{"total":146,"rows":[{"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":"2412.16256","title":"Aria-UI: Visual Grounding for GUI Instructions","created":"2024-12-20","cited_by_count":140,"area":null},{"id":"2403.03174","title":"MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting","created":"2024-03-05","cited_by_count":129,"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":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97,"area":null},{"id":"2403.14610","title":"T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy","created":"2024-03-21","cited_by_count":94,"area":null},{"id":"2312.11557","title":"SAI3D: Segment Any Instance in 3D Scenes","created":"2023-12-17","cited_by_count":90,"area":null},{"id":"2410.16268","title":"SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree","created":"2024-10-21","cited_by_count":80,"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":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75,"area":null},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71,"area":null},{"id":"2412.04455","title":"Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection","created":"2024-12-05","cited_by_count":63,"area":null},{"id":"2307.09220","title":"A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future","created":"2023-07-18","cited_by_count":61,"area":null},{"id":"2606.03748","title":"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models","created":"2026-06-02","cited_by_count":57,"area":null},{"id":"2310.03923","title":"Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation","created":"2023-10-05","cited_by_count":54,"area":null},{"id":"2311.13601","title":"Visual In-Context Prompting","created":"2023-11-22","cited_by_count":52,"area":null},{"id":"2312.13305","title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","created":"2023-12-20","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":"2408.11811","title":"EmbodiedSAM: Online Segment Any 3D Thing in Real Time","created":"2024-08-21","cited_by_count":40,"area":null},{"id":"2410.06964","title":"Bridge the Points: Graph-based Few-shot Segment Anything Semantically","created":"2024-10-09","cited_by_count":35,"area":null},{"id":"2312.09788","title":"Collaborating Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-15","cited_by_count":34,"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":"2409.18431","title":"Search3D: Hierarchical Open-Vocabulary 3D Segmentation","created":"2024-09-27","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":"2401.17904","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","created":"2024-01-31","cited_by_count":30,"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":"2406.20081","title":"Segment Anything without Supervision","created":"2024-06-28","cited_by_count":28,"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":"2402.18115","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries","created":"2024-02-28","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":"2502.02548","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","created":"2025-02-04","cited_by_count":22,"area":null},{"id":"2310.08530","title":"X-Pose: Detecting Any Keypoints","created":"2023-10-12","cited_by_count":21,"area":null},{"id":"2310.14277","title":"A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application","created":"2023-10-22","cited_by_count":21,"area":null},{"id":"2504.10445","title":"RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users","created":"2025-04-14","cited_by_count":21,"area":null},{"id":"2311.13596","title":"T-Rex: Counting by Visual Prompting","created":"2023-11-22","cited_by_count":20,"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":"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":"2407.19323","title":"MSP-MVS: Multi-Granularity Segmentation Prior Guided Multi-View Stereo","created":"2024-07-27","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":"2407.16696","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2507.05427","title":"OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts","created":"2025-07-07","cited_by_count":15,"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":"2401.04651","title":"Learning to Prompt Segment Anything Models","created":"2024-01-09","cited_by_count":13,"area":null},{"id":"2405.00587","title":"GraCo: Granularity-Controllable Interactive Segmentation","created":"2024-05-01","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":"2402.08960","title":"Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision","created":"2024-02-14","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":"2408.09085","title":"Segment Anything with Multiple Modalities","created":"2024-08-17","cited_by_count":12,"area":null},{"id":"2410.14980","title":"DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain","created":"2024-10-19","cited_by_count":12,"area":null},{"id":"2503.01309","title":"OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging","created":"2025-03-03","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":"2602.16356","title":"Articulated 3D Scene Graphs for Open-World Mobile Manipulation","created":"2026-02-18","cited_by_count":11,"area":null},{"id":"2312.03628","title":"Boosting Segment Anything Model Towards Open-Vocabulary Learning","created":"2023-12-06","cited_by_count":10,"area":null},{"id":"2406.02435","title":"Generative Active Learning for Long-tailed Instance Segmentation","created":"2024-06-04","cited_by_count":10,"area":null},{"id":"2512.17459","title":"3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework","created":"2025-12-19","cited_by_count":10,"area":null},{"id":"2311.04246","title":"ADFactory: An Effective Framework for Generalizing Optical Flow with Nerf","created":"2023-11-07","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":"2407.21284","title":"Robust Box Prompt based SAM for Medical Image Segmentation","created":"2024-07-31","cited_by_count":9,"area":null},{"id":"2501.00752","title":"Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation","created":"2025-01-01","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},{"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":"2404.05661","title":"Automatic Controllable Colorization via Imagination","created":"2024-04-08","cited_by_count":7,"area":null},{"id":"2411.15288","title":"There is no SAMantics! Exploring SAM as a Backbone for Visual Understanding Tasks","created":"2024-11-22","cited_by_count":7,"area":null},{"id":"2504.05249","title":"Texture2LoD3: Enabling LoD3 Building Reconstruction With Panoramic Images","created":"2025-04-07","cited_by_count":7,"area":null},{"id":"2311.15776","title":"Stable Segment Anything Model","created":"2023-11-27","cited_by_count":6,"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":"2401.12217","title":"Exploring Simple Open-Vocabulary Semantic Segmentation","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2404.02585","title":"Unsegment Anything by Simulating Deformation","created":"2024-04-03","cited_by_count":6,"area":null},{"id":"2407.16682","title":"SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2408.06632","title":"EditScribe: Non-Visual Image Editing with Natural Language Verification Loops","created":"2024-08-13","cited_by_count":6,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2510.03701","title":"Referring Expression Comprehension for Small Objects","created":"2025-10-04","cited_by_count":6,"area":null},{"id":"2403.19607","title":"SAID-NeRF: Segmentation-AIDed NeRF for Depth Completion of Transparent Objects","created":"2024-03-28","cited_by_count":5,"area":null},{"id":"2405.15286","title":"3D Annotation-Free Learning by Distilling 2D Open-Vocabulary Segmentation Models for Autonomous Driving","created":"2024-05-24","cited_by_count":5,"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":"2407.09686","title":"SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images","created":"2024-07-12","cited_by_count":5,"area":null},{"id":"2408.11030","title":"OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2409.18733","title":"Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval","created":"2024-09-26","cited_by_count":5,"area":null},{"id":"2412.15979","title":"MR-GDINO: Efficient Open-World Continual Object Detection","created":"2024-12-20","cited_by_count":5,"area":null},{"id":"2309.11077","title":"Weak Supervision for Label Efficient Visual Bug Detection","created":"2023-09-20","cited_by_count":4,"area":null},{"id":"2404.11299","title":"Learning from Unlabelled Data with Transformers: Domain Adaptation for Semantic Segmentation of High Resolution Aerial Images","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2404.13239","title":"Beyond Pixel-Wise Supervision for Medical Image Segmentation: From Traditional Models to Foundation Models","created":"2024-04-20","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":"2412.10719","title":"Just a Few Glances: Open-Set Visual Perception with Image Prompt Paradigm","created":"2024-12-14","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":"2403.01418","title":"A Simple-but-effective Baseline for Training-free Class-Agnostic Counting","created":"2024-03-03","cited_by_count":3,"area":null},{"id":"2404.11981","title":"Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation","created":"2024-04-18","cited_by_count":3,"area":null},{"id":"2406.11384","title":"Understanding Multi-Granularity for Open-Vocabulary Part Segmentation","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2503.01130","title":"AirRoom: Objects Matter in Room Reidentification","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2503.12094","title":"E-SAM: Training-Free Segment Every Entity Model","created":"2025-03-15","cited_by_count":3,"area":null},{"id":"2503.16413","title":"M3: 3D-Spatial MultiModal Memory","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2601.23159","title":"Segment Any Events with Language","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2606.08980","title":"EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2403.10780","title":"Segment Any Object Model (SAOM): Real-to-Simulation Fine-Tuning Strategy for Multi-Class Multi-Instance Segmentation","created":"2024-03-16","cited_by_count":2,"area":null}],"next_cursor":"100"}