{"total":62,"rows":[{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230,"area":null},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710,"area":null},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321,"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":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104,"area":null},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89,"area":null},{"id":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75,"area":null},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2103.16110","title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain","created":"2021-03-30","cited_by_count":67,"area":"mllm"},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2301.05226","title":"See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning","created":"2023-01-12","cited_by_count":51,"area":"lr"},{"id":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27,"area":null},{"id":"2110.02526","title":"Coarse-to-Fine Reasoning for Visual Question Answering","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2209.10326","title":"Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering","created":"2022-09-21","cited_by_count":25,"area":"lr"},{"id":"2306.08751","title":"Improving Selective Visual Question Answering by Learning from Your Peers","created":"2023-06-14","cited_by_count":25,"area":null},{"id":"2105.04836","title":"Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules","created":"2021-05-11","cited_by_count":22,"area":null},{"id":"2104.08108","title":"Cross-Modal Retrieval Augmentation for Multi-Modal Classification","created":"2021-04-16","cited_by_count":20,"area":null},{"id":"2109.13139","title":"Multimodal Integration of Human-Like Attention in Visual Question Answering","created":"2021-09-27","cited_by_count":20,"area":null},{"id":"2105.14300","title":"LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answering","created":"2021-05-29","cited_by_count":17,"area":null},{"id":"2302.09636","title":"Interpretable Medical Image Visual Question Answering via Multi-Modal Relationship Graph Learning","created":"2023-02-19","cited_by_count":17,"area":null},{"id":"2109.13116","title":"VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2106.04484","title":"Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions","created":"2021-06-08","cited_by_count":15,"area":null},{"id":"2410.20883","title":"Improving Generalization in Visual Reasoning via Self-Ensemble","created":"2024-10-28","cited_by_count":15,"area":"lr"},{"id":"2108.08965","title":"Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling","created":"2021-08-20","cited_by_count":14,"area":null},{"id":"2212.13296","title":"VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challenges","created":"2022-12-26","cited_by_count":14,"area":"lr"},{"id":"2208.01813","title":"TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation","created":"2022-08-03","cited_by_count":12,"area":null},{"id":"2105.00421","title":"A survey on VQA_Datasets and Approaches","created":"2021-05-02","cited_by_count":11,"area":null},{"id":"2309.02155","title":"S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning","created":"2023-09-05","cited_by_count":10,"area":null},{"id":"2402.02503","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","created":"2024-02-04","cited_by_count":9,"area":null},{"id":"2105.11541","title":"Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation","created":"2021-05-24","cited_by_count":8,"area":null},{"id":"2204.00879","title":"Co-VQA : Answering by Interactive Sub Question Sequence","created":"2022-04-02","cited_by_count":8,"area":null},{"id":"2407.15346","title":"Knowledge Acquisition Disentanglement for Knowledge-based Visual Question Answering with Large Language Models","created":"2024-07-22","cited_by_count":8,"area":null},{"id":"2105.04780","title":"Cross-Modal Generative Augmentation for Visual Question Answering","created":"2021-05-11","cited_by_count":7,"area":null},{"id":"2205.12616","title":"Guiding Visual Question Answering with Attention Priors","created":"2022-05-25","cited_by_count":7,"area":"lr"},{"id":"2209.06954","title":"Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering","created":"2022-09-14","cited_by_count":7,"area":"mllm"},{"id":"2210.10176","title":"Entity-Focused Dense Passage Retrieval for Outside-Knowledge Visual Question Answering","created":"2022-10-18","cited_by_count":7,"area":null},{"id":"2210.14966","title":"What's Different between Visual Question Answering for Machine \"Understanding\" Versus for Accessibility?","created":"2022-10-26","cited_by_count":6,"area":null},{"id":"2310.09147","title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2112.12792","title":"Understanding and Measuring Robustness of Multimodal Learning","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2310.19516","title":"Generating Context-Aware Natural Answers for Questions in 3D Scenes","created":"2023-10-30","cited_by_count":5,"area":null},{"id":"2404.13947","title":"Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answering","created":"2024-04-22","cited_by_count":5,"area":"mllm"},{"id":"2112.07270","title":"Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering","created":"2021-12-14","cited_by_count":4,"area":null},{"id":"2304.01603","title":"Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA","created":"2023-04-04","cited_by_count":4,"area":null},{"id":"2106.13445","title":"A Picture May Be Worth a Hundred Words for Visual Question Answering","created":"2021-06-25","cited_by_count":3,"area":null},{"id":"2401.10712","title":"Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge","created":"2024-01-19","cited_by_count":3,"area":"lr"},{"id":"2403.10037","title":"Knowledge Condensation and Reasoning for Knowledge-based VQA","created":"2024-03-15","cited_by_count":3,"area":"lr"},{"id":"2412.18351","title":"Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering","created":"2024-12-24","cited_by_count":3,"area":"agents"},{"id":"2103.14712","title":"Generating and Evaluating Explanations of Attended and Error-Inducing Input Regions for VQA Models","created":"2021-03-26","cited_by_count":2,"area":null},{"id":"2112.13706","title":"Multi-Image Visual Question Answering","created":"2021-12-27","cited_by_count":2,"area":null},{"id":"2202.07712","title":"Privacy Preserving Visual Question Answering","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2203.12929","title":"Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2205.05137","title":"Sibylvariant Transformations for Robust Text Classification","created":"2022-05-10","cited_by_count":2,"area":null},{"id":"2207.01772","title":"Vision-and-Language Pretraining","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2109.02370","title":"Improved RAMEN: Towards Domain Generalization for Visual Question Answering","created":"2021-09-06","cited_by_count":1,"area":null},{"id":"2111.03994","title":"NarrationBot and InfoBot: A Hybrid System for Automated Video Description","created":"2021-11-07","cited_by_count":1,"area":null},{"id":"2405.11145","title":"Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless Predictions","created":"2024-05-18","cited_by_count":1,"area":null},{"id":"2512.05530","title":"MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models","created":"2025-12-05","cited_by_count":1,"area":"lr"},{"id":"2111.06075","title":"Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture","created":"2021-11-11","cited_by_count":0,"area":null},{"id":"2202.08124","title":"XFBoost: Improving Text Generation with Controllable Decoders","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2607.23921","title":"DDVT: Dynamic Dual-level Vision Transformer Fusion Network for Answer Grounding in Visual Question Answering","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":null}