{"total":87,"rows":[{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"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":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346,"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":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85,"area":null},{"id":"2211.08545","title":"MapQA: A Dataset for Question Answering on Choropleth Maps","created":"2022-11-15","cited_by_count":85,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2205.03147","title":"From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data","created":"2022-05-06","cited_by_count":39,"area":null},{"id":"2205.08148","title":"Gender and Racial Bias in Visual Question Answering Datasets","created":"2022-05-17","cited_by_count":39,"area":null},{"id":"2204.02285","title":"SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering","created":"2022-04-05","cited_by_count":38,"area":null},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2103.05568","title":"Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering","created":"2021-03-09","cited_by_count":33,"area":null},{"id":"2202.09195","title":"A Review on Methods and Applications in Multimodal Deep Learning","created":"2022-02-18","cited_by_count":29,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2105.11087","title":"Recent Advances and Trends in Multimodal Deep Learning: A Review","created":"2021-05-24","cited_by_count":26,"area":null},{"id":"2204.13653","title":"GRIT: General Robust Image Task Benchmark","created":"2022-04-28","cited_by_count":26,"area":null},{"id":"2209.12028","title":"Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline","created":"2022-09-24","cited_by_count":25,"area":null},{"id":"2310.10942","title":"UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models","created":"2023-10-17","cited_by_count":25,"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":"2106.03921","title":"Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning","created":"2021-06-07","cited_by_count":23,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"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":"2205.12191","title":"Reassessing Evaluation Practices in Visual Question Answering: A Case Study on Out-of-Distribution Generalization","created":"2022-05-24","cited_by_count":20,"area":null},{"id":"2112.10728","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","created":"2021-12-20","cited_by_count":19,"area":null},{"id":"2210.02081","title":"Locate before Answering: Answer Guided Question Localization for Video Question Answering","created":"2022-10-05","cited_by_count":19,"area":null},{"id":"2312.15820","title":"WebVLN: Vision-and-Language Navigation on Websites","created":"2023-12-25","cited_by_count":19,"area":null},{"id":"2104.12471","title":"Contextualized Keyword Representations for Multi-modal Retinal Image Captioning","created":"2021-04-26","cited_by_count":16,"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":"2308.06262","title":"Foundation Model is Efficient Multimodal Multitask Model Selector","created":"2023-08-11","cited_by_count":16,"area":null},{"id":"2205.07548","title":"A Neuro-Symbolic ASP Pipeline for Visual Question Answering","created":"2022-05-16","cited_by_count":14,"area":null},{"id":"2101.00151","title":"DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue","created":"2021-01-01","cited_by_count":13,"area":null},{"id":"2103.03987","title":"Selective Replay Enhances Learning in Online Continual Analogical Reasoning","created":"2021-03-06","cited_by_count":12,"area":null},{"id":"2305.17690","title":"HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language","created":"2023-05-28","cited_by_count":12,"area":null},{"id":"2402.18695","title":"Grounding Language Models for Visual Entity Recognition","created":"2024-02-28","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":"2107.09858","title":"Weighted Intersection over Union (wIoU) for Evaluating Image Segmentation","created":"2021-07-21","cited_by_count":11,"area":null},{"id":"2111.14792","title":"Classification-Regression for Chart Comprehension","created":"2021-11-29","cited_by_count":11,"area":null},{"id":"2103.15022","title":"'Just because you are right, doesn't mean I am wrong': Overcoming a Bottleneck in the Development and Evaluation of Open-Ended Visual Question Answering (VQA) Tasks","created":"2021-03-28","cited_by_count":10,"area":null},{"id":"2305.00581","title":"Multimodal Graph Transformer for Multimodal Question Answering","created":"2023-04-30","cited_by_count":10,"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":"2402.09717","title":"Visually Dehallucinative Instruction Generation: Know What You Don't Know","created":"2024-02-15","cited_by_count":10,"area":null},{"id":"2503.14421","title":"ExDDV: A New Dataset for Explainable Deepfake Detection in Video","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2209.06650","title":"WildQA: In-the-Wild Video Question Answering","created":"2022-09-14","cited_by_count":9,"area":null},{"id":"2304.03147","title":"Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions","created":"2023-04-06","cited_by_count":9,"area":null},{"id":"2403.19454","title":"JDocQA: Japanese Document Question Answering Dataset for Generative Language Models","created":"2024-03-28","cited_by_count":9,"area":null},{"id":"2405.19794","title":"Video Question Answering for People with Visual Impairments Using an Egocentric 360-Degree Camera","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2107.00811","title":"Target-dependent UNITER: A Transformer-Based Multimodal Language Comprehension Model for Domestic Service Robots","created":"2021-07-02","cited_by_count":7,"area":null},{"id":"2303.02635","title":"VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning","created":"2023-03-05","cited_by_count":7,"area":null},{"id":"2304.02168","title":"I2I: Initializing Adapters with Improvised Knowledge","created":"2023-04-04","cited_by_count":7,"area":null},{"id":"2404.10652","title":"ViTextVQA: A Large-Scale Visual Question Answering Dataset and a Novel Multimodal Feature Fusion Method for Vietnamese Text Comprehension in Images","created":"2024-04-16","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":"2308.08628","title":"Learning the meanings of function words from grounded language using a visual question answering model","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2309.07403","title":"Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance","created":"2023-09-14","cited_by_count":6,"area":null},{"id":"2412.01132","title":"Eyes on the Road: State-of-the-Art Video Question Answering Models Assessment for Traffic Monitoring Tasks","created":"2024-12-02","cited_by_count":6,"area":null},{"id":"2203.01322","title":"Recent, rapid advancement in visual question answering architecture: a review","created":"2022-03-02","cited_by_count":5,"area":null},{"id":"2306.08641","title":"Towards AGI in Computer Vision: Lessons Learned from GPT and Large Language Models","created":"2023-06-14","cited_by_count":5,"area":null},{"id":"2312.13594","title":"Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2409.04053","title":"COLUMBUS: Evaluating COgnitive Lateral Understanding through Multiple-choice reBUSes","created":"2024-09-06","cited_by_count":5,"area":null},{"id":"2410.14991","title":"ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2201.03342","title":"COIN: Counterfactual Image Generation for VQA Interpretation","created":"2022-01-10","cited_by_count":4,"area":null},{"id":"2208.03030","title":"ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding","created":"2022-08-05","cited_by_count":3,"area":null},{"id":"2407.02218","title":"Multi-Modal Video Dialog State Tracking in the Wild","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2410.09379","title":"Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2503.07631","title":"OWLViz: An Open-World Benchmark for Visual Question Answering","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2509.20750","title":"Confidence-guided Refinement Reasoning for Zero-shot Question Answering","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2104.10139","title":"Towards Solving Multimodal Comprehension","created":"2021-04-20","cited_by_count":2,"area":null},{"id":"2105.07141","title":"Show Why the Answer is Correct! Towards Explainable AI using Compositional Temporal Attention","created":"2021-05-15","cited_by_count":2,"area":null},{"id":"2106.08914","title":"$C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2302.13069","title":"Medical visual question answering using joint self-supervised learning","created":"2023-02-25","cited_by_count":2,"area":null},{"id":"2312.12723","title":"Multi-Clue Reasoning with Memory Augmentation for Knowledge-based Visual Question Answering","created":"2023-12-20","cited_by_count":2,"area":null},{"id":"2409.11059","title":"OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2104.00107","title":"Analysis on Image Set Visual Question Answering","created":"2021-03-31","cited_by_count":1,"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":"2203.06215","title":"Can I see an Example? Active Learning the Long Tail of Attributes and Relations","created":"2022-03-11","cited_by_count":1,"area":null},{"id":"2301.12032","title":"BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models","created":"2023-01-28","cited_by_count":1,"area":null},{"id":"2310.04443","title":"Human Mobility Question Answering (Vision Paper)","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2408.07349","title":"Automated Retinal Image Analysis and Medical Report Generation through Deep Learning","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2410.22648","title":"SimpsonsVQA: Enhancing Inquiry-Based Learning with a Tailored Dataset","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2411.07516","title":"SparrowVQE: Visual Question Explanation for Course Content Understanding","created":"2024-11-12","cited_by_count":1,"area":null},{"id":"2101.06573","title":"Understanding in Artificial Intelligence","created":"2021-01-17","cited_by_count":0,"area":null},{"id":"2203.03727","title":"Barlow constrained optimization for Visual Question Answering","created":"2022-03-07","cited_by_count":0,"area":null},{"id":"2302.09208","title":"Bridge Damage Cause Estimation Using Multiple Images Based on Visual Question Answering","created":"2023-02-18","cited_by_count":0,"area":null},{"id":"2402.08348","title":"Visually Dehallucinative Instruction Generation","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2404.01151","title":"Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2502.09285","title":"EmoAssist: Emotional Assistant for Visual Impairment Community","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2504.14054","title":"Occlusion-Ordered Semantic Instance Segmentation","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2603.03580","title":"An Effective Data Augmentation Method by Asking Questions about Scene Text Images","created":"2026-03-03","cited_by_count":0,"area":null}],"next_cursor":null}