{"total":125,"rows":[{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540,"area":null},{"id":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312,"area":null},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","cited_by_count":187,"area":null},{"id":"2303.02151","title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","created":"2023-03-03","cited_by_count":152,"area":null},{"id":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135,"area":null},{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103,"area":null},{"id":"2310.12945","title":"3D-GPT: Procedural 3D Modeling with Large Language Models","created":"2023-10-19","cited_by_count":95,"area":null},{"id":"2304.01195","title":"Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement","created":"2023-04-03","cited_by_count":84,"area":null},{"id":"2302.02551","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","created":"2023-02-06","cited_by_count":79,"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":"2403.06659","title":"Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement","created":"2024-03-11","cited_by_count":67,"area":null},{"id":"2306.05493","title":"Multi-Modal Classifiers for Open-Vocabulary Object Detection","created":"2023-06-08","cited_by_count":53,"area":null},{"id":"2305.18287","title":"LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections","created":"2023-05-29","cited_by_count":43,"area":null},{"id":"2312.10908","title":"CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update","created":"2023-12-18","cited_by_count":43,"area":null},{"id":"2311.16241","title":"SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance","created":"2023-11-27","cited_by_count":41,"area":null},{"id":"2304.03391","title":"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval","created":"2023-04-06","cited_by_count":36,"area":null},{"id":"2309.01093","title":"CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection","created":"2023-09-03","cited_by_count":36,"area":null},{"id":"2312.09788","title":"Collaborating Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-15","cited_by_count":34,"area":null},{"id":"2309.00096","title":"AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation","created":"2023-08-31","cited_by_count":29,"area":null},{"id":"2211.15603","title":"Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation","created":"2022-11-28","cited_by_count":28,"area":null},{"id":"2401.01736","title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2401.13837","title":"Democratizing Fine-grained Visual Recognition with Large Language Models","created":"2024-01-24","cited_by_count":25,"area":null},{"id":"2404.06194","title":"Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"area":null},{"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":"2310.19660","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2404.17753","title":"Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification","created":"2024-04-27","cited_by_count":19,"area":null},{"id":"2404.09941","title":"Evolving Interpretable Visual Classifiers with Large Language Models","created":"2024-04-15","cited_by_count":18,"area":null},{"id":"2310.09929","title":"Prompting Scientific Names for Zero-Shot Species Recognition","created":"2023-10-15","cited_by_count":14,"area":null},{"id":"2311.01064","title":"Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Images","created":"2023-11-02","cited_by_count":13,"area":null},{"id":"2401.04651","title":"Learning to Prompt Segment Anything Models","created":"2024-01-09","cited_by_count":13,"area":null},{"id":"2306.10191","title":"Neural Priming for Sample-Efficient Adaptation","created":"2023-06-16","cited_by_count":12,"area":null},{"id":"2308.09033","title":"Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks","created":"2023-08-17","cited_by_count":12,"area":null},{"id":"2410.13016","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","created":"2024-10-16","cited_by_count":12,"area":null},{"id":"2311.18402","title":"MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2405.10053","title":"SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection","created":"2024-05-16","cited_by_count":11,"area":null},{"id":"2410.01544","title":"Boosting Weakly-Supervised Referring Image Segmentation via Progressive Comprehension","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2403.02626","title":"Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2412.09402","title":"MultiEYE: Dataset and Benchmark for OCT-Enhanced Retinal Disease Recognition from Fundus Images","created":"2024-12-12","cited_by_count":9,"area":null},{"id":"2302.12948","title":"Agile Modeling: From Concept to Classifier in Minutes","created":"2023-02-25","cited_by_count":8,"area":null},{"id":"2309.06809","title":"TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification","created":"2023-09-13","cited_by_count":8,"area":null},{"id":"2404.00701","title":"Training-Free Semantic Segmentation via LLM-Supervision","created":"2024-03-31","cited_by_count":8,"area":null},{"id":"2408.00759","title":"Text-Guided Video Masked Autoencoder","created":"2024-08-01","cited_by_count":8,"area":null},{"id":"2408.06970","title":"Prompt-Based Segmentation at Multiple Resolutions and Lighting Conditions using Segment Anything Model 2","created":"2024-08-13","cited_by_count":8,"area":null},{"id":"2508.03207","title":"Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration","created":"2025-08-05","cited_by_count":8,"area":null},{"id":"2307.04317","title":"Text Descriptions are Compressive and Invariant Representations for Visual Learning","created":"2023-07-10","cited_by_count":7,"area":null},{"id":"2312.15571","title":"A Survey on Open-Set Image Recognition","created":"2023-12-25","cited_by_count":7,"area":null},{"id":"2406.00639","title":"An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition","created":"2024-06-02","cited_by_count":7,"area":null},{"id":"2302.11557","title":"K-Diag: Knowledge-enhanced Disease Diagnosis in Radiographic Imaging","created":"2023-02-22","cited_by_count":6,"area":null},{"id":"2311.13612","title":"Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning","created":"2023-11-21","cited_by_count":6,"area":null},{"id":"2408.00331","title":"DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation","created":"2024-08-01","cited_by_count":6,"area":null},{"id":"2412.10624","title":"CATALOG: A Camera Trap Language-guided Contrastive Learning Model","created":"2024-12-14","cited_by_count":6,"area":null},{"id":"2503.16106","title":"OSLoPrompt: Bridging Low-Supervision Challenges and Open-Set Domain Generalization in CLIP","created":"2025-03-20","cited_by_count":6,"area":null},{"id":"2505.16778","title":"Single Domain Generalization for Few-Shot Counting via Universal Representation Matching","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2310.14804","title":"Large Language Models can Share Images, Too!","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2311.11293","title":"From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web","created":"2023-11-19","cited_by_count":5,"area":null},{"id":"2408.04879","title":"On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey","created":"2024-08-09","cited_by_count":5,"area":null},{"id":"2411.19346","title":"CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections","created":"2024-11-28","cited_by_count":5,"area":null},{"id":"2510.04564","title":"Conditional Representation Learning for Customized Tasks","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2401.01482","title":"Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition","created":"2024-01-03","cited_by_count":4,"area":null},{"id":"2405.13007","title":"News Recommendation with Category Description by a Large Language Model","created":"2024-05-13","cited_by_count":4,"area":null},{"id":"2406.02774","title":"Diffusion-Refined VQA Annotations for Semi-Supervised Gaze Following","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2407.18058","title":"I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2503.20301","title":"Attribute-formed Class-specific Concept Space: Endowing Language Bottleneck Model with Better Interpretability and Scalability","created":"2025-03-26","cited_by_count":4,"area":null},{"id":"2504.10487","title":"FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation","created":"2025-04-14","cited_by_count":4,"area":null},{"id":"2508.01602","title":"Enhancing Zero-Shot Brain Tumor Subtype Classification via Fine-Grained Patch-Text Alignment","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2602.06333","title":"Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2402.04416","title":"Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2403.02714","title":"DomainVerse: A Benchmark Towards Real-World Distribution Shifts For Tuning-Free Adaptive Domain Generalization","created":"2024-03-05","cited_by_count":3,"area":null},{"id":"2407.17491","title":"Robust Adaptation of Foundation Models with Black-Box Visual Prompting","created":"2024-07-04","cited_by_count":3,"area":null},{"id":"2409.13676","title":"A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2411.15099","title":"Context-Aware Multimodal Pretraining","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2502.10060","title":"DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2509.22645","title":"HERMAN: Hierarchical Representation Matching for CLIP-based Class-Incremental Learning","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2509.26036","title":"SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2510.14737","title":"Free-Grained Hierarchical Visual Recognition","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2510.26311","title":"Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning","created":"2025-10-30","cited_by_count":3,"area":null},{"id":"2512.16202","title":"Open Ad-hoc Categorization with Contextualized Feature Learning","created":"2025-12-18","cited_by_count":3,"area":null},{"id":"2303.05122","title":"M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios","created":"2023-03-09","cited_by_count":2,"area":null},{"id":"2311.18420","title":"TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2410.07173","title":"Better Language Models Exhibit Higher Visual Alignment","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2411.18651","title":"Verbalized Representation Learning for Interpretable Few-Shot Generalization","created":"2024-11-27","cited_by_count":2,"area":null},{"id":"2411.19757","title":"Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models","created":"2024-11-29","cited_by_count":2,"area":null},{"id":"2412.17684","title":"COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptation","created":"2024-12-23","cited_by_count":2,"area":null},{"id":"2501.16481","title":"Generating customized prompts for Zero-Shot Rare Event Medical Image Classification using LLM","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2503.02248","title":"Making Better Mistakes in CLIP-Based Zero-Shot Classification with Hierarchy-Aware Language Prompts","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2503.05424","title":"Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2503.06847","title":"MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2506.04713","title":"Enabling Validation for Robust Few-Shot Recognition","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2508.01074","title":"Evading Data Provenance in Deep Neural Networks","created":"2025-08-01","cited_by_count":2,"area":null},{"id":"2508.03102","title":"Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2508.05065","title":"Decoupling Continual Semantic Segmentation","created":"2025-08-07","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":"2311.10933","title":"Representing visual classification as a linear combination of words","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2311.14062","title":"Hardware Resilience Properties of Text-Guided Image Classifiers","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2404.09778","title":"The Devil is in the Few Shots: Iterative Visual Knowledge Completion for Few-shot Learning","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2407.13808","title":"CoAPT: Context Attribute words for Prompt Tuning","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2407.16145","title":"Improved Few-Shot Image Classification Through Multiple-Choice Questions","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2412.00364","title":"LMSeg: Unleashing the Power of Large-Scale Models for Open-Vocabulary Semantic Segmentation","created":"2024-11-30","cited_by_count":1,"area":null}],"next_cursor":"100"}