{"total":51,"rows":[{"id":"2210.10163","title":"MedCLIP: Contrastive Learning from Unpaired Medical Images and Text","created":"2022-10-18","cited_by_count":570,"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":"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":"2401.10815","title":"Exploring scalable medical image encoders beyond text supervision","created":"2024-01-19","cited_by_count":132,"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":"2402.08093","title":"BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data","created":"2024-02-12","cited_by_count":75,"area":null},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68,"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":"2303.15796","title":"KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation","created":"2023-03-28","cited_by_count":39,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39,"area":null},{"id":"2306.07196","title":"Retrieval-Enhanced Contrastive Vision-Text Models","created":"2023-06-12","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":"2403.16005","title":"Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval","created":"2024-03-24","cited_by_count":36,"area":null},{"id":"2301.10939","title":"Affective Faces for Goal-Driven Dyadic Communication","created":"2023-01-26","cited_by_count":35,"area":null},{"id":"2212.06202","title":"Doubly Right Object Recognition: A Why Prompt for Visual Rationales","created":"2022-12-12","cited_by_count":29,"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":"2306.14060","title":"DesCo: Learning Object Recognition with Rich Language Descriptions","created":"2023-06-24","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":"2402.02968","title":"Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives","created":"2024-02-05","cited_by_count":23,"area":null},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2404.09447","title":"kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies","created":"2024-04-15","cited_by_count":20,"area":null},{"id":"2207.12888","title":"LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection","created":"2022-07-26","cited_by_count":18,"area":null},{"id":"2304.08480","title":"DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training","created":"2023-04-17","cited_by_count":15,"area":null},{"id":"2205.12617","title":"DisinfoMeme: A Multimodal Dataset for Detecting Meme Intentionally Spreading Out Disinformation","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2206.01125","title":"Prefix Conditioning Unifies Language and Label Supervision","created":"2022-06-02","cited_by_count":13,"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":"2304.14204","title":"Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining","created":"2023-04-26","cited_by_count":11,"area":null},{"id":"2309.14327","title":"DeepSpeed-VisualChat: Multi-Round Multi-Image Interleave Chat via Multi-Modal Causal Attention","created":"2023-09-25","cited_by_count":10,"area":null},{"id":"2311.01025","title":"Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2408.12023","title":"Limitations in Employing Natural Language Supervision for Sensor-Based Human Activity Recognition -- And Ways to Overcome Them","created":"2024-08-21","cited_by_count":10,"area":null},{"id":"2306.07952","title":"MOFI: Learning Image Representations from Noisy Entity Annotated Images","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2411.01494","title":"Finding NeMo: Negative-mined Mosaic Augmentation for Referring Image Segmentation","created":"2024-11-03","cited_by_count":7,"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":"2403.10047","title":"TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model","created":"2024-03-15","cited_by_count":5,"area":null},{"id":"2410.02086","title":"Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2506.14107","title":"D\\'ej\\`a Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2307.11934","title":"LAMP: Leveraging Language Prompts for Multi-person Pose Estimation","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2311.08782","title":"Language Semantic Graph Guided Data-Efficient Learning","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2508.21550","title":"EZ-Sort: Efficient Pairwise Comparison via Zero-Shot CLIP-Based Pre-Ordering and Human-in-the-Loop Sorting","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2210.05879","title":"Learning by Asking Questions for Knowledge-based Novel Object Recognition","created":"2022-10-12","cited_by_count":2,"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":"2502.16733","title":"Coreset Selection via LLM-based Concept Bottlenecks","created":"2025-02-23","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":"2511.17103","title":"Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text Pairs","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2412.02262","title":"Composing Open-domain Vision with RAG for Ocean Monitoring and Conservation","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2508.06832","title":"Remote Sensing Image Intelligent Interpretation with the Language-Centered Perspective: Principles, Methods and Challenges","created":"2025-08-09","cited_by_count":1,"area":null},{"id":"2603.20839","title":"Dodgersort: Uncertainty-Aware VLM-Guided Human-in-the-Loop Pairwise Ranking","created":"2026-03-21","cited_by_count":1,"area":null},{"id":"2311.14544","title":"Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning","created":"2023-11-24","cited_by_count":0,"area":null},{"id":"2411.15611","title":"If you can describe it, they can see it: Cross-Modal Learning of Visual Concepts from Textual Descriptions","created":"2024-11-23","cited_by_count":0,"area":null},{"id":"2610.00973","title":"Concept Driven Domain Adaptation: Finding an Abstract Needle in a Haystack","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}