{"total":72,"rows":[{"id":"2305.03048","title":"Personalize Segment Anything Model with One Shot","created":"2023-05-04","cited_by_count":250,"area":null},{"id":"2304.03284","title":"SegGPT: Segmenting Everything In Context","created":"2023-04-06","cited_by_count":194,"area":null},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185,"area":null},{"id":"2305.13310","title":"Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching","created":"2023-05-22","cited_by_count":142,"area":null},{"id":"2411.14347","title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding","created":"2024-11-21","cited_by_count":89,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"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":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51,"area":null},{"id":"2309.08816","title":"EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding","created":"2023-09-15","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":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","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":"2503.01342","title":"UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface","created":"2025-03-03","cited_by_count":27,"area":null},{"id":"2312.08007","title":"Unveiling Parts Beyond Objects:Towards Finer-Granularity Referring Expression Segmentation","created":"2023-12-13","cited_by_count":22,"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":"2407.16696","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2512.12309","title":"WeDetect: Fast Open-Vocabulary Object Detection as Retrieval","created":"2025-12-13","cited_by_count":14,"area":null},{"id":"2507.19599","title":"Object-centric Video Question Answering with Visual Grounding and Referring","created":"2025-07-25","cited_by_count":13,"area":null},{"id":"2502.02589","title":"COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation","created":"2025-02-04","cited_by_count":12,"area":null},{"id":"2505.18816","title":"Reasoning Segmentation for Images and Videos: A Survey","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2503.10596","title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","created":"2025-03-13","cited_by_count":11,"area":null},{"id":"2504.13621","title":"Visual Intention Grounding for Egocentric Assistants","created":"2025-04-18","cited_by_count":11,"area":null},{"id":"2507.23734","title":"RAGNet: Large-scale Reasoning-based Affordance Segmentation Benchmark towards General Grasping","created":"2025-07-31","cited_by_count":11,"area":null},{"id":"2508.00518","title":"Fine-grained Spatiotemporal Grounding on Egocentric Videos","created":"2025-08-01","cited_by_count":11,"area":null},{"id":"2407.09648","title":"3x2: 3D Object Part Segmentation by 2D Semantic Correspondences","created":"2024-07-12","cited_by_count":10,"area":null},{"id":"2511.01294","title":"Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects","created":"2025-11-03","cited_by_count":9,"area":null},{"id":"2512.04585","title":"SAM3-I: Segment Anything with Instructions","created":"2025-12-04","cited_by_count":9,"area":null},{"id":"2501.02201","title":"Acknowledging Focus Ambiguity in Visual Questions","created":"2025-01-04","cited_by_count":8,"area":null},{"id":"2505.21795","title":"SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2509.13747","title":"Improving Generalized Visual Grounding with Instance-aware Joint Learning","created":"2025-09-17","cited_by_count":8,"area":null},{"id":"2407.10918","title":"PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2305.17768","title":"AIMS: All-Inclusive Multi-Level Segmentation","created":"2023-05-28","cited_by_count":6,"area":null},{"id":"2404.12386","title":"SOHES: Self-supervised Open-world Hierarchical Entity Segmentation","created":"2024-04-18","cited_by_count":6,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"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":"2504.01954","title":"Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities","created":"2025-04-02","cited_by_count":5,"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":"2505.13788","title":"Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2304.05832","title":"Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2602.13195","title":"Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2404.12289","title":"Resilience through Scene Context in Visual Referring Expression Generation","created":"2024-04-18","cited_by_count":2,"area":null},{"id":"2504.05305","title":"URECA: Unique Region Caption Anything","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2510.18083","title":"Chimera: Compositional Image Generation using Part-based Concepting","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2307.02615","title":"Human Inspired Progressive Alignment and Comparative Learning for Grounded Word Acquisition","created":"2023-07-05","cited_by_count":1,"area":null},{"id":"2406.11534","title":"Inpainting the Gaps: A Novel Framework for Evaluating Explanation Methods in Vision Transformers","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2406.12757","title":"MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2505.17695","title":"SynRES: Towards Referring Expression Segmentation in the Wild via Synthetic Data","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2604.18562","title":"AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2606.29786","title":"OP3DSG: Open-Vocabulary Part-Aware 3D Scene Graph Generation for Real-World Environments","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2608.23869","title":"Gen2Physics: Grounding Generated 3D Meshes in Physics via Multi-View Material Decomposition","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2409.19960","title":"TROPE: TRaining-Free Object-Part Enhancement for Seamlessly Improving Fine-Grained Zero-Shot Image Captioning","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2501.07434","title":"Guided SAM: Label-Efficient Part Segmentation","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2504.08166","title":"Learning Object Focused Attention","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2507.05838","title":"Inter- and Intra-image Refinement for Few Shot Segmentation","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2512.10102","title":"Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2601.01454","title":"PartImageNet++ Dataset: Enhancing Visual Models with High-Quality Part Annotations","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2602.06369","title":"Revisiting Salient Object Detection from an Observer-Centric Perspective","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2604.11411","title":"Online Reasoning Video Object Segmentation","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.12113","title":"PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.14923","title":"SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.15942","title":"Decomposed Vision-Language Alignment for Fine-Grained Open-Vocabulary Segmentation","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.16903","title":"WOW-Seg: A Word-free Open World Segmentation Model","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.22068","title":"COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.21594","title":"Boundary-by-Mask: Few-Shot Instance Segmentation with Mask-Conditioned Boundary Learning for Texture-Poor Industrial Parts","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.29267","title":"Enhancing Part-Level Point Grounding for Any Open-Source MLLMs","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2608.02140","title":"HiResNets: Native Full-HD Video Recognition with Foveal Residual Streams","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.12408","title":"GSO-Net: Visual State Machines for Hazardous Freight Transfer Compliance at Petrochemical Logistics Nodes","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.19143","title":"PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.39785","title":"Seeing as Humans Do: Learning from Motion to Segment Anything Without Supervision","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}