{"total":34,"rows":[{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"area":null},{"id":"2303.11897","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","created":"2023-03-21","cited_by_count":428,"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":"2310.18235","title":"Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation","created":"2023-10-27","cited_by_count":171,"area":null},{"id":"2212.10846","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","created":"2022-12-21","cited_by_count":115,"area":null},{"id":"2302.11154","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","created":"2023-02-22","cited_by_count":113,"area":null},{"id":"2210.08773","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","created":"2022-10-17","cited_by_count":88,"area":null},{"id":"2303.07274","title":"Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images","created":"2023-03-13","cited_by_count":80,"area":null},{"id":"2401.07781","title":"Towards A Better Metric for Text-to-Video Generation","created":"2024-01-15","cited_by_count":51,"area":null},{"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":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24,"area":null},{"id":"2306.16762","title":"Unified Language Representation for Question Answering over Text, Tables, and Images","created":"2023-06-29","cited_by_count":22,"area":null},{"id":"2410.20327","title":"R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest","created":"2024-10-27","cited_by_count":21,"area":null},{"id":"2408.07303","title":"Enhancing Visual Question Answering through Ranking-Based Hybrid Training and Multimodal Fusion","created":"2024-08-14","cited_by_count":16,"area":null},{"id":"2310.17050","title":"Exploring Question Decomposition for Zero-Shot VQA","created":"2023-10-25","cited_by_count":12,"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":"2306.16478","title":"Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering","created":"2023-06-28","cited_by_count":10,"area":null},{"id":"2312.14055","title":"Multi-Sentence Grounding for Long-term Instructional Video","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2209.05401","title":"MaXM: Towards Multilingual Visual Question Answering","created":"2022-09-12","cited_by_count":9,"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":"2302.11752","title":"EVJVQA Challenge: Multilingual Visual Question Answering","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2303.07519","title":"Architext: Language-Driven Generative Architecture Design","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2301.03238","title":"MAQA: A Multimodal QA Benchmark for Negation","created":"2023-01-09","cited_by_count":4,"area":null},{"id":"2312.17343","title":"AQUALLM: Audio Question Answering Data Generation Using Large Language Models","created":"2023-12-28","cited_by_count":4,"area":null},{"id":"2506.03096","title":"FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2507.01627","title":"Chart Question Answering from Real-World Analytical Narratives","created":"2025-07-02","cited_by_count":3,"area":null},{"id":"2406.02889","title":"Language-guided Detection and Mitigation of Unknown Dataset Bias","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2506.16571","title":"Capturing Visualization Design Rationale","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2509.20871","title":"SCRA-VQA: Summarized Caption-Rerank for Augmented Large Language Models in Visual Question Answering","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2606.19584","title":"Language-Instructed Vision Embeddings for Controllable and Generalizable Perception","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2309.15487","title":"Tackling VQA with Pretrained Foundation Models without Further Training","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2406.08840","title":"Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2507.12816","title":"FIQ: Fundamental Question Generation with the Integration of Question Embeddings for Video Question Answering","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2511.17618","title":"Foundational Question Generation for Video Question Answering via an Embedding-Integrated Approach","created":"2025-11-18","cited_by_count":0,"area":null}],"next_cursor":null}