{"total":110,"rows":[{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"area":null},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"area":null},{"id":"2311.13165","title":"Multimodal Large Language Models: A Survey","created":"2023-11-22","cited_by_count":195,"area":"mllm"},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171,"area":null},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2406.10328","title":"From Pixels to Prose: A Large Dataset of Dense Image Captions","created":"2024-06-14","cited_by_count":54,"area":"mllm"},{"id":"2310.06838","title":"AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description","created":"2023-10-10","cited_by_count":49,"area":null},{"id":"2202.01993","title":"Grounding Answers for Visual Questions Asked by Visually Impaired People","created":"2022-02-04","cited_by_count":47,"area":null},{"id":"2402.18091","title":"Polos: Multimodal Metric Learning from Human Feedback for Image Captioning","created":"2024-02-28","cited_by_count":46,"area":"alignment"},{"id":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43,"area":"mllm"},{"id":"2305.14897","title":"Text encoders bottleneck compositionality in contrastive vision-language models","created":"2023-05-24","cited_by_count":34,"area":"mllm"},{"id":"2204.11964","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","created":"2022-04-25","cited_by_count":30,"area":null},{"id":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27,"area":null},{"id":"2506.11672","title":"Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning","created":"2025-06-13","cited_by_count":27,"area":"mllm"},{"id":"2211.09778","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","created":"2022-11-17","cited_by_count":26,"area":null},{"id":"2312.00968","title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","created":"2023-12-01","cited_by_count":26,"area":"mllm"},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2205.13125","title":"Prompt-based Learning for Unpaired Image Captioning","created":"2022-05-26","cited_by_count":23,"area":null},{"id":"2109.13701","title":"CIDEr-R: Robust Consensus-based Image Description Evaluation","created":"2021-09-28","cited_by_count":22,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2205.10646","title":"Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics","created":"2022-05-21","cited_by_count":18,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2308.12383","title":"With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning","created":"2023-08-23","cited_by_count":18,"area":null},{"id":"2206.09592","title":"DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection","created":"2022-06-20","cited_by_count":17,"area":"diffusion"},{"id":"2207.07243","title":"LineCap: Line Charts for Data Visualization Captioning Models","created":"2022-07-15","cited_by_count":17,"area":null},{"id":"2404.14715","title":"FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction","created":"2024-04-23","cited_by_count":17,"area":"mllm"},{"id":"2405.09931","title":"Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition","created":"2024-05-16","cited_by_count":17,"area":null},{"id":"2410.07336","title":"Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training","created":"2024-10-09","cited_by_count":16,"area":null},{"id":"2104.08376","title":"Concadia: Towards Image-Based Text Generation with a Purpose","created":"2021-04-16","cited_by_count":15,"area":null},{"id":"2203.13883","title":"Multi-modal Misinformation Detection: Approaches, Challenges and Opportunities","created":"2022-03-25","cited_by_count":15,"area":null},{"id":"2502.18290","title":"Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models","created":"2025-02-25","cited_by_count":14,"area":"mllm"},{"id":"2502.16098","title":"Beyond Visual Perception: Insights from Smartphone Interaction of Visually Impaired Users with Large Multimodal Models","created":"2025-02-22","cited_by_count":13,"area":"mllm"},{"id":"2512.11715","title":"EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing","created":"2025-12-12","cited_by_count":12,"area":"diffusion"},{"id":"2204.12974","title":"CapOnImage: Context-driven Dense-Captioning on Image","created":"2022-04-27","cited_by_count":11,"area":null},{"id":"2207.11810","title":"VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments","created":"2022-07-24","cited_by_count":11,"area":null},{"id":"2403.01487","title":"InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding","created":"2024-03-03","cited_by_count":11,"area":"mllm"},{"id":"2405.00485","title":"What Makes for Good Image Captions?","created":"2024-05-01","cited_by_count":11,"area":null},{"id":"2407.04923","title":"OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video Understanding","created":"2024-07-06","cited_by_count":11,"area":"mllm"},{"id":"2409.14083","title":"SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information","created":"2024-09-21","cited_by_count":11,"area":"mllm"},{"id":"2409.19255","title":"DENEB: A Hallucination-Robust Automatic Evaluation Metric for Image Captioning","created":"2024-09-28","cited_by_count":11,"area":null},{"id":"2503.22610","title":"Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users","created":"2025-03-28","cited_by_count":11,"area":"mllm"},{"id":"2309.05956","title":"Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation","created":"2023-09-12","cited_by_count":10,"area":"diffusion"},{"id":"2403.07469","title":"A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes","created":"2024-03-12","cited_by_count":10,"area":null},{"id":"2108.02059","title":"Question-controlled Text-aware Image Captioning","created":"2021-08-04","cited_by_count":9,"area":null},{"id":"2306.05240","title":"Dealing with Semantic Underspecification in Multimodal NLP","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2311.15562","title":"Fully Authentic Visual Question Answering Dataset from Online Communities","created":"2023-11-27","cited_by_count":9,"area":null},{"id":"2406.02265","title":"Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning","created":"2024-06-04","cited_by_count":9,"area":"rag"},{"id":"2103.11474","title":"#PraCegoVer: A Large Dataset for Image Captioning in Portuguese","created":"2021-03-21","cited_by_count":8,"area":null},{"id":"2105.08106","title":"Multi-Modal Image Captioning for the Visually Impaired","created":"2021-05-17","cited_by_count":8,"area":null},{"id":"2304.14623","title":"Quality-agnostic Image Captioning to Safely Assist People with Vision Impairment","created":"2023-04-28","cited_by_count":8,"area":null},{"id":"2407.06177","title":"Vision-Language Models under Cultural and Inclusive Considerations","created":"2024-07-08","cited_by_count":8,"area":"mllm"},{"id":"2603.17809","title":"Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients","created":"2026-03-18","cited_by_count":8,"area":"mllm"},{"id":"2111.12727","title":"Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets","created":"2021-11-24","cited_by_count":7,"area":null},{"id":"2301.05323","title":"Salient Object Detection for Images Taken by People With Vision Impairments","created":"2023-01-12","cited_by_count":7,"area":null},{"id":"2306.08173","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2411.10945","title":"Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera","created":"2024-11-17","cited_by_count":7,"area":null},{"id":"2311.04192","title":"JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models","created":"2023-11-07","cited_by_count":6,"area":null},{"id":"2210.06716","title":"Low-resource Neural Machine Translation with Cross-modal Alignment","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2303.08389","title":"PR-MCS: Perturbation Robust Metric for MultiLingual Image Captioning","created":"2023-03-15","cited_by_count":5,"area":null},{"id":"2405.06611","title":"\"We are at the mercy of others' opinion\": Supporting Blind People in Recreational Window Shopping with AI-infused Technology","created":"2024-05-10","cited_by_count":5,"area":null},{"id":"2406.00980","title":"Selectively Answering Visual Questions","created":"2024-06-03","cited_by_count":5,"area":"mllm"},{"id":"2407.18243","title":"BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairments","created":"2024-07-25","cited_by_count":5,"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":"2410.08860","title":"Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2412.10761","title":"Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation","created":"2024-12-14","cited_by_count":5,"area":null},{"id":"2507.01409","title":"CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2212.03230","title":"Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning","created":"2022-12-06","cited_by_count":4,"area":null},{"id":"2306.00301","title":"CapText: Large Language Model-based Caption Generation From Image Context and Description","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2307.10518","title":"Interactive Segmentation for Diverse Gesture Types Without Context","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2308.10447","title":"Explore and Tell: Embodied Visual Captioning in 3D Environments","created":"2023-08-21","cited_by_count":3,"area":null},{"id":"2504.11441","title":"TADACap: Time-series Adaptive Domain-Aware Captioning","created":"2025-04-15","cited_by_count":3,"area":null},{"id":"2511.08917","title":"\"It's trained by non-disabled people\": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models","created":"2025-11-12","cited_by_count":3,"area":"mllm"},{"id":"2604.21718","title":"Building a Precise Video Language with Human-AI Oversight","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2401.10005","title":"Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation","created":"2024-01-18","cited_by_count":2,"area":"lr"},{"id":"2409.14215","title":"@Bench: Benchmarking Vision-Language Models for Human-centered Assistive Technology","created":"2024-09-21","cited_by_count":2,"area":"mllm"},{"id":"2609.36893","title":"Momentum-Coupled Rubric Adaptation for Detailed Image Captioning","created":"2026-09-29","cited_by_count":2,"area":null},{"id":"2108.12575","title":"Goal-driven text descriptions for images","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2205.14769","title":"UPB at SemEval-2022 Task 5: Enhancing UNITER with Image Sentiment and Graph Convolutional Networks for Multimedia Automatic Misogyny Identification","created":"2022-05-29","cited_by_count":1,"area":null},{"id":"2304.07567","title":"CoVLR: Coordinating Cross-Modal Consistency and Intra-Modal Structure for Vision-Language Retrieval","created":"2023-04-15","cited_by_count":1,"area":null},{"id":"2306.03500","title":"Towards Adaptable and Interactive Image Captioning with Data Augmentation and Episodic Memory","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2312.10613","title":"p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models","created":"2023-12-17","cited_by_count":1,"area":"mllm"},{"id":"2403.17564","title":"Task-Oriented Paraphrase Analytics","created":"2024-03-26","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":"2408.15714","title":"Pixels to Prose: Understanding the art of Image Captioning","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2106.05437","title":"Data augmentation to improve robustness of image captioning solutions","created":"2021-06-10","cited_by_count":0,"area":null},{"id":"2201.00969","title":"Interactive Attention AI to translate low light photos to captions for night scene understanding in women safety","created":"2022-01-04","cited_by_count":0,"area":null},{"id":"2202.05331","title":"Describing image focused in cognitive and visual details for visually impaired people: An approach to generating inclusive paragraphs","created":"2022-02-10","cited_by_count":0,"area":null},{"id":"2211.09427","title":"Feedback is Needed for Retakes: An Explainable Poor Image Notification Framework for the Visually Impaired","created":"2022-11-17","cited_by_count":0,"area":null},{"id":"2306.01753","title":"Preconditioned Visual Language Inference with Weak Supervision","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2306.03476","title":"Putting Humans in the Image Captioning Loop","created":"2023-06-06","cited_by_count":0,"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":"2407.19351","title":"AccessShare: Co-designing Data Access and Sharing with Blind People","created":"2024-07-27","cited_by_count":0,"area":null},{"id":"2408.16827","title":"Fluent and Accurate Image Captioning with a Self-Trained Reward Model","created":"2024-08-29","cited_by_count":0,"area":"alignment"},{"id":"2503.19361","title":"ImageSet2Text: Describing Sets of Images through Text","created":"2025-03-25","cited_by_count":0,"area":null}],"next_cursor":"100"}