{"total":102,"rows":[{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2310.18961","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","created":"2023-10-29","cited_by_count":271,"area":null},{"id":"2210.07225","title":"Unified Vision and Language Prompt Learning","created":"2022-10-13","cited_by_count":148,"area":"mllm"},{"id":"2310.16436","title":"DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models","created":"2023-10-25","cited_by_count":128,"area":"lr"},{"id":"2306.01293","title":"LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning","created":"2023-06-02","cited_by_count":107,"area":null},{"id":"2304.05653","title":"A Closer Look at the Explainability of Contrastive Language-Image Pre-training","created":"2023-04-12","cited_by_count":96,"area":"mllm"},{"id":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91,"area":null},{"id":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67,"area":null},{"id":"2311.16194","title":"BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP","created":"2023-11-26","cited_by_count":67,"area":"mllm"},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59,"area":null},{"id":"2210.02390","title":"Bayesian Prompt Learning for Image-Language Model Generalization","created":"2022-10-05","cited_by_count":51,"area":null},{"id":"2211.12739","title":"Texts as Images in Prompt Tuning for Multi-Label Image Recognition","created":"2022-11-23","cited_by_count":51,"area":"mllm"},{"id":"2404.03248","title":"Learning Transferable Negative Prompts for Out-of-Distribution Detection","created":"2024-04-04","cited_by_count":43,"area":null},{"id":"2211.02219","title":"Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models","created":"2022-11-04","cited_by_count":40,"area":"mllm"},{"id":"2312.07353","title":"CLIP in Medical Imaging: A Survey","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2503.20188","title":"Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector","created":"2025-03-26","cited_by_count":40,"area":"mllm"},{"id":"2307.16634","title":"CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification","created":"2023-07-31","cited_by_count":39,"area":null},{"id":"2304.04521","title":"GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection","created":"2023-04-10","cited_by_count":36,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2207.01887","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","created":"2022-07-05","cited_by_count":33,"area":null},{"id":"2307.03135","title":"Distilling Large Vision-Language Model with Out-of-Distribution Generalizability","created":"2023-07-06","cited_by_count":33,"area":"mllm"},{"id":"2306.01669","title":"Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning","created":"2023-06-02","cited_by_count":30,"area":"mllm"},{"id":"2407.01400","title":"GalLoP: Learning Global and Local Prompts for Vision-Language Models","created":"2024-07-01","cited_by_count":29,"area":"mllm"},{"id":"2410.00320","title":"PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection","created":"2024-10-01","cited_by_count":29,"area":null},{"id":"2303.18232","title":"DIME-FM: DIstilling Multimodal and Efficient Foundation Models","created":"2023-03-31","cited_by_count":28,"area":"mllm"},{"id":"2303.13223","title":"Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels","created":"2023-03-23","cited_by_count":24,"area":null},{"id":"2304.04512","title":"Defense-Prefix for Preventing Typographic Attacks on CLIP","created":"2023-04-10","cited_by_count":24,"area":"mllm"},{"id":"2501.18592","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2308.01890","title":"DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations","created":"2023-08-03","cited_by_count":22,"area":null},{"id":"2307.11978","title":"Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?","created":"2023-07-22","cited_by_count":21,"area":"mllm"},{"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":"2409.19696","title":"Vision-Language Models are Strong Noisy Label Detectors","created":"2024-09-29","cited_by_count":16,"area":"mllm"},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2305.04536","title":"LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition","created":"2023-05-08","cited_by_count":15,"area":null},{"id":"2411.03359","title":"Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection","created":"2024-11-05","cited_by_count":15,"area":"mllm"},{"id":"2504.14280","title":"CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey","created":"2025-04-19","cited_by_count":15,"area":null},{"id":"2405.06926","title":"TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Prompt","created":"2024-05-11","cited_by_count":14,"area":"mllm"},{"id":"2208.13474","title":"Prompt Tuning with Soft Context Sharing for Vision-Language Models","created":"2022-08-29","cited_by_count":13,"area":"mllm"},{"id":"2401.04651","title":"Learning to Prompt Segment Anything Models","created":"2024-01-09","cited_by_count":13,"area":null},{"id":"2303.09100","title":"Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Models","created":"2023-03-16","cited_by_count":12,"area":"mllm"},{"id":"2310.15985","title":"Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning","created":"2023-10-24","cited_by_count":10,"area":null},{"id":"2510.08177","title":"Long-tailed Recognition with Model Rebalancing","created":"2025-10-09","cited_by_count":10,"area":null},{"id":"2407.18520","title":"Text-Region Matching for Multi-Label Image Recognition with Missing Labels","created":"2024-07-26","cited_by_count":9,"area":null},{"id":"2507.09500","title":"Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations","created":"2025-07-13","cited_by_count":9,"area":"mllm"},{"id":"2403.01209","title":"Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning","created":"2024-03-02","cited_by_count":8,"area":"mllm"},{"id":"2403.12964","title":"Enhancing Vision-Language Few-Shot Adaptation with Negative Learning","created":"2024-03-19","cited_by_count":8,"area":"mllm"},{"id":"2306.16016","title":"Positive Label Is All You Need for Multi-Label Classification","created":"2023-06-28","cited_by_count":7,"area":null},{"id":"2406.15556","title":"Open-Vocabulary Temporal Action Localization using Multimodal Guidance","created":"2024-06-21","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":"2404.16193","title":"Improving Multi-label Recognition using Class Co-Occurrence Probabilities","created":"2024-04-24","cited_by_count":6,"area":null},{"id":"2405.03501","title":"Boosting Single Positive Multi-label Classification with Generalized Robust Loss","created":"2024-05-06","cited_by_count":6,"area":null},{"id":"2503.15337","title":"Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2301.04494","title":"Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains","created":"2023-01-11","cited_by_count":5,"area":null},{"id":"2407.09073","title":"Open Vocabulary Multi-Label Video Classification","created":"2024-07-12","cited_by_count":5,"area":"mllm"},{"id":"2407.15173","title":"Rethinking Domain Adaptation and Generalization in the Era of CLIP","created":"2024-07-21","cited_by_count":5,"area":null},{"id":"2502.19106","title":"A Survey on Foundation-Model-Based Industrial Defect Detection","created":"2025-02-26","cited_by_count":5,"area":null},{"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":"2506.21017","title":"Multimodal Prompt Alignment for Facial Expression Recognition","created":"2025-06-26","cited_by_count":4,"area":"mllm"},{"id":"2312.04160","title":"Text as Image: Learning Transferable Adapter for Multi-Label Classification","created":"2023-12-07","cited_by_count":3,"area":"mllm"},{"id":"2409.12499","title":"End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2507.05020","title":"Adaptation of Multi-modal Representation Models for Multi-task Surgical Computer Vision","created":"2025-07-07","cited_by_count":3,"area":null},{"id":"2508.06382","title":"Text as Any-Modality for Zero-Shot Classification by Consistent Prompt Tuning","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2511.09540","title":"vMFCoOp: Towards Equilibrium on a Unified Hyperspherical Manifold for Prompting Biomedical VLMs","created":"2025-11-12","cited_by_count":3,"area":"mllm"},{"id":"2401.01181","title":"Query-Based Knowledge Sharing for Open-Vocabulary Multi-Label Classification","created":"2024-01-02","cited_by_count":2,"area":"distill"},{"id":"2403.19669","title":"Analyzing the Roles of Language and Vision in Learning from Limited Data","created":"2024-02-15","cited_by_count":2,"area":null},{"id":"2404.03144","title":"Diverse and Tailored Image Generation for Zero-shot Multi-label Classification","created":"2024-04-04","cited_by_count":2,"area":null},{"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":"2407.20920","title":"SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition","created":"2024-07-30","cited_by_count":2,"area":null},{"id":"2502.16911","title":"SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models","created":"2025-02-24","cited_by_count":2,"area":"mllm"},{"id":"2503.19670","title":"fine-CLIP: Enhancing Zero-Shot Fine-Grained Surgical Action Recognition with Vision-Language Models","created":"2025-03-25","cited_by_count":2,"area":"mllm"},{"id":"2504.03801","title":"Semantic-guided Representation Learning for Multi-Label Recognition","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2505.01064","title":"Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs","created":"2025-05-02","cited_by_count":2,"area":"mllm"},{"id":"2507.05007","title":"Multi-modal Representations for Fine-grained Multi-label Critical View of Safety Recognition","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2401.16991","title":"Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels","created":"2024-01-30","cited_by_count":1,"area":null},{"id":"2405.06468","title":"Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image Classification","created":"2024-05-10","cited_by_count":1,"area":"mllm"},{"id":"2409.08381","title":"Rethinking Prompting Strategies for Multi-Label Recognition with Partial Annotations","created":"2024-09-12","cited_by_count":1,"area":"mllm"},{"id":"2502.02977","title":"Efficiently Disentangling CLIP for Multi-Object Perception","created":"2025-02-05","cited_by_count":1,"area":"mllm"},{"id":"2503.06993","title":"CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model","created":"2025-03-10","cited_by_count":1,"area":"mllm"},{"id":"2505.11758","title":"Generalizable Vision-Language Few-Shot Adaptation with Predictive Prompts and Negative Learning","created":"2025-05-16","cited_by_count":1,"area":"mllm"},{"id":"2506.10575","title":"Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning","created":"2025-06-12","cited_by_count":1,"area":"mllm"},{"id":"2506.10730","title":"IQE-CLIP: Instance-aware Query Embedding for Zero-/Few-shot Anomaly Detection in Medical Domain","created":"2025-06-12","cited_by_count":1,"area":"mllm"},{"id":"2507.05992","title":"Exploring Partial Multi-Label Learning via Integrating Semantic Co-occurrence Knowledge","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.03277","title":"PointAD+: Learning Hierarchical Representations for Zero-shot 3D Anomaly Detection","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2510.04770","title":"Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2511.20641","title":"Unleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognition","created":"2025-11-25","cited_by_count":1,"area":"mllm"},{"id":"2403.11631","title":"Compositional Kronecker Context Optimization for Vision-Language Models","created":"2024-03-18","cited_by_count":0,"area":"mllm"},{"id":"2403.16482","title":"Determined Multi-Label Learning via Similarity-Based Prompt","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2405.08695","title":"The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2405.15860","title":"Free Performance Gain from Mixing Multiple Partially Labeled Samples in Multi-label Image Classification","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2406.06119","title":"A Survey on Incomplete Multi-label Learning: Recent Advances and Future Trends","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2406.11252","title":"Mining Open Semantics from CLIP: A Relation Transition Perspective for Few-Shot Learning","created":"2024-06-17","cited_by_count":0,"area":"mllm"},{"id":"2407.04994","title":"The Solution for Language-Enhanced Image New Category Discovery","created":"2024-07-06","cited_by_count":0,"area":null},{"id":"2412.13732","title":"Modeling Multi-modal Cross-interaction for Multi-label Few-shot Image Classification Based on Local Feature Selection","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2509.23335","title":"DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2510.10055","title":"Incomplete Multi-Label Image Recognition by Co-learning Semantic-Aware Features and Label Recovery","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2511.18396","title":"Exploring Weak-to-Strong Generalization for CLIP-based Classification","created":"2025-11-23","cited_by_count":0,"area":"safety"},{"id":"2603.11617","title":"Noise-aware few-shot learning through bi-directional multi-view prompt alignment","created":"2026-03-12","cited_by_count":0,"area":"mllm"},{"id":"2604.03980","title":"Gram-Anchored Prompt Learning for Vision-Language Models via Second-Order Statistics","created":"2026-04-05","cited_by_count":0,"area":"mllm"},{"id":"2605.28347","title":"FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2608.12088","title":"RA-ClipScore: Making Generative Model Evaluation More Interpretable","created":"2026-08-12","cited_by_count":0,"area":null}],"next_cursor":"100"}