{"total":96,"rows":[{"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":"2103.15538","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","created":"2021-03-29","cited_by_count":84,"area":null},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65,"area":null},{"id":"2107.02331","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","created":"2021-07-06","cited_by_count":62,"area":null},{"id":"2308.12305","title":"FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning","created":"2023-08-21","cited_by_count":60,"area":null},{"id":"2306.17842","title":"SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs","created":"2023-06-30","cited_by_count":55,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2110.08515","title":"Multimodal Dialogue Response Generation","created":"2021-10-16","cited_by_count":32,"area":null},{"id":"2109.03438","title":"ArchivalQA: A Large-scale Benchmark Dataset for Open Domain Question Answering over Historical News Collections","created":"2021-09-08","cited_by_count":30,"area":null},{"id":"2203.05126","title":"PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks","created":"2022-03-10","cited_by_count":30,"area":null},{"id":"2205.05019","title":"Learning to Answer Visual Questions from Web Videos","created":"2022-05-10","cited_by_count":30,"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":"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":"2403.07874","title":"Beyond Text: Frozen Large Language Models in Visual Signal Comprehension","created":"2024-03-12","cited_by_count":23,"area":null},{"id":"2308.08414","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","created":"2023-08-16","cited_by_count":22,"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":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2112.03572","title":"Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices","created":"2021-12-07","cited_by_count":17,"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":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2410.20263","title":"EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering","created":"2024-10-26","cited_by_count":15,"area":null},{"id":"2410.23828","title":"Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection","created":"2024-10-31","cited_by_count":15,"area":null},{"id":"2104.05981","title":"CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2110.00711","title":"Asking questions on handwritten document collections","created":"2021-10-02","cited_by_count":14,"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":"2407.15589","title":"Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2502.15786","title":"MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding","created":"2025-02-18","cited_by_count":14,"area":null},{"id":"2109.08475","title":"GoG: Relation-aware Graph-over-Graph Network for Visual Dialog","created":"2021-09-17","cited_by_count":13,"area":null},{"id":"2410.10799","title":"Towards Foundation Models for 3D Vision: How Close Are We?","created":"2024-10-14","cited_by_count":13,"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":"2103.15974","title":"Domain-robust VQA with diverse datasets and methods but no target labels","created":"2021-03-29","cited_by_count":11,"area":null},{"id":"2104.07921","title":"VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks","created":"2021-04-16","cited_by_count":11,"area":null},{"id":"2109.08478","title":"Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation","created":"2021-09-17","cited_by_count":11,"area":null},{"id":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2109.06013","title":"Learning to Ground Visual Objects for Visual Dialog","created":"2021-09-13","cited_by_count":10,"area":null},{"id":"2306.16713","title":"Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering","created":"2023-06-29","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":"2206.01017","title":"Structured Two-stream Attention Network for Video Question Answering","created":"2022-06-02","cited_by_count":9,"area":null},{"id":"2209.05401","title":"MaXM: Towards Multilingual Visual Question Answering","created":"2022-09-12","cited_by_count":9,"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":"2203.17219","title":"SimVQA: Exploring Simulated Environments for Visual Question Answering","created":"2022-03-31","cited_by_count":8,"area":null},{"id":"2401.15275","title":"Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks","created":"2024-01-27","cited_by_count":8,"area":null},{"id":"2411.11150","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2206.01923","title":"From Pixels to Objects: Cubic Visual Attention for Visual Question Answering","created":"2022-06-04","cited_by_count":7,"area":null},{"id":"2209.01621","title":"Interactive Question Answering Systems: Literature Review","created":"2022-09-04","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":"2310.14670","title":"Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2502.15803","title":"Megrez-Omni Technical Report","created":"2025-02-19","cited_by_count":7,"area":null},{"id":"2302.11752","title":"EVJVQA Challenge: Multilingual Visual Question Answering","created":"2023-02-23","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":"2204.07302","title":"Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning","created":"2022-04-15","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":"2402.12846","title":"ConVQG: Contrastive Visual Question Generation with Multimodal Guidance","created":"2024-02-20","cited_by_count":4,"area":null},{"id":"2406.02601","title":"Multimodal Deep Learning for Low-Resource Settings: A Vector Embedding Alignment Approach for Healthcare Applications","created":"2024-06-02","cited_by_count":4,"area":null},{"id":"2503.01261","title":"Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2307.14142","title":"LOIS: Looking Out of Instance Semantics for Visual Question Answering","created":"2023-07-26","cited_by_count":3,"area":null},{"id":"2310.15597","title":"Emergent Communication in Interactive Sketch Question Answering","created":"2023-10-24","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":"2104.10139","title":"Towards Solving Multimodal Comprehension","created":"2021-04-20","cited_by_count":2,"area":null},{"id":"2104.14383","title":"Privacy-Preserving Federated Learning on Partitioned Attributes","created":"2021-04-29","cited_by_count":2,"area":null},{"id":"2201.10656","title":"MGA-VQA: Multi-Granularity Alignment for Visual Question Answering","created":"2022-01-25","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":"2210.17417","title":"Fashion-Specific Attributes Interpretation via Dual Gaussian Visual-Semantic Embedding","created":"2022-10-28","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":"2304.06277","title":"Optimizing Multi-Domain Performance with Active Learning-based Improvement Strategies","created":"2023-04-13","cited_by_count":1,"area":null},{"id":"2305.09107","title":"Is a Video worth $n\\times n$ Images? A Highly Efficient Approach to Transformer-based Video Question Answering","created":"2023-05-16","cited_by_count":1,"area":null},{"id":"2306.00409","title":"Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2308.09455","title":"Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2309.09179","title":"Syntax Tree Constrained Graph Network for Visual Question Answering","created":"2023-09-17","cited_by_count":1,"area":null},{"id":"2310.08187","title":"Visual Question Generation in Bengali","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2402.03607","title":"Enhancing Cross-Modal Contextual Congruence for Crowdfunding Success using Knowledge-infused Learning","created":"2024-02-06","cited_by_count":1,"area":null},{"id":"2407.05100","title":"Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference","created":"2024-07-06","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":"2502.06355","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2502.18725","title":"Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2502.19202","title":"LiGT: Layout-infused Generative Transformer for Visual Question Answering on Vietnamese Receipts","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2203.03727","title":"Barlow constrained optimization for Visual Question Answering","created":"2022-03-07","cited_by_count":0,"area":null},{"id":"2206.14355","title":"EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering","created":"2022-06-29","cited_by_count":0,"area":null},{"id":"2208.05798","title":"Aesthetic Visual Question Answering of Photographs","created":"2022-08-10","cited_by_count":0,"area":null},{"id":"2211.06688","title":"Partial Visual-Semantic Embedding: Fashion Intelligence System with Sensitive Part-by-Part Learning","created":"2022-11-12","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":"2303.02601","title":"Knowledge-Based Counterfactual Queries for Visual Question Answering","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2304.11993","title":"MMC: Multi-Modal Colorization of Images using Textual Descriptions","created":"2023-04-24","cited_by_count":0,"area":null},{"id":"2305.08059","title":"Semantic-aware Dynamic Retrospective-Prospective Reasoning for Event-level Video Question Answering","created":"2023-05-14","cited_by_count":0,"area":null},{"id":"2306.06622","title":"Weakly Supervised Visual Question Answer Generation","created":"2023-06-11","cited_by_count":0,"area":null},{"id":"2309.00133","title":"Distraction-free Embeddings for Robust VQA","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2407.00252","title":"Assistive Image Annotation Systems with Deep Learning and Natural Language Capabilities: A Review","created":"2024-06-28","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.03871","title":"Visual Instruction Tuning Aligns Modalities through Abstraction","created":"2026-06-02","cited_by_count":0,"area":null}],"next_cursor":null}