{"total":113,"rows":[{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681,"area":null},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687,"area":null},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532,"area":null},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376,"area":null},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274,"area":null},{"id":"2212.03588","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","created":"2022-12-07","cited_by_count":178,"area":null},{"id":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","cited_by_count":163,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151,"area":null},{"id":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","cited_by_count":141,"area":null},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120,"area":null},{"id":"2203.05328","title":"Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking","created":"2022-03-10","cited_by_count":119,"area":null},{"id":"2206.09541","title":"DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations","created":"2022-06-20","cited_by_count":102,"area":null},{"id":"2210.00990","title":"Visual Prompt Tuning for Generative Transfer Learning","created":"2022-10-03","cited_by_count":75,"area":null},{"id":"2302.04156","title":"Prompting for Multimodal Hateful Meme Classification","created":"2023-02-08","cited_by_count":69,"area":null},{"id":"2411.10332","title":"Number it: Temporal Grounding Videos like Flipping Manga","created":"2024-11-15","cited_by_count":65,"area":null},{"id":"2207.07180","title":"Contrastive Adapters for Foundation Model Group Robustness","created":"2022-07-14","cited_by_count":62,"area":null},{"id":"2207.14571","title":"Prompting for Multi-Modal Tracking","created":"2022-07-29","cited_by_count":59,"area":null},{"id":"2303.08138","title":"Diversity-Aware Meta Visual Prompting","created":"2023-03-14","cited_by_count":58,"area":null},{"id":"2203.11654","title":"Fine-Grained Scene Graph Generation with Data Transfer","created":"2022-03-22","cited_by_count":57,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2205.15509","title":"ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts","created":"2022-05-31","cited_by_count":45,"area":null},{"id":"2203.06667","title":"Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video","created":"2022-03-13","cited_by_count":43,"area":null},{"id":"2307.15567","title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","created":"2023-07-28","cited_by_count":42,"area":null},{"id":"2201.05979","title":"SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples","created":"2022-01-16","cited_by_count":39,"area":null},{"id":"2205.01850","title":"Visual Commonsense in Pretrained Unimodal and Multimodal Models","created":"2022-05-04","cited_by_count":39,"area":null},{"id":"2410.05352","title":"Recent Advances of Multimodal Continual Learning: A Comprehensive Survey","created":"2024-10-07","cited_by_count":39,"area":null},{"id":"2409.17531","title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion","created":"2024-09-26","cited_by_count":36,"area":null},{"id":"2203.08055","title":"Modular and Parameter-Efficient Multimodal Fusion with Prompting","created":"2022-03-15","cited_by_count":35,"area":null},{"id":"2305.08685","title":"CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding","created":"2023-05-15","cited_by_count":35,"area":null},{"id":"2203.08481","title":"Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding","created":"2022-03-16","cited_by_count":33,"area":null},{"id":"2403.02899","title":"Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation","created":"2024-03-05","cited_by_count":32,"area":null},{"id":"2305.13500","title":"Learning Emotion Representations from Verbal and Nonverbal Communication","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2401.01244","title":"Temporal Adaptive RGBT Tracking with Modality Prompt","created":"2024-01-02","cited_by_count":30,"area":null},{"id":"2411.01327","title":"Visual Fourier Prompt Tuning","created":"2024-11-02","cited_by_count":30,"area":null},{"id":"2404.02845","title":"Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation","created":"2024-04-03","cited_by_count":28,"area":null},{"id":"2208.02532","title":"Prompt Tuning for Generative Multimodal Pretrained Models","created":"2022-08-04","cited_by_count":25,"area":null},{"id":"2404.06362","title":"Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2303.07033","title":"SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency","created":"2023-03-13","cited_by_count":24,"area":null},{"id":"2308.12509","title":"Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval","created":"2023-08-24","cited_by_count":24,"area":null},{"id":"2312.10692","title":"Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion","created":"2023-12-17","cited_by_count":24,"area":null},{"id":"2205.13125","title":"Prompt-based Learning for Unpaired Image Captioning","created":"2022-05-26","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":"2303.15591","title":"Learning Expressive Prompting With Residuals for Vision Transformers","created":"2023-03-27","cited_by_count":21,"area":null},{"id":"2311.17048","title":"Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions","created":"2023-11-28","cited_by_count":21,"area":null},{"id":"2303.04995","title":"Text-Visual Prompting for Efficient 2D Temporal Video Grounding","created":"2023-03-09","cited_by_count":18,"area":null},{"id":"2409.10566","title":"Eureka: Evaluating and Understanding Large Foundation Models","created":"2024-09-13","cited_by_count":18,"area":null},{"id":"2410.06558","title":"Deep Correlated Prompting for Visual Recognition with Missing Modalities","created":"2024-10-09","cited_by_count":18,"area":null},{"id":"2205.11166","title":"Prompt Tuning for Discriminative Pre-trained Language Models","created":"2022-05-23","cited_by_count":17,"area":null},{"id":"2303.00198","title":"Convolutional Visual Prompt for Robust Visual Perception","created":"2023-03-01","cited_by_count":17,"area":null},{"id":"2312.14232","title":"Parrot Captions Teach CLIP to Spot Text","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2412.09283","title":"InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption","created":"2024-12-12","cited_by_count":17,"area":null},{"id":"2303.08678","title":"Visual Prompt Based Personalized Federated Learning","created":"2023-03-15","cited_by_count":16,"area":null},{"id":"2410.23556","title":"Language-guided Hierarchical Fine-grained Image Forgery Detection and Localization","created":"2024-10-31","cited_by_count":16,"area":null},{"id":"2209.01882","title":"PromptAttack: Prompt-based Attack for Language Models via Gradient Search","created":"2022-09-05","cited_by_count":15,"area":null},{"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":"2312.09738","title":"3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V","created":"2023-12-15","cited_by_count":15,"area":null},{"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":"2211.00849","title":"Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection","created":"2022-11-02","cited_by_count":14,"area":null},{"id":"2312.08010","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","created":"2023-12-13","cited_by_count":14,"area":null},{"id":"2303.08998","title":"Unified Visual Relationship Detection with Vision and Language Models","created":"2023-03-16","cited_by_count":13,"area":null},{"id":"2403.17369","title":"CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning","created":"2024-03-26","cited_by_count":13,"area":null},{"id":"2304.01830","title":"Learning to Name Classes for Vision and Language Models","created":"2023-04-04","cited_by_count":12,"area":null},{"id":"2310.03123","title":"Efficient Federated Prompt Tuning for Black-box Large Pre-trained Models","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2204.07841","title":"Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting","created":"2022-04-16","cited_by_count":11,"area":null},{"id":"2206.09358","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","created":"2022-06-19","cited_by_count":11,"area":null},{"id":"2207.14465","title":"Fine-grained Retrieval Prompt Tuning","created":"2022-07-29","cited_by_count":11,"area":null},{"id":"2210.01708","title":"Exploring Parameter-Efficient Fine-Tuning to Enable Foundation Models in Federated Learning","created":"2022-10-04","cited_by_count":11,"area":null},{"id":"2304.06957","title":"MVP-SEG: Multi-View Prompt Learning for Open-Vocabulary Semantic Segmentation","created":"2023-04-14","cited_by_count":10,"area":null},{"id":"2205.02456","title":"Declaration-based Prompt Tuning for Visual Question Answering","created":"2022-05-05","cited_by_count":9,"area":null},{"id":"2307.11922","title":"Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2404.06860","title":"Monocular 3D lane detection for Autonomous Driving: Recent Achievements, Challenges, and Outlooks","created":"2024-04-10","cited_by_count":9,"area":null},{"id":"2507.02798","title":"No time to train! Training-Free Reference-Based Instance Segmentation","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2210.06466","title":"Prompt Generation Networks for Input-Space Adaptation of Frozen Vision Transformers","created":"2022-10-12","cited_by_count":8,"area":null},{"id":"2303.01788","title":"Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving","created":"2023-03-03","cited_by_count":8,"area":null},{"id":"2401.01577","title":"Test-Time Personalization with Meta Prompt for Gaze Estimation","created":"2024-01-03","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":"2407.05578","title":"FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance","created":"2024-07-08","cited_by_count":8,"area":null},{"id":"2507.07802","title":"Synergistic Prompting for Robust Visual Recognition with Missing Modalities","created":"2025-07-10","cited_by_count":8,"area":null},{"id":"2310.05867","title":"Domain-wise Invariant Learning for Panoptic Scene Graph Generation","created":"2023-10-09","cited_by_count":7,"area":null},{"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":"2507.06085","title":"A Survey on Prompt Tuning","created":"2025-07-08","cited_by_count":7,"area":null},{"id":"2210.12617","title":"Modal-specific Pseudo Query Generation for Video Corpus Moment Retrieval","created":"2022-10-23","cited_by_count":6,"area":null},{"id":"2211.02043","title":"Could Giant Pretrained Image Models Extract Universal Representations?","created":"2022-11-03","cited_by_count":6,"area":null},{"id":"2401.16861","title":"Repositioning the Subject within Image","created":"2024-01-30","cited_by_count":6,"area":null},{"id":"2404.16193","title":"Improving Multi-label Recognition using Class Co-Occurrence Probabilities","created":"2024-04-24","cited_by_count":6,"area":null},{"id":"2406.01906","title":"ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2407.02389","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","created":"2024-07-02","cited_by_count":6,"area":null},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2510.09320","title":"Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2208.14889","title":"LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data","created":"2022-08-31","cited_by_count":5,"area":null},{"id":"2211.09371","title":"CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge","created":"2022-11-17","cited_by_count":5,"area":null},{"id":"2506.21237","title":"DiMPLe -- Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation","created":"2025-06-26","cited_by_count":5,"area":null},{"id":"2310.04671","title":"Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction","created":"2023-10-07","cited_by_count":4,"area":null},{"id":"2311.17812","title":"DAP: Domain-aware Prompt Learning for Vision-and-Language Navigation","created":"2023-11-29","cited_by_count":4,"area":null},{"id":"2211.16299","title":"Transferability Estimation Based On Principal Gradient Expectation","created":"2022-11-29","cited_by_count":3,"area":null},{"id":"2403.16539","title":"Data-Efficient 3D Visual Grounding via Order-Aware Referring","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2503.06106","title":"Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain Adaptation","created":"2025-03-08","cited_by_count":3,"area":null}],"next_cursor":"100"}