{"total":235,"rows":[{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"area":null},{"id":"2302.11713","title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?","created":"2023-02-23","cited_by_count":207,"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":"2106.09141","title":"Probing Image-Language Transformers for Verb Understanding","created":"2021-06-16","cited_by_count":109,"area":null},{"id":"2212.10015","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96,"area":null},{"id":"2202.05306","title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","created":"2022-02-10","cited_by_count":95,"area":null},{"id":"2212.04092","title":"Successive Prompting for Decomposing Complex Questions","created":"2022-12-08","cited_by_count":94,"area":null},{"id":"2111.10056","title":"Medical Visual Question Answering: A Survey","created":"2021-11-19","cited_by_count":93,"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":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2103.06922","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","created":"2021-03-11","cited_by_count":78,"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":"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":"2305.17256","title":"Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning","created":"2023-05-26","cited_by_count":69,"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":"2603.21687","title":"MIRAGE: The Illusion of Visual Understanding","created":"2026-03-23","cited_by_count":65,"area":null},{"id":"2106.12674","title":"Fairness via Representation Neutralization","created":"2021-06-23","cited_by_count":63,"area":null},{"id":"2206.01201","title":"REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering","created":"2022-06-02","cited_by_count":59,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2305.01233","title":"On Uni-Modal Feature Learning in Supervised Multi-Modal Learning","created":"2023-05-02","cited_by_count":53,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"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":"2404.16820","title":"Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings","created":"2024-04-25","cited_by_count":44,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"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":"2304.14133","title":"VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Bias","created":"2023-04-27","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":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"area":null},{"id":"2110.14375","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","created":"2021-10-27","cited_by_count":35,"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":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32,"area":null},{"id":"2106.13948","title":"Core Challenges in Embodied Vision-Language Planning","created":"2021-06-26","cited_by_count":30,"area":null},{"id":"2209.15605","title":"Bias Mimicking: A Simple Sampling Approach for Bias Mitigation","created":"2022-09-30","cited_by_count":30,"area":null},{"id":"2210.04692","title":"Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA","created":"2022-10-10","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":"2310.06238","title":"Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering","created":"2023-10-10","cited_by_count":29,"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":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"area":null},{"id":"2109.10613","title":"COVR: A test-bed for Visually Grounded Compositional Generalization with real images","created":"2021-09-22","cited_by_count":25,"area":null},{"id":"2111.01026","title":"Introspective Distillation for Robust Question Answering","created":"2021-11-01","cited_by_count":25,"area":null},{"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":"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":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24,"area":null},{"id":"2109.02071","title":"End-to-End Self-Debiasing Framework for Robust NLU Training","created":"2021-09-05","cited_by_count":24,"area":null},{"id":"2204.10496","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","created":"2022-04-22","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":"2401.13478","title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval","created":"2024-01-24","cited_by_count":23,"area":null},{"id":"2103.11263","title":"Self-Supervised Test-Time Learning for Reading Comprehension","created":"2021-03-20","cited_by_count":22,"area":null},{"id":"2110.01013","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","created":"2021-10-03","cited_by_count":22,"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":"2101.05479","title":"Understanding the Role of Scene Graphs in Visual Question Answering","created":"2021-01-14","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":"2202.12690","title":"On Modality Bias Recognition and Reduction","created":"2022-02-25","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":"2104.00926","title":"VisQA: X-raying Vision and Language Reasoning in Transformers","created":"2021-04-02","cited_by_count":19,"area":null},{"id":"2202.07280","title":"Saving Dense Retriever from Shortcut Dependency in Conversational Search","created":"2022-02-15","cited_by_count":19,"area":null},{"id":"2207.13316","title":"NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation","created":"2022-07-27","cited_by_count":19,"area":null},{"id":"2312.00935","title":"Understanding Unimodal Bias in Multimodal Deep Linear Networks","created":"2023-12-01","cited_by_count":19,"area":null},{"id":"2105.01993","title":"AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss","created":"2021-05-05","cited_by_count":18,"area":null},{"id":"2106.04605","title":"Check It Again: Progressive Visual Question Answering via Visual Entailment","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2205.05739","title":"Learning to Retrieve Videos by Asking Questions","created":"2022-05-11","cited_by_count":18,"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":"2404.12020","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","created":"2024-04-18","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":"2104.03656","title":"How Transferable are Reasoning Patterns in VQA?","created":"2021-04-08","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":"2209.08529","title":"Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances","created":"2022-09-18","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":"2106.08170","title":"How Modular Should Neural Module Networks Be for Systematic Generalization?","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2203.06907","title":"Hierarchical Memory Learning for Fine-Grained Scene Graph Generation","created":"2022-03-14","cited_by_count":15,"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":"2110.00519","title":"Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images","created":"2021-10-01","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":"2302.06975","title":"A Review of the Role of Causality in Developing Trustworthy AI Systems","created":"2023-02-14","cited_by_count":14,"area":null},{"id":"2408.02464","title":"Fairness and Bias Mitigation in Computer Vision: A Survey","created":"2024-08-05","cited_by_count":13,"area":null},{"id":"2104.04182","title":"FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework","created":"2021-04-09","cited_by_count":12,"area":null},{"id":"2109.01934","title":"Weakly Supervised Relative Spatial Reasoning for Visual Question Answering","created":"2021-09-04","cited_by_count":12,"area":null},{"id":"2208.00690","title":"Generative Bias for Robust Visual Question Answering","created":"2022-08-01","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":"2308.04553","title":"From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition","created":"2023-08-08","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":"2412.13989","title":"What makes a good metric? Evaluating automatic metrics for text-to-image consistency","created":"2024-12-18","cited_by_count":12,"area":null},{"id":"2509.24709","title":"IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2103.02937","title":"Visual Question Answering: which investigated applications?","created":"2021-03-04","cited_by_count":11,"area":null},{"id":"2105.00421","title":"A survey on VQA_Datasets and Approaches","created":"2021-05-02","cited_by_count":11,"area":null},{"id":"2111.04321","title":"Towards Debiasing Temporal Sentence Grounding in Video","created":"2021-11-08","cited_by_count":11,"area":null},{"id":"2201.03639","title":"Multi-Query Video Retrieval","created":"2022-01-10","cited_by_count":11,"area":null},{"id":"2203.05243","title":"A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach","created":"2022-03-10","cited_by_count":11,"area":null},{"id":"2203.07613","title":"CARETS: A Consistency And Robustness Evaluative Test Suite for VQA","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2204.02426","title":"OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2305.07021","title":"Simple Token-Level Confidence Improves Caption Correctness","created":"2023-05-11","cited_by_count":11,"area":null},{"id":"2407.16638","title":"Unveiling and Mitigating Bias in Audio Visual Segmentation","created":"2024-07-23","cited_by_count":11,"area":null},{"id":"2502.15895","title":"Directional Gradient Projection for Robust Fine-Tuning of Foundation Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2101.06980","title":"Mitigating the Position Bias of Transformer Models in Passage Re-Ranking","created":"2021-01-18","cited_by_count":10,"area":null},{"id":"2107.11576","title":"X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering","created":"2021-07-24","cited_by_count":10,"area":null},{"id":"2409.17455","title":"Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models","created":"2024-09-26","cited_by_count":10,"area":null}],"next_cursor":"100"}