{"total":162,"rows":[{"id":"2411.11922","title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","created":"2024-11-18","cited_by_count":94,"area":null},{"id":"2407.20179","title":"Theia: Distilling Diverse Vision Foundation Models for Robot Learning","created":"2024-07-29","cited_by_count":61,"area":null},{"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":"2503.07135","title":"VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation","created":"2025-03-10","cited_by_count":46,"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":"2402.13349","title":"Aria Everyday Activities Dataset","created":"2024-02-20","cited_by_count":39,"area":null},{"id":"2408.10123","title":"Learning Precise Affordances from Egocentric Videos for Robotic Manipulation","created":"2024-08-19","cited_by_count":34,"area":null},{"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":"2312.09128","title":"Tokenize Anything via Prompting","created":"2023-12-14","cited_by_count":31,"area":null},{"id":"2503.14029","title":"Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting","created":"2025-03-18","cited_by_count":31,"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":"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":"2409.13401","title":"PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images","created":"2024-09-20","cited_by_count":24,"area":null},{"id":"2402.16663","title":"UN-SAM: Universal Prompt-Free Segmentation for Generalized Nuclei Images","created":"2024-02-26","cited_by_count":22,"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":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20,"area":null},{"id":"2312.05760","title":"RepViT-SAM: Towards Real-Time Segmenting Anything","created":"2023-12-10","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":"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":"2411.03706","title":"3DGS-CD: 3D Gaussian Splatting-based Change Detection for Physical Object Rearrangement","created":"2024-11-06","cited_by_count":15,"area":null},{"id":"2410.17772","title":"Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models","created":"2024-10-23","cited_by_count":14,"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":"2405.00256","title":"ASAM: Boosting Segment Anything Model with Adversarial Tuning","created":"2024-05-01","cited_by_count":12,"area":null},{"id":"2407.00718","title":"ASPS: Augmented Segment Anything Model for Polyp Segmentation","created":"2024-06-30","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":"2407.14153","title":"De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation","created":"2024-07-19","cited_by_count":11,"area":null},{"id":"2503.03045","title":"ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulation","created":"2025-03-04","cited_by_count":11,"area":null},{"id":"2510.24195","title":"Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2","created":"2025-10-28","cited_by_count":11,"area":null},{"id":"2603.22387","title":"Efficient Universal Perception Encoder","created":"2026-03-23","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":"2404.08255","title":"Practical Region-level Attack against Segment Anything Models","created":"2024-04-12","cited_by_count":9,"area":null},{"id":"2407.00596","title":"HATs: Hierarchical Adaptive Taxonomy Segmentation for Panoramic Pathology Image Analysis","created":"2024-06-30","cited_by_count":9,"area":null},{"id":"2505.18686","title":"WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation","created":"2025-05-24","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":"2401.07502","title":"Compositional Oil Spill Detection Based on Object Detector and Adapted Segment Anything Model from SAR Images","created":"2024-01-15","cited_by_count":8,"area":null},{"id":"2402.12677","title":"Object-level Geometric Structure Preserving for Natural Image Stitching","created":"2024-02-20","cited_by_count":8,"area":null},{"id":"2503.04106","title":"WeakMedSAM: Weakly-Supervised Medical Image Segmentation via SAM with Sub-Class Exploration and Prompt Affinity Mining","created":"2025-03-06","cited_by_count":8,"area":null},{"id":"2504.08603","title":"FindAnything: Open-Vocabulary and Object-Centric Mapping for Robot Exploration in Any Environment","created":"2025-04-11","cited_by_count":8,"area":null},{"id":"2504.14440","title":"SG-Reg: Generalizable and Efficient Scene Graph Registration","created":"2025-04-20","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":"2403.09195","title":"SAM-Lightening: A Lightweight Segment Anything Model with Dilated Flash Attention to Achieve 30 times Acceleration","created":"2024-03-14","cited_by_count":7,"area":null},{"id":"2408.02924","title":"Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater Environment","created":"2024-08-06","cited_by_count":7,"area":null},{"id":"2412.10943","title":"Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes","created":"2024-12-14","cited_by_count":7,"area":null},{"id":"2501.13667","title":"MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation","created":"2025-01-23","cited_by_count":7,"area":null},{"id":"2503.06261","title":"Segment Anything, Even Occluded","created":"2025-03-08","cited_by_count":7,"area":null},{"id":"2503.17733","title":"GS-LTS: 3D Gaussian Splatting-Based Adaptive Modeling for Long-Term Service Robots","created":"2025-03-22","cited_by_count":7,"area":null},{"id":"2506.06026","title":"O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2511.19425","title":"SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation","created":"2025-11-24","cited_by_count":7,"area":null},{"id":"2401.10228","title":"RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything","created":"2024-01-18","cited_by_count":6,"area":null},{"id":"2403.04924","title":"$\\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2409.07172","title":"Swin-LiteMedSAM: A Lightweight Box-Based Segment Anything Model for Large-Scale Medical Image Datasets","created":"2024-09-11","cited_by_count":6,"area":null},{"id":"2501.01101","title":"Deformable Gaussian Splatting for Efficient and High-Fidelity Reconstruction of Surgical Scenes","created":"2025-01-02","cited_by_count":6,"area":null},{"id":"2407.08965","title":"Lite-SAM Is Actually What You Need for Segment Everything","created":"2024-07-12","cited_by_count":5,"area":null},{"id":"2411.11285","title":"Zero-Shot Automatic Annotation and Instance Segmentation using LLM-Generated Datasets: Eliminating Field Imaging and Manual Annotation for Deep Learning Model Development","created":"2024-11-18","cited_by_count":5,"area":null},{"id":"2505.15581","title":"Advancing Marine Research: UWSAM Framework and UIIS10K Dataset for Precise Underwater Instance Segmentation","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2506.11131","title":"Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2507.00659","title":"LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment","created":"2025-07-01","cited_by_count":5,"area":null},{"id":"2508.08697","title":"ROD: RGB-Only Fast and Efficient Off-road Freespace Detection","created":"2025-08-12","cited_by_count":5,"area":null},{"id":"2511.15771","title":"UniUltra: Interactive Parameter-Efficient SAM2 for Universal Ultrasound Segmentation","created":"2025-11-19","cited_by_count":5,"area":null},{"id":"2403.04194","title":"SAM-PD: How Far Can SAM Take Us in Tracking and Segmenting Anything in Videos by Prompt Denoising","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2405.20109","title":"FMARS: Annotating Remote Sensing Images for Disaster Management using Foundation Models","created":"2024-05-30","cited_by_count":4,"area":null},{"id":"2407.09979","title":"PFPs: Prompt-guided Flexible Pathological Segmentation for Diverse Potential Outcomes Using Large Vision and Language Models","created":"2024-07-13","cited_by_count":4,"area":null},{"id":"2407.10131","title":"WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models","created":"2024-07-14","cited_by_count":4,"area":null},{"id":"2502.01216","title":"Exploring Few-Shot Defect Segmentation in General Industrial Scenarios with Metric Learning and Vision Foundation Models","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2503.07266","title":"RS2-SAM2: Customized SAM2 for Referring Remote Sensing Image Segmentation","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2505.04861","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2506.02854","title":"Hierarchical Self-Prompting SAM: A Prompt-Free Medical Image Segmentation Framework","created":"2025-06-03","cited_by_count":4,"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":"2511.20027","title":"SAM-MI: A Mask-Injected Framework for Enhancing Open-Vocabulary Semantic Segmentation with SAM","created":"2025-11-25","cited_by_count":4,"area":null},{"id":"2603.16063","title":"ViT-AdaLA: Adapting Vision Transformers with Linear Attention","created":"2026-03-17","cited_by_count":4,"area":null},{"id":"2603.26541","title":"OVI-MAP:Open-Vocabulary Instance-Semantic Mapping","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2402.05008","title":"EfficientViT-SAM: Accelerated Segment Anything Model Without Accuracy Loss","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2409.02368","title":"Pluralistic Salient Object Detection","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2410.16995","title":"E-3DGS: Gaussian Splatting with Exposure and Motion Events","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2502.02257","title":"UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2503.06515","title":"SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model","created":"2025-03-09","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":"2506.06909","title":"Gaussian Mapping for Evolving Scenes","created":"2025-06-07","cited_by_count":3,"area":null},{"id":"2506.21547","title":"SAM4D: Segment Anything in Camera and LiDAR Streams","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2512.22830","title":"3D Scene Change Modeling With Consistent Multi-View Aggregation","created":"2025-12-28","cited_by_count":3,"area":null},{"id":"2601.00537","title":"Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarios","created":"2026-01-02","cited_by_count":3,"area":null},{"id":"2602.21712","title":"Innovative Tooth Segmentation Using Hierarchical Features and Bidirectional Sequence Modeling","created":"2026-02-25","cited_by_count":3,"area":null},{"id":"2312.06736","title":"SqueezeSAM: User friendly mobile interactive segmentation","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2401.04403","title":"MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation","created":"2024-01-09","cited_by_count":2,"area":null},{"id":"2403.09307","title":"Annotation Free Semantic Segmentation with Vision Foundation Models","created":"2024-03-14","cited_by_count":2,"area":null},{"id":"2408.05729","title":"A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot","created":"2024-08-11","cited_by_count":2,"area":null},{"id":"2409.17486","title":"Global-Local Medical SAM Adaptor Based on Full Adaption","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2410.10267","title":"big.LITTLE Vision Transformer for Efficient Visual Recognition","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2410.12214","title":"Order-aware Interactive Segmentation","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2411.02974","title":"Region-Guided Attack on the Segment Anything Model (SAM)","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2412.20901","title":"ILDiff: Generate Transparent Animated Stickers by Implicit Layout Distillation","created":"2024-12-30","cited_by_count":2,"area":null},{"id":"2502.02763","title":"Looking Locally: Object-Centric Vision Transformers as Foundation Models for Efficient Segmentation","created":"2025-02-04","cited_by_count":2,"area":null},{"id":"2502.12604","title":"S2C: Learning Noise-Resistant Differences for Unsupervised Change Detection in Multimodal Remote Sensing Images","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2504.21544","title":"SAM4EM: Efficient memory-based two stage prompt-free segment anything model adapter for complex 3D neuroscience electron microscopy stacks","created":"2025-04-30","cited_by_count":2,"area":null},{"id":"2505.22855","title":"IRS: Incremental Relationship-guided Segmentation for Digital Pathology","created":"2025-05-28","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":"2507.22792","title":"Segment Anything for Video: A Comprehensive Review of Video Object Segmentation and Tracking from Past to Future","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2509.12741","title":"Force-Modulated Visual Policy for Robot-Assisted Dressing with Arm Motions","created":"2025-09-16","cited_by_count":2,"area":null}],"next_cursor":"100"}