{"total":48,"rows":[{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711,"area":null},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190,"area":null},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625,"area":null},{"id":"2305.13310","title":"Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching","created":"2023-05-22","cited_by_count":142,"area":null},{"id":"2308.01907","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","created":"2023-08-03","cited_by_count":116,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"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":"2404.07990","title":"OpenBias: Open-set Bias Detection in Text-to-Image Generative Models","created":"2024-04-11","cited_by_count":61,"area":null},{"id":"2312.01261","title":"TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models","created":"2023-12-03","cited_by_count":52,"area":null},{"id":"2404.02904","title":"ALOHa: A New Measure for Hallucination in Captioning Models","created":"2024-04-03","cited_by_count":45,"area":null},{"id":"2305.04118","title":"Exploring Human-Like Translation Strategy with Large Language Models","created":"2023-05-06","cited_by_count":44,"area":null},{"id":"2304.04227","title":"Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions","created":"2023-04-09","cited_by_count":42,"area":null},{"id":"2312.07374","title":"Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2304.09349","title":"LLM as A Robotic Brain: Unifying Egocentric Memory and Control","created":"2023-04-19","cited_by_count":33,"area":null},{"id":"2312.11666","title":"HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles","created":"2023-12-18","cited_by_count":30,"area":null},{"id":"2404.19752","title":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","created":"2024-04-30","cited_by_count":28,"area":null},{"id":"2305.20062","title":"Chatting Makes Perfect: Chat-based Image Retrieval","created":"2023-05-31","cited_by_count":25,"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":"2310.05010","title":"Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data","created":"2023-10-08","cited_by_count":22,"area":null},{"id":"2306.11593","title":"Improving Image Captioning Descriptiveness by Ranking and LLM-based Fusion","created":"2023-06-20","cited_by_count":21,"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":"2311.18765","title":"MLLMs-Augmented Visual-Language Representation Learning","created":"2023-11-30","cited_by_count":21,"area":null},{"id":"2406.05271","title":"USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2407.18589","title":"HICEScore: A Hierarchical Metric for Image Captioning Evaluation","created":"2024-07-26","cited_by_count":12,"area":null},{"id":"2407.17398","title":"3D Question Answering for City Scene Understanding","created":"2024-07-24","cited_by_count":10,"area":null},{"id":"2506.21233","title":"ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation","created":"2025-06-26","cited_by_count":9,"area":null},{"id":"2503.09962","title":"Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification","created":"2025-03-13","cited_by_count":8,"area":null},{"id":"2505.20873","title":"Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2308.09970","title":"Tackling Vision Language Tasks Through Learning Inner Monologues","created":"2023-08-19","cited_by_count":7,"area":null},{"id":"2403.16897","title":"Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text","created":"2024-03-25","cited_by_count":7,"area":null},{"id":"2410.05217","title":"Organizing Unstructured Image Collections using Natural Language","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2408.14547","title":"Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization","created":"2024-08-26","cited_by_count":5,"area":null},{"id":"2505.03132","title":"VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis","created":"2025-05-06","cited_by_count":5,"area":null},{"id":"2308.16349","title":"Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations","created":"2023-08-30","cited_by_count":4,"area":null},{"id":"2412.11927","title":"Transparent and Coherent Procedural Mistake Detection","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2504.08806","title":"Endowing Embodied Agents with Spatial Reasoning Capabilities for Vision-and-Language Navigation","created":"2025-04-09","cited_by_count":4,"area":null},{"id":"2405.15406","title":"A Misleading Gallery of Fluid Motion by Generative Artificial Intelligence","created":"2024-05-24","cited_by_count":3,"area":null},{"id":"2507.09562","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2408.16700","title":"GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models","created":"2024-08-29","cited_by_count":2,"area":null},{"id":"2602.19217","title":"Questions beyond Pixels: Integrating Commonsense Knowledge in Visual Question Generation for Remote Sensing","created":"2026-02-22","cited_by_count":2,"area":null},{"id":"2305.14740","title":"ECHo: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2308.02833","title":"A Comprehensive Analysis of Real-World Image Captioning and Scene Identification","created":"2023-08-05","cited_by_count":1,"area":null},{"id":"2310.01356","title":"Less is More: Toward Zero-Shot Local Scene Graph Generation via Foundation Models","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2603.03024","title":"MA-CoNav: A Master-Slave Multi-Agent Framework with Hierarchical Collaboration and Dual-Level Reflection for Long-Horizon Embodied VLN","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2412.18124","title":"VisionLLM-based Multimodal Fusion Network for Glottic Carcinoma Early Detection","created":"2024-12-24","cited_by_count":0,"area":null},{"id":"2503.19361","title":"ImageSet2Text: Describing Sets of Images through Text","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2601.15172","title":"Is Peer Review Really in Decline? Analyzing Review Quality across Venues and Time","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2607.15299","title":"MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation","created":"2026-07-07","cited_by_count":0,"area":null}],"next_cursor":null}