{"total":96,"rows":[{"id":"2308.12213","title":"CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No","created":"2023-08-23","cited_by_count":130,"area":null},{"id":"2407.12442","title":"ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference","created":"2024-07-17","cited_by_count":113,"area":"mllm"},{"id":"2408.04883","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","created":"2024-08-09","cited_by_count":111,"area":null},{"id":"2312.00878","title":"Grounding Everything: Emerging Localization Properties in Vision-Language Transformers","created":"2023-12-01","cited_by_count":91,"area":"mllm"},{"id":"2305.07304","title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","created":"2023-05-12","cited_by_count":83,"area":"mllm"},{"id":"2305.08196","title":"A Comprehensive Survey on Segment Anything Model for Vision and Beyond","created":"2023-05-14","cited_by_count":64,"area":null},{"id":"2407.08268","title":"Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation","created":"2024-07-11","cited_by_count":61,"area":"mllm"},{"id":"2311.00453","title":"CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection","created":"2023-11-01","cited_by_count":58,"area":null},{"id":"2312.16580","title":"VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting","created":"2023-12-27","cited_by_count":45,"area":null},{"id":"2411.19331","title":"Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation","created":"2024-11-28","cited_by_count":44,"area":null},{"id":"2312.07374","title":"Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2306.04121","title":"Matte Anything: Interactive Natural Image Matting with Segment Anything Models","created":"2023-06-07","cited_by_count":39,"area":null},{"id":"2403.20253","title":"MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation","created":"2024-03-29","cited_by_count":37,"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":"2307.00038","title":"Training-free Object Counting with Prompts","created":"2023-06-30","cited_by_count":34,"area":null},{"id":"2411.15869","title":"Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation","created":"2024-11-24","cited_by_count":34,"area":"mllm"},{"id":"2506.23270","title":"Token Activation Map to Visually Explain Multimodal LLMs","created":"2025-06-29","cited_by_count":32,"area":"mllm"},{"id":"2402.16749","title":"MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model","created":"2024-02-26","cited_by_count":30,"area":null},{"id":"2507.02994","title":"MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2310.18049","title":"Text Augmented Spatial-aware Zero-shot Referring Image Segmentation","created":"2023-10-27","cited_by_count":21,"area":null},{"id":"2407.09033","title":"Textual Query-Driven Mask Transformer for Domain Generalized Segmentation","created":"2024-07-12","cited_by_count":21,"area":"mllm"},{"id":"2503.08723","title":"Is CLIP ideal? No. Can we fix it? Yes!","created":"2025-03-10","cited_by_count":21,"area":null},{"id":"2312.12828","title":"TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training","created":"2023-12-20","cited_by_count":19,"area":null},{"id":"2411.13836","title":"CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation","created":"2024-11-21","cited_by_count":17,"area":null},{"id":"2511.07923","title":"Exploring the Underwater World Segmentation without Extra Training","created":"2025-11-11","cited_by_count":16,"area":null},{"id":"2505.21501","title":"Vision Transformers with Self-Distilled Registers","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2403.12693","title":"As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2308.15939","title":"Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization","created":"2023-08-30","cited_by_count":10,"area":null},{"id":"2404.11957","title":"The devil is in the object boundary: towards annotation-free instance segmentation using Foundation Models","created":"2024-04-18","cited_by_count":10,"area":null},{"id":"2409.08492","title":"Tri-Plane Mamba: Efficiently Adapting Segment Anything Model for 3D Medical Images","created":"2024-09-13","cited_by_count":9,"area":"ssm"},{"id":"2501.10067","title":"FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization","created":"2025-01-17","cited_by_count":8,"area":null},{"id":"2502.18816","title":"Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP","created":"2025-02-26","cited_by_count":8,"area":"mllm"},{"id":"2505.23769","title":"TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models","created":"2025-05-29","cited_by_count":7,"area":null},{"id":"2312.15901","title":"Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation","created":"2023-12-26","cited_by_count":6,"area":"mllm"},{"id":"2404.00323","title":"CLIP-driven Outliers Synthesis for few-shot OOD detection","created":"2024-03-30","cited_by_count":6,"area":null},{"id":"2405.14294","title":"Tuning-free Universally-Supervised Semantic Segmentation","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2508.05430","title":"Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions","created":"2025-08-07","cited_by_count":6,"area":"mllm"},{"id":"2312.14149","title":"TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification","created":"2023-12-21","cited_by_count":5,"area":"mllm"},{"id":"2505.15217","title":"Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2509.22415","title":"Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models","created":"2025-09-26","cited_by_count":5,"area":"mllm"},{"id":"2404.00384","title":"TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias","created":"2024-03-30","cited_by_count":4,"area":"distill"},{"id":"2405.04782","title":"Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection","created":"2024-05-08","cited_by_count":4,"area":null},{"id":"2408.01942","title":"Visual Grounding for Object-Level Generalization in Reinforcement Learning","created":"2024-08-04","cited_by_count":4,"area":"lr"},{"id":"2504.10487","title":"FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation","created":"2025-04-14","cited_by_count":4,"area":null},{"id":"2306.08541","title":"Fine-Tuned but Zero-Shot 3D Shape Sketch View Similarity and Retrieval","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2308.12522","title":"Uniformly Distributed Category Prototype-Guided Vision-Language Framework for Long-Tail Recognition","created":"2023-08-24","cited_by_count":3,"area":"mllm"},{"id":"2406.19057","title":"Segment Anything Model for automated image data annotation: empirical studies using text prompts from Grounding DINO","created":"2024-06-27","cited_by_count":3,"area":null},{"id":"2506.06818","title":"Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation","created":"2025-06-07","cited_by_count":3,"area":null},{"id":"2507.09562","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2406.18197","title":"Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Scheme","created":"2024-06-26","cited_by_count":2,"area":"mllm"},{"id":"2407.03634","title":"SOWA: Adapting Hierarchical Frozen Window Self-Attention to Visual-Language Models for Better Anomaly Detection","created":"2024-07-04","cited_by_count":2,"area":"mllm"},{"id":"2407.11750","title":"Cycle Contrastive Adversarial Learning for Unsupervised image Deraining","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2507.13378","title":"A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospects","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2602.17799","title":"Enabling Training-Free Text-Based Remote Sensing Segmentation","created":"2026-02-19","cited_by_count":2,"area":"mllm"},{"id":"2602.20853","title":"On the Explainability of Vision-Language Models in Art History","created":"2026-02-24","cited_by_count":2,"area":"mllm"},{"id":"2603.18086","title":"SSP-SAM: SAM with Semantic-Spatial Prompt for Referring Expression Segmentation","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2605.12325","title":"VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2412.09240","title":"VLMs meet UDA: Boosting Transferability of Open Vocabulary Segmentation with Unsupervised Domain Adaptation","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2502.02977","title":"Efficiently Disentangling CLIP for Multi-Object Perception","created":"2025-02-05","cited_by_count":1,"area":"mllm"},{"id":"2503.22241","title":"Agent-Centric Personalized Multiple Clustering with Multi-Modal LLMs","created":"2025-03-28","cited_by_count":1,"area":"mllm"},{"id":"2506.23323","title":"FA-Seg: A Fast and Accurate Diffusion-Based Method for Open-Vocabulary Segmentation","created":"2025-06-29","cited_by_count":1,"area":"diffusion"},{"id":"2508.00213","title":"SAM-PTx: Text-Guided Fine-Tuning of SAM with Parameter-Efficient, Parallel-Text Adapters","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2508.03447","title":"CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection","created":"2025-08-05","cited_by_count":1,"area":"mllm"},{"id":"2509.00527","title":"Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement","created":"2025-08-30","cited_by_count":1,"area":"synth"},{"id":"2509.02962","title":"Resilient Multimodal Industrial Surface Defect Detection with Uncertain Sensors Availability","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2509.20479","title":"Are Foundation Models Ready for Industrial Defect Recognition? A Reality Check on Real-World Data","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2605.16651","title":"Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations","created":"2026-05-15","cited_by_count":1,"area":"mllm"},{"id":"2605.19410","title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2606.24997","title":"What's in an Earth Embedding? An Explainability Analysis of Location Encoders","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.03165","title":"Rethinking Brain Decoding with CLIP: The Role of Adversarial Robustness","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2504.00812","title":"Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2505.22209","title":"A Survey on Training-free Open-Vocabulary Semantic Segmentation","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2505.22259","title":"Domain Adaptation of Attention Heads for Zero-shot Anomaly Detection","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2509.18919","title":"Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2511.08156","title":"LandSegmenter: Towards a Flexible Foundation Model for Land Use and Land Cover Mapping","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2512.07360","title":"Structure-Aware Feature Rectification with Region Adjacency Graphs for Training-Free Open-Vocabulary Semantic Segmentation","created":"2025-12-08","cited_by_count":0,"area":"mllm"},{"id":"2512.24224","title":"ARM: A Learnable, Plug-and-Play Module for CLIP-based Open-vocabulary Semantic Segmentation","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2602.03594","title":"TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.14134","title":"DenseMLLM: Standard Multimodal LLMs for Dense Prediction","created":"2026-02-15","cited_by_count":0,"area":"mllm"},{"id":"2602.22462","title":"MammoWise: Multi-Model Local RAG Pipeline for Mammography Report Generation","created":"2026-02-25","cited_by_count":0,"area":"rag"},{"id":"2602.23869","title":"Open-Vocabulary Semantic Segmentation in Remote Sensing via Hierarchical Attention Masking and Model Composition","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.08347","title":"Local-Global Prompt Learning via Sparse Optimal Transport","created":"2026-03-09","cited_by_count":0,"area":"mllm"},{"id":"2603.14222","title":"Membership Inference for Contrastive Pre-training Models with Text-only PII Queries","created":"2026-03-15","cited_by_count":0,"area":"safety"},{"id":"2604.05296","title":"From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.08110","title":"OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic Segmentation","created":"2026-04-09","cited_by_count":0,"area":"mllm"},{"id":"2605.03259","title":"CropVLM: A Domain-Adapted Vision-Language Model for Open-Set Crop Analysis","created":"2026-05-05","cited_by_count":0,"area":"mllm"},{"id":"2605.24807","title":"CLIP-Guided SAM: Parameter-Efficient Semantic Conditioning for Promptable Segmentation","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.11231","title":"CFCamo: A Counterfactual Detect-or-Abstain Framework for Camouflaged Object Detection","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.07135","title":"Sparse Attention for Dense Open-Vocabulary Prediction in CLIP","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.03991","title":"Perceptual Anchoring: Prototype-Guided Text Calibration for Training-free Open-Vocabulary Semantic Segmentation","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.08283","title":"MARS-CLIP: Multi-Resolution and Attention Refined Zero-Shot Image Segmentation","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.12663","title":"What Did the MLLM Hear? Token-Level Spectro-Temporal Grounding for Audio MLLM Explainability","created":"2026-09-11","cited_by_count":0,"area":"mllm"},{"id":"2609.27142","title":"MINER: Multi-crop INference-time Enhancement for Rare-Object Retrieval with Frozen Dual Encoders","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.27356","title":"Beyond Mean Foils: Auditing Worst-Foil Specificity in Frozen CLIP Region Explanations","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.37638","title":"Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2610.05115","title":"PCLM: Small-target localization with frozen CLIP via prototype contrast and local magnification","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}