon Robot Manipulation","created":"2025-02-14","cited_by_count":15,"area":"vla"},{"id":"2503.12006","title":"ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object","created":"2025-03-15","cited_by_count":15,"area":null},{"id":"2305.12659","title":"UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model","created":"2023-05-22","cited_by_count":14,"area":null},{"id":"2504.00356","title":"Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2306.09278","title":"Robustness Analysis on Foundational Segmentation Models","created":"2023-06-15","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":"2308.10382","title":"False Negative/Positive Control for SAM on Noisy Medical Images","created":"2023-08-20","cited_by_count":12,"area":null},{"id":"2308.15316","title":"3D-MuPPET: 3D Multi-Pigeon Pose Estimation and Tracking","created":"2023-08-29","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":"2407.19435","title":"ASI-Seg: Audio-Driven Surgical Instrument Segmentation with Surgeon Intention Understanding","created":"2024-07-28","cited_by_count":12,"area":null},{"id":"2410.10719","title":"4-LEGS: 4D Language Embedded Gaussian Splatting","created":"2024-10-14","cited_by_count":12,"area":null},{"id":"2309.00655","title":"RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion","created":"2023-09-01","cited_by_count":11,"area":null},{"id":"2310.06992","title":"Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models","created":"2023-10-10","cited_by_count":11,"area":null},{"id":"2408.09115","title":"GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentation","created":"2024-08-17","cited_by_count":11,"area":null},{"id":"2412.01826","title":"RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations","created":"2024-12-02","cited_by_count":11,"area":null},{"id":"2504.11092","title":"Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting","created":"2025-04-15","cited_by_count":11,"area":null},{"id":"2311.11465","title":"Understanding Segment Anything Model: SAM is Biased Towards Texture Rather than Shape","created":"2023-06-03","cited_by_count":10,"area":null},{"id":"2501.16443","title":"Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning","created":"2025-01-27","cited_by_count":10,"area":"wm"},{"id":"2504.05541","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2510.01119","title":"Instant4D: 4D Gaussian Splatting in Minutes","created":"2025-10-01","cited_by_count":10,"area":null},{"id":"2310.01946","title":"CoralVOS: Dataset and Benchmark for Coral Video Segmentation","created":"2023-10-03","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":"2405.17940","title":"World Models for General Surgical Grasping","created":"2024-05-28","cited_by_count":9,"area":"wm"},{"id":"2506.07996","title":"UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2311.10529","title":"Enhancing the Reliability of Segment Anything Model for Auto-Prompting Medical Image Segmentation with Uncertainty Rectification","created":"2023-11-17","cited_by_count":8,"area":null},{"id":"2312.14481","title":"SurgicalPart-SAM: Part-to-Whole Collaborative Prompting for Surgical Instrument Segmentation","created":"2023-12-22","cited_by_count":8,"area":null},{"id":"2402.16338","title":"BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM","created":"2024-02-26","cited_by_count":8,"area":null},{"id":"2405.02608","title":"UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model","created":"2024-05-04","cited_by_count":8,"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":"2507.09577","title":"Memory-Augmented SAM2 for Training-Free Surgical Video Segmentation","created":"2025-07-13","cited_by_count":8,"area":null},{"id":"2308.06962","title":"Color-NeuS: Reconstructing Neural Implicit Surfaces with Color","created":"2023-08-14","cited_by_count":7,"area":null}],"next_cursor":"100"}