{"total":107,"rows":[{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776,"area":"lr"},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267,"area":null},{"id":"2503.06520","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","created":"2025-03-09","cited_by_count":239,"area":"lr"},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185,"area":null},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159,"area":"mllm"},{"id":"2301.01795","title":"PACO: Parts and Attributes of Common Objects","created":"2023-01-04","cited_by_count":146,"area":null},{"id":"2205.09329","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","created":"2022-05-19","cited_by_count":133,"area":null},{"id":"2206.10207","title":"SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders","created":"2022-06-21","cited_by_count":114,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2409.10542","title":"SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation","created":"2024-09-01","cited_by_count":69,"area":"mllm"},{"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":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53,"area":"lr"},{"id":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51,"area":null},{"id":"2212.03862","title":"Teaching Matters: Investigating the Role of Supervision in Vision Transformers","created":"2022-12-07","cited_by_count":45,"area":null},{"id":"2308.11737","title":"Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape","created":"2023-08-22","cited_by_count":44,"area":null},{"id":"2212.05946","title":"Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks","created":"2022-12-12","cited_by_count":37,"area":null},{"id":"2312.17448","title":"Tracking with Human-Intent Reasoning","created":"2023-12-29","cited_by_count":33,"area":"lr"},{"id":"2405.15232","title":"DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception","created":"2024-05-24","cited_by_count":32,"area":"mllm"},{"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":"2503.13881","title":"MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation","created":"2025-03-18","cited_by_count":28,"area":"lr"},{"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":"2309.03173","title":"PDiscoNet: Semantically consistent part discovery for fine-grained recognition","created":"2023-09-06","cited_by_count":21,"area":null},{"id":"2402.14327","title":"Subobject-level Image Tokenization","created":"2024-02-22","cited_by_count":21,"area":null},{"id":"2510.23603","title":"PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity","created":"2025-10-27","cited_by_count":21,"area":"mllm"},{"id":"2503.13026","title":"HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model","created":"2025-03-17","cited_by_count":20,"area":"mllm"},{"id":"2212.01806","title":"Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks","created":"2022-12-04","cited_by_count":18,"area":null},{"id":"2210.00314","title":"Learning Hierarchical Image Segmentation For Recognition and By Recognition","created":"2022-10-01","cited_by_count":16,"area":null},{"id":"2412.11576","title":"DCBM: Data-Efficient Visual Concept Bottleneck Models","created":"2024-12-16","cited_by_count":16,"area":null},{"id":"2305.16804","title":"Towards Open-World Segmentation of Parts","created":"2023-05-26","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":"2406.05271","title":"USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2407.14412","title":"DEAL: Disentangle and Localize Concept-level Explanations for VLMs","created":"2024-07-19","cited_by_count":14,"area":"mllm"},{"id":"2405.00587","title":"GraCo: Granularity-Controllable Interactive Segmentation","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2310.16047","title":"From Posterior Sampling to Meaningful Diversity in Image Restoration","created":"2023-10-24","cited_by_count":12,"area":null},{"id":"2505.07209","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","created":"2025-05-12","cited_by_count":12,"area":null},{"id":"2209.09117","title":"Part-Based Models Improve Adversarial Robustness","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2306.07404","title":"Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation","created":"2023-06-12","cited_by_count":11,"area":null},{"id":"2503.10596","title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","created":"2025-03-13","cited_by_count":11,"area":null},{"id":"2207.14227","title":"Visual Recognition by Request","created":"2022-07-28","cited_by_count":10,"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":"2407.04538","title":"PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers","created":"2024-07-05","cited_by_count":9,"area":null},{"id":"2503.09320","title":"2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos","created":"2025-03-12","cited_by_count":9,"area":null},{"id":"2311.08400","title":"Towards Open-Ended Visual Recognition with Large Language Model","created":"2023-11-14","cited_by_count":8,"area":null},{"id":"2510.08759","title":"Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis","created":"2025-10-09","cited_by_count":8,"area":"mllm"},{"id":"2312.09812","title":"Structural Information Guided Multimodal Pre-training for Vehicle-centric Perception","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2402.14891","title":"LLMBind: A Unified Modality-Task Integration Framework","created":"2024-02-22","cited_by_count":7,"area":"mllm"},{"id":"2403.05297","title":"PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck","created":"2024-03-08","cited_by_count":7,"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":"2502.04050","title":"PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models","created":"2025-02-06","cited_by_count":7,"area":"diffusion"},{"id":"2512.00395","title":"Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Prediction","created":"2025-11-29","cited_by_count":7,"area":"mllm"},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"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":"2407.04709","title":"Efficient 4D Radar Data Auto-labeling Method using LiDAR-based Object Detection Network","created":"2024-05-13","cited_by_count":6,"area":null},{"id":"2409.04714","title":"Unleashing the Power of Generic Segmentation Models: A Simple Baseline for Infrared Small Target Detection","created":"2024-09-07","cited_by_count":6,"area":null},{"id":"2411.00132","title":"Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales","created":"2024-10-31","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":"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":"2510.06243","title":"CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning","created":"2025-10-03","cited_by_count":5,"area":"lr"},{"id":"2207.13428","title":"Leveraging GAN Priors for Few-Shot Part Segmentation","created":"2022-07-27","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":"2412.19331","title":"CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models","created":"2024-12-26","cited_by_count":4,"area":"mllm"},{"id":"2501.09688","title":"Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation","created":"2025-01-16","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":"2505.20759","title":"PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding","created":"2025-05-27","cited_by_count":4,"area":"mllm"},{"id":"2506.16806","title":"FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation","created":"2025-06-20","cited_by_count":4,"area":"mllm"},{"id":"2308.12757","title":"PartSeg: Few-shot Part Segmentation via Part-aware Prompt Learning","created":"2023-08-24","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":"2212.10280","title":"Internal Diverse Image Completion","created":"2022-12-18","cited_by_count":2,"area":null},{"id":"2408.08108","title":"Unsupervised Part Discovery via Dual Representation Alignment","created":"2024-08-15","cited_by_count":2,"area":null},{"id":"2410.09312","title":"Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis","created":"2024-10-12","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":"2504.06432","title":"D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition","created":"2025-04-08","cited_by_count":2,"area":"diffusion"},{"id":"2507.12883","title":"HRSeg: High-Resolution Visual Perception and Enhancement for Reasoning Segmentation","created":"2025-07-17","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":"2512.19934","title":"Vehicle-centric Perception via Multimodal Structured Pre-training","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2601.19060","title":"Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models","created":"2026-01-27","cited_by_count":2,"area":"mllm"},{"id":"2606.30613","title":"Sequential Planning via Anchored Robotic Keypoints","created":"2026-06-29","cited_by_count":2,"area":"vla"},{"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":"2409.17109","title":"Unveiling Ontological Commitment in Multi-Modal Foundation Models","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.13989","title":"Reproducibility study of \"LICO: Explainable Models with Language-Image Consistency\"","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2501.04144","title":"Chirpy3D: Part-Aware Multi-View Diffusion for Creative Fine-Grained Object Generation","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2503.07346","title":"Hidden in Plain Sight -- Class Competition Focuses Attribution Maps","created":"2025-03-10","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":"2507.11985","title":"Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2508.08821","title":"3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs","created":"2025-08-12","cited_by_count":1,"area":"mllm"},{"id":"2510.25263","title":"LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentation","created":"2025-10-29","cited_by_count":1,"area":"mllm"},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2603.01305","title":"AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models","created":"2026-03-01","cited_by_count":1,"area":"mllm"},{"id":"2604.09942","title":"I Walk the Line: Examining the Role of Gestalt Continuity in Object Binding for Vision Transformers","created":"2026-04-10","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":"2405.13264","title":"Part-based Quantitative Analysis for Heatmaps","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2409.01353","title":"From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation","created":"2024-09-02","cited_by_count":0,"area":null},{"id":"2411.02858","title":"OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsing","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2502.19540","title":"Dictionary-based Framework for Interpretable and Consistent Object Parsing","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2503.17820","title":"RefCut: Interactive Segmentation with Reference Guidance","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2509.15393","title":"Generating Part-Based Global Explanations Via Correspondence","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.14583","title":"Talking Points: Describing and Localizing Pixels","created":"2025-10-16","cited_by_count":0,"area":"mllm"},{"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}],"next_cursor":"100"}