{"total":376,"rows":[{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863,"area":null},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360,"area":null},{"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":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455,"area":"mllm"},{"id":"2312.00732","title":"Gaussian Grouping: Segment and Edit Anything in 3D Scenes","created":"2023-12-01","cited_by_count":393,"area":null},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311,"area":"lr"},{"id":"2309.03903","title":"Tracking Anything with Decoupled Video Segmentation","created":"2023-09-07","cited_by_count":197,"area":null},{"id":"2306.16269","title":"RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model","created":"2023-06-28","cited_by_count":181,"area":null},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159,"area":"mllm"},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114,"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":"2504.03600","title":"MedSAM2: Segment Anything in 3D Medical Images and Videos","created":"2025-04-04","cited_by_count":96,"area":null},{"id":"2312.11557","title":"SAI3D: Segment Any Instance in 3D Scenes","created":"2023-12-17","cited_by_count":90,"area":null},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81,"area":null},{"id":"2402.17726","title":"VRP-SAM: SAM with Visual Reference Prompt","created":"2024-02-27","cited_by_count":75,"area":null},{"id":"2501.00599","title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","created":"2024-12-31","cited_by_count":72,"area":null},{"id":"2312.07661","title":"CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor","created":"2023-12-12","cited_by_count":69,"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":"2405.02280","title":"DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos","created":"2024-05-03","cited_by_count":63,"area":null},{"id":"2401.10232","title":"ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions","created":"2024-01-18","cited_by_count":57,"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":"2406.04221","title":"Matching Anything by Segmenting Anything","created":"2024-06-06","cited_by_count":50,"area":null},{"id":"2402.15487","title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","created":"2024-02-23","cited_by_count":48,"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":"2312.00081","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","created":"2023-11-30","cited_by_count":46,"area":"mllm"},{"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":"2504.06632","title":"PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering","created":"2025-04-09","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":"2408.03322","title":"Segment Anything in Medical Images and Videos: Benchmark and Deployment","created":"2024-08-06","cited_by_count":42,"area":null},{"id":"2312.03626","title":"TokenCompose: Text-to-Image Diffusion with Token-level Supervision","created":"2023-12-06","cited_by_count":40,"area":"diffusion"},{"id":"2503.08677","title":"OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting","created":"2025-03-11","cited_by_count":39,"area":"diffusion"},{"id":"2312.07063","title":"Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation","created":"2023-12-12","cited_by_count":38,"area":"diffusion"},{"id":"2404.02790","title":"MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation","created":"2024-04-03","cited_by_count":38,"area":null},{"id":"2406.09627","title":"RobustSAM: Segment Anything Robustly on Degraded Images","created":"2024-06-13","cited_by_count":36,"area":null},{"id":"2312.08372","title":"SAM-guided Graph Cut for 3D Instance Segmentation","created":"2023-12-13","cited_by_count":35,"area":null},{"id":"2408.12957","title":"Image Segmentation in Foundation Model Era: A Survey","created":"2024-08-23","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":"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":"2503.01610","title":"Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior","created":"2025-03-03","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":"2411.12814","title":"Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline","created":"2024-11-19","cited_by_count":30,"area":null},{"id":"2501.06693","title":"Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation","created":"2025-01-12","cited_by_count":30,"area":null},{"id":"2503.08625","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","created":"2025-03-11","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":"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":"2404.08639","title":"COCONut: Modernizing COCO Segmentation","created":"2024-04-12","cited_by_count":24,"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":"2311.11273","title":"Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection","created":"2023-11-19","cited_by_count":22,"area":"mllm"},{"id":"2402.04648","title":"OV-NeRF: Open-vocabulary Neural Radiance Fields with Vision and Language Foundation Models for 3D Semantic Understanding","created":"2024-02-07","cited_by_count":22,"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":"2406.13378","title":"PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation","created":"2024-06-19","cited_by_count":22,"area":null},{"id":"2308.14133","title":"Cheap Lunch for Medical Image Segmentation by Fine-tuning SAM on Few Exemplars","created":"2023-08-27","cited_by_count":21,"area":null},{"id":"2409.18686","title":"A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation","created":"2024-09-27","cited_by_count":21,"area":null},{"id":"2410.20197","title":"Transferable Adversarial Attacks on SAM and Its Downstream Models","created":"2024-10-26","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":"2312.01531","title":"SANeRF-HQ: Segment Anything for NeRF in High Quality","created":"2023-12-03","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":"2307.11035","title":"Cascade-DETR: Delving into High-Quality Universal Object Detection","created":"2023-07-20","cited_by_count":19,"area":null},{"id":"2408.14802","title":"RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images","created":"2024-08-27","cited_by_count":19,"area":null},{"id":"2409.15269","title":"ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild","created":"2024-09-23","cited_by_count":19,"area":null},{"id":"2310.12995","title":"Comprehensive Multimodal Segmentation in Medical Imaging: Combining YOLOv8 with SAM and HQ-SAM Models","created":"2023-10-04","cited_by_count":18,"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":"2312.05039","title":"SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Control","created":"2023-12-08","cited_by_count":18,"area":"diffusion"},{"id":"2401.05906","title":"PartSTAD: 2D-to-3D Part Segmentation Task Adaptation","created":"2024-01-11","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":"2406.11740","title":"Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policies","created":"2024-06-17","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":"2401.13051","title":"PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation","created":"2024-01-23","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":"2407.19305","title":"GP-VLS: A general-purpose vision language model for surgery","created":"2024-07-27","cited_by_count":17,"area":"mllm"},{"id":"2409.06214","title":"Towards Generalizable Scene Change Detection","created":"2024-09-10","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":"2411.00626","title":"ZIM: Zero-Shot Image Matting for Anything","created":"2024-11-01","cited_by_count":16,"area":null},{"id":"2411.16183","title":"Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking","created":"2024-11-25","cited_by_count":15,"area":null},{"id":"2412.19080","title":"Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation","created":"2024-12-26","cited_by_count":15,"area":null},{"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":"2410.09909","title":"UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation","created":"2024-10-13","cited_by_count":14,"area":null},{"id":"2411.14847","title":"Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly 4D Reconstruction","created":"2024-11-22","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":"2402.02555","title":"High-Quality Entity Segmentation and Grounding","created":"2024-02-04","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":"2411.10161","title":"SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning","created":"2024-11-15","cited_by_count":13,"area":"mllm"},{"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":"2405.00256","title":"ASAM: Boosting Segment Anything Model with Adversarial Tuning","created":"2024-05-01","cited_by_count":12,"area":null},{"id":"2406.17005","title":"PVUW 2024 Challenge on Complex Video Understanding: Methods and Results","created":"2024-06-24","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":"2408.15628","title":"CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection","created":"2024-08-28","cited_by_count":12,"area":null},{"id":"2504.05058","title":"Not All Data Are Unlearned Equally","created":"2025-04-07","cited_by_count":12,"area":"safety"},{"id":"2506.23121","title":"CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation","created":"2025-06-29","cited_by_count":12,"area":null},{"id":"2309.14809","title":"ENIGMA-51: Towards a Fine-Grained Understanding of Human-Object Interactions in Industrial Scenarios","created":"2023-09-26","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":"2311.17833","title":"DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations","created":"2023-11-29","cited_by_count":11,"area":null}],"next_cursor":"100"}