{"total":84,"rows":[{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2502.04263","title":"Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion","created":"2025-02-06","cited_by_count":43,"area":"mllm"},{"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":"2305.18010","title":"Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models","created":"2023-05-29","cited_by_count":38,"area":"mllm"},{"id":"2403.16005","title":"Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval","created":"2024-03-24","cited_by_count":36,"area":null},{"id":"2403.03715","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","created":"2024-03-06","cited_by_count":35,"area":null},{"id":"2307.16525","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","created":"2023-07-31","cited_by_count":34,"area":null},{"id":"2403.11650","title":"Prioritized Semantic Learning for Zero-shot Instance Navigation","created":"2024-03-18","cited_by_count":31,"area":null},{"id":"2312.01998","title":"Language-only Efficient Training of Zero-shot Composed Image Retrieval","created":"2023-12-04","cited_by_count":27,"area":null},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2303.15932","title":"Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation","created":"2023-03-28","cited_by_count":23,"area":null},{"id":"2310.18049","title":"Text Augmented Spatial-aware Zero-shot Referring Image Segmentation","created":"2023-10-27","cited_by_count":21,"area":null},{"id":"2401.06129","title":"Distilling Vision-Language Models on Millions of Videos","created":"2024-01-11","cited_by_count":20,"area":"mllm"},{"id":"2310.04420","title":"BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity","created":"2023-10-06","cited_by_count":19,"area":null},{"id":"2408.10202","title":"SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP","created":"2024-08-19","cited_by_count":19,"area":"mllm"},{"id":"2307.16686","title":"Guiding Image Captioning Models Toward More Specific Captions","created":"2023-07-31","cited_by_count":17,"area":null},{"id":"2402.09816","title":"Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment","created":"2024-02-15","cited_by_count":15,"area":"mllm"},{"id":"2409.04796","title":"Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection","created":"2024-09-07","cited_by_count":15,"area":null},{"id":"2312.08865","title":"Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2308.13218","title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2404.02157","title":"Segment Any 3D Object with Language","created":"2024-04-02","cited_by_count":13,"area":null},{"id":"2401.02347","title":"Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training","created":"2024-01-04","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":"2311.08396","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","created":"2023-11-14","cited_by_count":11,"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":"2409.18046","title":"IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning","created":"2024-09-26","cited_by_count":11,"area":null},{"id":"2410.09472","title":"DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning","created":"2024-10-12","cited_by_count":11,"area":"rag"},{"id":"2308.12045","title":"CgT-GAN: CLIP-guided Text GAN for Image Captioning","created":"2023-08-23","cited_by_count":10,"area":null},{"id":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2602.07026","title":"Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models","created":"2026-02-02","cited_by_count":10,"area":"mllm"},{"id":"2503.18406","title":"Instruct-CLIP: Improving Instruction-Guided Image Editing with Automated Data Refinement Using Contrastive Learning","created":"2025-03-24","cited_by_count":9,"area":null},{"id":"2309.12242","title":"Weakly-supervised Automated Audio Captioning via text only training","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2502.16427","title":"Fine-Grained Captioning of Long Videos through Scene Graph Consolidation","created":"2025-02-23","cited_by_count":8,"area":"mllm"},{"id":"2601.09385","title":"SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing","created":"2026-01-14","cited_by_count":8,"area":"mllm"},{"id":"2305.18072","title":"Image Captioning with Multi-Context Synthetic Data","created":"2023-05-29","cited_by_count":7,"area":"diffusion"},{"id":"2402.10896","title":"PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter","created":"2024-02-16","cited_by_count":7,"area":"alignment"},{"id":"2501.00437","title":"Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning","created":"2024-12-31","cited_by_count":7,"area":"diffusion"},{"id":"2404.01745","title":"Unleash the Potential of CLIP for Video Highlight Detection","created":"2024-04-02","cited_by_count":6,"area":null},{"id":"2407.11211","title":"Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2410.01529","title":"Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2306.16649","title":"ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles","created":"2023-06-29","cited_by_count":5,"area":null},{"id":"2405.07046","title":"RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning","created":"2024-05-11","cited_by_count":5,"area":null},{"id":"2512.09056","title":"ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors","created":"2025-12-09","cited_by_count":5,"area":null},{"id":"2402.17298","title":"ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2403.13756","title":"Enhancing Gait Video Analysis in Neurodegenerative Diseases by Knowledge Augmentation in Vision Language Model","created":"2024-03-20","cited_by_count":4,"area":"mllm"},{"id":"2403.18969","title":"A Survey on Large Language Models from Concept to Implementation","created":"2024-03-27","cited_by_count":4,"area":null},{"id":"2405.18258","title":"Text-only Synthesis for Image Captioning","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2505.19614","title":"Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2311.05043","title":"Zero-shot Translation of Attention Patterns in VQA Models to Natural Language","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2507.18616","title":"SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2311.18291","title":"TLDR: Text Based Last-layer Retraining for Debiasing Image Classifiers","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2503.05204","title":"Data-Efficient Generalization for Zero-shot Composed Image Retrieval","created":"2025-03-07","cited_by_count":2,"area":"mllm"},{"id":"2510.02898","title":"One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2403.19193","title":"Text Data-Centric Image Captioning with Interactive Prompts","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2409.09362","title":"Generating Event-oriented Attribution for Movies via Two-Stage Prefix-Enhanced Multimodal LLM","created":"2024-09-14","cited_by_count":1,"area":"mllm"},{"id":"2410.09365","title":"Debiasing Vison-Language Models with Text-Only Training","created":"2024-10-12","cited_by_count":1,"area":"mllm"},{"id":"2412.13834","title":"Maybe you are looking for CroQS: Cross-modal Query Suggestion for Text-to-Image Retrieval","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2509.19203","title":"Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions","created":"2025-09-23","cited_by_count":1,"area":"lr"},{"id":"2510.24446","title":"SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space","created":"2025-10-28","cited_by_count":1,"area":"lr"},{"id":"2512.03463","title":"Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models","created":"2025-12-03","cited_by_count":1,"area":"mllm"},{"id":"2512.04309","title":"Text-Only Training for Image Captioning with Retrieval Augmentation and Modality Gap Correction","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2601.02764","title":"Netflix Artwork Personalization via LLM Post-training","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2307.05591","title":"Linear Alignment of Vision-language Models for Image Captioning","created":"2023-07-10","cited_by_count":0,"area":"mllm"},{"id":"2307.14750","title":"Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation","created":"2023-07-27","cited_by_count":0,"area":"rag"},{"id":"2409.19840","title":"Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2409.19960","title":"TROPE: TRaining-Free Object-Part Enhancement for Seamlessly Improving Fine-Grained Zero-Shot Image Captioning","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2412.08158","title":"How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey","created":"2024-12-11","cited_by_count":0,"area":"lr"},{"id":"2503.23679","title":"The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2506.22817","title":"Unleashing the Multi-View Fusion Potential: Noise Correction in VLM for Open-Vocabulary 3D Scene Understanding","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2508.01270","title":"SGCap: Decoding Semantic Group for Zero-shot Video Captioning","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2602.01257","title":"Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2603.22946","title":"Caption Generation for Dongba Paintings via Prompt Learning and Semantic Fusion","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.00279","title":"The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment","created":"2026-03-31","cited_by_count":0,"area":"mllm"},{"id":"2605.22484","title":"Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2605.29628","title":"COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.28986","title":"Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.00994","title":"Entity-Faithful Repair of Synthetic Supervision for Zero-Shot Image Captioning","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.06972","title":"Generative Embedding Benchmark: How Much Information Survives in a Dense Embedding?","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.11013","title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.24142","title":"What Does Prompt Learning Change? -A Natural-Language Concept Analysis of Vision-Language Models","created":"2026-08-25","cited_by_count":0,"area":"mllm"},{"id":"2608.28218","title":"Focus Where It Counts: A Salience-Driven Vision-Language Model for Low Vision Assistance","created":"2026-08-28","cited_by_count":0,"area":"mllm"},{"id":"2609.12965","title":"Generative Retrieval for Unsupervised Text-Based Person Search","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}