{"total":111,"rows":[{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619,"area":null},{"id":"2111.10056","title":"Medical Visual Question Answering: A Survey","created":"2021-11-19","cited_by_count":93,"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":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"area":null},{"id":"2202.01993","title":"Grounding Answers for Visual Questions Asked by Visually Impaired People","created":"2022-02-04","cited_by_count":47,"area":null},{"id":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43,"area":"mllm"},{"id":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"area":null},{"id":"2107.12651","title":"Greedy Gradient Ensemble for Robust Visual Question Answering","created":"2021-07-27","cited_by_count":34,"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":"2401.09454","title":"Voila-A: Aligning Vision-Language Models with User's Gaze Attention","created":"2023-12-22","cited_by_count":28,"area":"mllm"},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2202.02838","title":"Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment","created":"2022-02-06","cited_by_count":27,"area":null},{"id":"2303.00885","title":"Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision","created":"2023-03-02","cited_by_count":27,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2306.05731","title":"Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions","created":"2023-06-09","cited_by_count":25,"area":null},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","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":"2206.13413","title":"RES: A Robust Framework for Guiding Visual Explanation","created":"2022-06-27","cited_by_count":22,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2111.01628","title":"Human Attention in Fine-grained Classification","created":"2021-11-02","cited_by_count":21,"area":null},{"id":"2305.11033","title":"Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature","created":"2023-05-18","cited_by_count":21,"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":"2205.10226","title":"Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?","created":"2022-04-25","cited_by_count":20,"area":null},{"id":"2303.13043","title":"Top-Down Visual Attention from Analysis by Synthesis","created":"2023-03-23","cited_by_count":19,"area":null},{"id":"2207.11850","title":"Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problem","created":"2022-07-24","cited_by_count":18,"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":"2405.09931","title":"Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition","created":"2024-05-16","cited_by_count":17,"area":null},{"id":"2104.10283","title":"GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering","created":"2021-04-20","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":"2211.14736","title":"Attribution-based XAI Methods in Computer Vision: A Review","created":"2022-11-27","cited_by_count":16,"area":null},{"id":"2503.13891","title":"Where do Large Vision-Language Models Look at when Answering Questions?","created":"2025-03-18","cited_by_count":15,"area":"mllm"},{"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":"2109.06122","title":"Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering","created":"2021-09-13","cited_by_count":14,"area":null},{"id":"2308.11662","title":"VQA Therapy: Exploring Answer Differences by Visually Grounding Answers","created":"2023-08-21","cited_by_count":14,"area":null},{"id":"2105.05964","title":"Connecting What to Say With Where to Look by Modeling Human Attention Traces","created":"2021-05-12","cited_by_count":13,"area":null},{"id":"2201.05299","title":"A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering","created":"2022-01-14","cited_by_count":13,"area":null},{"id":"2206.11212","title":"VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives","created":"2022-06-22","cited_by_count":12,"area":"lr"},{"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":"2403.10940","title":"ViSaRL: Visual Reinforcement Learning Guided by Human Saliency","created":"2024-03-16","cited_by_count":12,"area":"deeprl"},{"id":"2103.02937","title":"Visual Question Answering: which investigated applications?","created":"2021-03-04","cited_by_count":11,"area":null},{"id":"2202.12626","title":"Joint Answering and Explanation for Visual Commonsense Reasoning","created":"2022-02-25","cited_by_count":11,"area":"lr"},{"id":"2101.10710","title":"Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) method","created":"2021-01-26","cited_by_count":10,"area":null},{"id":"2107.07013","title":"Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity","created":"2021-07-14","cited_by_count":10,"area":null},{"id":"2210.10914","title":"Prophet Attention: Predicting Attention with Future Attention for Image Captioning","created":"2022-10-19","cited_by_count":10,"area":null},{"id":"2102.01916","title":"Answer Questions with Right Image Regions: A Visual Attention Regularization Approach","created":"2021-02-03","cited_by_count":9,"area":null},{"id":"2401.07803","title":"Uncovering the Full Potential of Visual Grounding Methods in VQA","created":"2024-01-15","cited_by_count":9,"area":null},{"id":"2402.18673","title":"Trends, Applications, and Challenges in Human Attention Modelling","created":"2024-02-28","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2207.02334","title":"Weakly Supervised Grounding for VQA in Vision-Language Transformers","created":"2022-07-05","cited_by_count":8,"area":null},{"id":"2305.15015","title":"Measuring Faithful and Plausible Visual Grounding in VQA","created":"2023-05-24","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":"2204.09093","title":"Behind the Machine's Gaze: Neural Networks with Biologically-inspired Constraints Exhibit Human-like Visual Attention","created":"2022-04-19","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":"2403.17545","title":"A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions","created":"2024-03-26","cited_by_count":7,"area":null},{"id":"2104.03046","title":"Multimodal Continuous Visual Attention Mechanisms","created":"2021-04-07","cited_by_count":6,"area":null},{"id":"2310.08537","title":"Saliency-Bench: A Comprehensive Benchmark for Evaluating Visual Explanations","created":"2023-10-12","cited_by_count":6,"area":null},{"id":"2106.14069","title":"Saying the Unseen: Video Descriptions via Dialog Agents","created":"2021-06-26","cited_by_count":5,"area":null},{"id":"2110.06863","title":"Improving Users' Mental Model with Attention-directed Counterfactual Edits","created":"2021-10-13","cited_by_count":5,"area":null},{"id":"2310.18343","title":"PHD: Pixel-Based Language Modeling of Historical Documents","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2406.18253","title":"On the Role of Visual Grounding in VQA","created":"2024-06-26","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":"2307.13345","title":"Do humans and Convolutional Neural Networks attend to similar areas during scene classification: Effects of task and image type","created":"2023-07-25","cited_by_count":4,"area":null},{"id":"2605.30912","title":"Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR","created":"2026-05-29","cited_by_count":4,"area":"mllm"},{"id":"2107.05799","title":"Human Attention during Goal-directed Reading Comprehension Relies on Task Optimization","created":"2021-07-13","cited_by_count":3,"area":null},{"id":"2403.06904","title":"Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2410.10184","title":"Eliminating the Language Bias for Visual Question Answering with fine-grained Causal Intervention","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2101.10942","title":"Absolute Value Constraint: The Reason for Invalid Performance Evaluation Results of Neural Network Models for Stock Price Prediction","created":"2021-01-10","cited_by_count":2,"area":null},{"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":"2104.14102","title":"Comparing Visual Reasoning in Humans and AI","created":"2021-04-29","cited_by_count":2,"area":null},{"id":"2108.02915","title":"LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching","created":"2021-08-06","cited_by_count":2,"area":null},{"id":"2110.05159","title":"Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2111.03195","title":"Addressing Multiple Salient Object Detection via Dual-Space Long-Range Dependencies","created":"2021-11-04","cited_by_count":2,"area":null},{"id":"2203.10690","title":"CNN Attention Guidance for Improved Orthopedics Radiographic Fracture Classification","created":"2022-03-21","cited_by_count":2,"area":null},{"id":"2207.00782","title":"Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review","created":"2022-07-02","cited_by_count":2,"area":null},{"id":"2302.02117","title":"Learning to Agree on Vision Attention for Visual Commonsense Reasoning","created":"2023-02-04","cited_by_count":2,"area":"lr"},{"id":"2305.14882","title":"Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering","created":"2023-05-24","cited_by_count":2,"area":"mllm"},{"id":"2309.02691","title":"A Joint Study of Phrase Grounding and Task Performance in Vision and Language Models","created":"2023-09-06","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":"2606.16122","title":"Thinking with Visual Grounding","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2606.17410","title":"Attention Alignment Between Humans and Vision-Language Models","created":"2026-06-16","cited_by_count":2,"area":"mllm"},{"id":"2201.03965","title":"On the Efficacy of Co-Attention Transformer Layers in Visual Question Answering","created":"2022-01-11","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":"2204.09774","title":"Attention in Reasoning: Dataset, Analysis, and Modeling","created":"2022-04-20","cited_by_count":1,"area":"lr"},{"id":"2207.02574","title":"Is the U-Net Directional-Relationship Aware?","created":"2022-07-06","cited_by_count":1,"area":null},{"id":"2211.12100","title":"Simulating Human Gaze with Neural Visual Attention","created":"2022-11-22","cited_by_count":1,"area":null},{"id":"2302.10764","title":"On The Coherence of Quantitative Evaluation of Visual Explanations","created":"2023-02-14","cited_by_count":1,"area":null},{"id":"2305.19664","title":"Unveiling Cross Modality Bias in Visual Question Answering: A Causal View with Possible Worlds VQA","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2402.01352","title":"Describing Images $\\textit{Fast and Slow}$: Quantifying and Predicting the Variation in Human Signals during Visuo-Linguistic Processes","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2406.00955","title":"How Video Meetings Change Your Expression","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2410.04609","title":"VISTA: A Visual and Textual Attention Dataset for Interpreting Multimodal Models","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2507.15655","title":"HW-MLVQA: Elucidating Multilingual Handwritten Document Understanding with a Comprehensive VQA Benchmark","created":"2025-07-21","cited_by_count":1,"area":"mllm"},{"id":"2605.00905","title":"DIAGRAMS: A Review Framework for Reasoning-Level Attribution in Diagram QA","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2108.12585","title":"On the Significance of Question Encoder Sequence Model in the Out-of-Distribution Performance in Visual Question Answering","created":"2021-08-28","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":"2305.02375","title":"MaskSearch: Querying Image Masks at Scale","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2402.19133","title":"Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations","created":"2024-02-29","cited_by_count":0,"area":null},{"id":"2404.06563","title":"Demonstration of MaskSearch: Efficiently Querying Image Masks for Machine Learning Workflows","created":"2024-04-09","cited_by_count":0,"area":null},{"id":"2405.13032","title":"Faithful Attention Explainer: Verbalizing Decisions Based on Discriminative Features","created":"2024-05-16","cited_by_count":0,"area":null},{"id":"2506.07168","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","created":"2025-06-08","cited_by_count":0,"area":null}],"next_cursor":"100"}