{"total":113,"rows":[{"id":"2109.05014","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","created":"2021-09-10","cited_by_count":301,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102,"area":null},{"id":"2103.12248","title":"Multi-Modal Answer Validation for Knowledge-Based VQA","created":"2021-03-23","cited_by_count":79,"area":null},{"id":"2202.02703","title":"Multi-modal Sensor Fusion for Auto Driving Perception: A Survey","created":"2022-02-06","cited_by_count":76,"area":null},{"id":"2104.03149","title":"Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering","created":"2021-04-07","cited_by_count":71,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2304.09974","title":"SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery","created":"2023-04-19","cited_by_count":48,"area":null},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2406.01210","title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","created":"2024-06-03","cited_by_count":44,"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":"2203.09138","title":"MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering","created":"2022-03-17","cited_by_count":36,"area":null},{"id":"2411.01409","title":"Classifier-guided Gradient Modulation for Enhanced Multimodal Learning","created":"2024-11-03","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":"2103.06132","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","created":"2021-03-10","cited_by_count":32,"area":null},{"id":"2302.09019","title":"Tensor Networks Meet Neural Networks: A Survey and Future Perspectives","created":"2023-01-22","cited_by_count":32,"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":"2106.04067","title":"LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation","created":"2021-06-08","cited_by_count":28,"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":"2104.03015","title":"RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network","created":"2021-04-07","cited_by_count":27,"area":null},{"id":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"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":"2308.14363","title":"Mobile Foundation Model as Firmware","created":"2023-08-28","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":"2101.06013","title":"Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge","created":"2021-01-15","cited_by_count":24,"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":"2402.02045","title":"MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning","created":"2024-02-03","cited_by_count":23,"area":null},{"id":"2405.13949","title":"PitVQA: Image-grounded Text Embedding LLM for Visual Question Answering in Pituitary Surgery","created":"2024-05-22","cited_by_count":23,"area":null},{"id":"2205.11501","title":"VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering","created":"2022-05-23","cited_by_count":22,"area":null},{"id":"2403.18383","title":"Generative Multi-modal Models are Good Class-Incremental Learners","created":"2024-03-27","cited_by_count":22,"area":null},{"id":"2204.07780","title":"Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks","created":"2022-04-16","cited_by_count":21,"area":null},{"id":"2301.09460","title":"HRVQA: A Visual Question Answering Benchmark for High-Resolution Aerial Images","created":"2023-01-23","cited_by_count":21,"area":null},{"id":"2405.14974","title":"LOVA3: Learning to Visual Question Answering, Asking and Assessment","created":"2024-05-23","cited_by_count":21,"area":null},{"id":"2202.12076","title":"Phrase-Based Affordance Detection via Cyclic Bilateral Interaction","created":"2022-02-24","cited_by_count":19,"area":null},{"id":"2204.00486","title":"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval","created":"2022-04-01","cited_by_count":19,"area":null},{"id":"2404.08589","title":"Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts","created":"2024-04-12","cited_by_count":18,"area":null},{"id":"2112.11691","title":"Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation","created":"2021-12-22","cited_by_count":17,"area":null},{"id":"2307.05182","title":"CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","created":"2023-07-11","cited_by_count":17,"area":null},{"id":"2408.04958","title":"Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery","created":"2024-08-09","cited_by_count":17,"area":null},{"id":"2104.03656","title":"How Transferable are Reasoning Patterns in VQA?","created":"2021-04-08","cited_by_count":16,"area":null},{"id":"2305.18842","title":"Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2402.12728","title":"Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering","created":"2024-02-20","cited_by_count":16,"area":null},{"id":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14,"area":null},{"id":"2105.02626","title":"A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations","created":"2021-04-29","cited_by_count":14,"area":null},{"id":"2107.01671","title":"Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory","created":"2021-07-04","cited_by_count":14,"area":null},{"id":"2108.02924","title":"Interpretable Visual Understanding with Cognitive Attention Network","created":"2021-08-06","cited_by_count":12,"area":null},{"id":"2203.14463","title":"Large-scale Bilingual Language-Image Contrastive Learning","created":"2022-03-28","cited_by_count":12,"area":null},{"id":"2205.04713","title":"Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures","created":"2022-05-10","cited_by_count":12,"area":null},{"id":"2208.05647","title":"PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding","created":"2022-08-11","cited_by_count":12,"area":null},{"id":"2308.10402","title":"Simple Baselines for Interactive Video Retrieval with Questions and Answers","created":"2023-08-21","cited_by_count":12,"area":null},{"id":"2407.03386","title":"Visual Robustness Benchmark for Visual Question Answering (VQA)","created":"2024-07-03","cited_by_count":12,"area":null},{"id":"2110.11298","title":"Video and Text Matching with Conditioned Embeddings","created":"2021-10-21","cited_by_count":10,"area":null},{"id":"2407.08130","title":"Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning","created":"2024-07-11","cited_by_count":10,"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":"2305.06407","title":"Combo of Thinking and Observing for Outside-Knowledge VQA","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2412.16936","title":"Rationale-guided Prompting for Knowledge-based Visual Question Answering","created":"2024-12-22","cited_by_count":9,"area":null},{"id":"2504.13112","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","created":"2025-04-17","cited_by_count":9,"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":"2302.10473","title":"Oriented object detection in optical remote sensing images using deep learning: a survey","created":"2023-02-21","cited_by_count":8,"area":null},{"id":"2406.09016","title":"Cross-Modal Learning for Anomaly Detection in Complex Industrial Process: Methodology and Benchmark","created":"2024-06-13","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":"2411.11150","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2106.05597","title":"Supervising the Transfer of Reasoning Patterns in VQA","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2203.02985","title":"Dynamic Key-value Memory Enhanced Multi-step Graph Reasoning for Knowledge-based Visual Question Answering","created":"2022-03-06","cited_by_count":7,"area":null},{"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":"2108.02180","title":"Ordered Attention for Coherent Visual Storytelling","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2109.11848","title":"How to find a good image-text embedding for remote sensing visual question answering?","created":"2021-09-24","cited_by_count":6,"area":null},{"id":"2208.11253","title":"FashionVQA: A Domain-Specific Visual Question Answering System","created":"2022-08-24","cited_by_count":6,"area":null},{"id":"2207.10404","title":"Semantic-aware Modular Capsule Routing for Visual Question Answering","created":"2022-07-21","cited_by_count":5,"area":null},{"id":"2307.01067","title":"Localized Questions in Medical Visual Question Answering","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2107.03216","title":"MuVAM: A Multi-View Attention-based Model for Medical Visual Question Answering","created":"2021-07-07","cited_by_count":4,"area":null},{"id":"2110.04828","title":"FLAME: Facial Landmark Heatmap Activated Multimodal Gaze Estimation","created":"2021-10-10","cited_by_count":4,"area":null},{"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":"2201.03342","title":"COIN: Counterfactual Image Generation for VQA Interpretation","created":"2022-01-10","cited_by_count":4,"area":null},{"id":"2302.05894","title":"Neural Architecture Search with Multimodal Fusion Methods for Diagnosing Dementia","created":"2023-02-12","cited_by_count":4,"area":null},{"id":"2306.16645","title":"Deep Equilibrium Multimodal Fusion","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2311.16782","title":"The curse of language biases in remote sensing VQA: the role of spatial attributes, language diversity, and the need for clear evaluation","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2410.15266","title":"GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning","created":"2024-10-20","cited_by_count":4,"area":null},{"id":"2105.06160","title":"Relation-aware Hierarchical Attention Framework for Video Question Answering","created":"2021-05-13","cited_by_count":3,"area":null},{"id":"2510.20877","title":"Multimodal Negative Learning","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2101.08978","title":"Visual Question Answering based on Local-Scene-Aware Referring Expression Generation","created":"2021-01-22","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":"2202.04306","title":"Can Open Domain Question Answering Systems Answer Visual Knowledge Questions?","created":"2022-02-09","cited_by_count":2,"area":null},{"id":"2207.13242","title":"Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base","created":"2022-07-27","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":"2310.01842","title":"SelfGraphVQA: A Self-Supervised Graph Neural Network for Scene-based Question Answering","created":"2023-10-03","cited_by_count":2,"area":null},{"id":"2402.03896","title":"Multimodal Rationales for Explainable Visual Question Answering","created":"2024-02-06","cited_by_count":2,"area":null},{"id":"2410.09776","title":"ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videos","created":"2024-10-13","cited_by_count":2,"area":null},{"id":"2107.11509","title":"Cycled Compositional Learning between Images and Text","created":"2021-07-24","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":"2202.06858","title":"An experimental study of the vision-bottleneck in VQA","created":"2022-02-14","cited_by_count":1,"area":null},{"id":"2204.00975","title":"Question-Driven Graph Fusion Network For Visual Question Answering","created":"2022-04-03","cited_by_count":1,"area":null},{"id":"2303.07545","title":"Implicit and Explicit Commonsense for Multi-sentence Video Captioning","created":"2023-03-14","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":"2408.07989","title":"IIU: Independent Inference Units for Knowledge-based Visual Question Answering","created":"2024-08-15","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":"2508.08974","title":"Text-conditioned State Space Model For Domain-generalized Change Detection Visual Question Answering","created":"2025-08-12","cited_by_count":1,"area":null}],"next_cursor":"100"}