{"total":116,"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":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"id":"2102.09542","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","created":"2021-02-18","cited_by_count":449,"area":null},{"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":"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":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2112.08614","title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language","created":"2021-12-16","cited_by_count":126,"area":null},{"id":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97,"area":null},{"id":"2111.10056","title":"Medical Visual Question Answering: A Survey","created":"2021-11-19","cited_by_count":93,"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":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"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":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2109.04014","title":"Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering","created":"2021-09-09","cited_by_count":50,"area":null},{"id":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2203.15125","title":"Text2Pos: Text-to-Point-Cloud Cross-Modal Localization","created":"2022-03-28","cited_by_count":40,"area":null},{"id":"2107.05348","title":"Zero-shot Visual Question Answering using Knowledge Graph","created":"2021-07-12","cited_by_count":37,"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":"2309.01093","title":"CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection","created":"2023-09-03","cited_by_count":36,"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":"2105.11087","title":"Recent Advances and Trends in Multimodal Deep Learning: A Review","created":"2021-05-24","cited_by_count":26,"area":null},{"id":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2109.08029","title":"Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answering","created":"2021-09-15","cited_by_count":25,"area":null},{"id":"2110.02526","title":"Coarse-to-Fine Reasoning for Visual Question Answering","created":"2021-10-06","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":"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":"2112.10006","title":"Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey","created":"2021-12-18","cited_by_count":23,"area":null},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2306.00424","title":"End-to-end Knowledge Retrieval with Multi-modal Queries","created":"2023-06-01","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":"2311.07536","title":"A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering","created":"2023-11-13","cited_by_count":23,"area":null},{"id":"2106.04053","title":"Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding","created":"2021-06-08","cited_by_count":21,"area":null},{"id":"2303.01903","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","created":"2023-03-03","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":"2605.05185","title":"OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents","created":"2026-05-06","cited_by_count":21,"area":null},{"id":"2104.08108","title":"Cross-Modal Retrieval Augmentation for Multi-Modal Classification","created":"2021-04-16","cited_by_count":20,"area":null},{"id":"2210.13626","title":"VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge","created":"2022-10-24","cited_by_count":20,"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":"2206.14989","title":"A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA","created":"2022-06-30","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":"2207.12888","title":"LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection","created":"2022-07-26","cited_by_count":18,"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":"2107.01671","title":"Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory","created":"2021-07-04","cited_by_count":14,"area":null},{"id":"2304.13649","title":"A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2310.13570","title":"A Simple Baseline for Knowledge-Based Visual Question Answering","created":"2023-10-20","cited_by_count":14,"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":"2410.10799","title":"Towards Foundation Models for 3D Vision: How Close Are We?","created":"2024-10-14","cited_by_count":13,"area":null},{"id":"2108.02924","title":"Interpretable Visual Understanding with Cognitive Attention Network","created":"2021-08-06","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":"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":"2105.00421","title":"A survey on VQA_Datasets and Approaches","created":"2021-05-02","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":"2308.08529","title":"Diagnosing Human-object Interaction Detectors","created":"2023-08-16","cited_by_count":11,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2503.18923","title":"Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models","created":"2025-03-24","cited_by_count":11,"area":null},{"id":"2303.03761","title":"Graph Neural Networks in Vision-Language Image Understanding: A Survey","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2306.16478","title":"Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering","created":"2023-06-28","cited_by_count":10,"area":null},{"id":"2203.07890","title":"K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition","created":"2022-03-15","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":"2402.02503","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","created":"2024-02-04","cited_by_count":9,"area":null},{"id":"2405.03373","title":"Knowledge-aware Text-Image Retrieval for Remote Sensing Images","created":"2024-05-06","cited_by_count":9,"area":null},{"id":"2112.06888","title":"Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection","created":"2021-12-13","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":"2411.11150","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2110.13395","title":"Transferring Domain-Agnostic Knowledge in Video Question Answering","created":"2021-10-26","cited_by_count":7,"area":null},{"id":"2111.12301","title":"Two-stage Rule-induction Visual Reasoning on RPMs with an Application to Video Prediction","created":"2021-11-24","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":"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":"2402.06287","title":"AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems","created":"2024-02-09","cited_by_count":7,"area":null},{"id":"2201.02010","title":"Self-Training Vision Language BERTs with a Unified Conditional Model","created":"2022-01-06","cited_by_count":6,"area":null},{"id":"2403.05770","title":"Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning","created":"2024-03-09","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":"2401.06443","title":"BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation Pretraining","created":"2024-01-12","cited_by_count":5,"area":null},{"id":"2202.04015","title":"NEWSKVQA: Knowledge-Aware News Video Question Answering","created":"2022-02-08","cited_by_count":4,"area":null},{"id":"2204.04680","title":"Reasoning with Multi-Structure Commonsense Knowledge in Visual Dialog","created":"2022-04-10","cited_by_count":4,"area":null},{"id":"2205.06435","title":"TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages","created":"2022-05-13","cited_by_count":4,"area":null},{"id":"2210.08554","title":"COFAR: Commonsense and Factual Reasoning in Image Search","created":"2022-10-16","cited_by_count":4,"area":null},{"id":"2303.10699","title":"FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering","created":"2023-03-19","cited_by_count":4,"area":null},{"id":"2402.02541","title":"Knowledge Generation for Zero-shot Knowledge-based VQA","created":"2024-02-04","cited_by_count":4,"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":"2106.06147","title":"NAAQA: A Neural Architecture for Acoustic Question Answering","created":"2021-06-11","cited_by_count":3,"area":null},{"id":"2110.00269","title":"A Survey of Knowledge Enhanced Pre-trained Models","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2204.01450","title":"Learning Commonsense-aware Moment-Text Alignment for Fast Video Temporal Grounding","created":"2022-04-04","cited_by_count":3,"area":null},{"id":"2210.05879","title":"Learning by Asking Questions for Knowledge-based Novel Object Recognition","created":"2022-10-12","cited_by_count":2,"area":null},{"id":"2211.05190","title":"Towards Reasoning-Aware Explainable VQA","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2303.02411","title":"The Contribution of Knowledge in Visiolinguistic Learning: A Survey on Tasks and Challenges","created":"2023-03-04","cited_by_count":2,"area":null},{"id":"2309.01955","title":"A Survey on Interpretable Cross-modal Reasoning","created":"2023-09-05","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":"2406.09994","title":"Precision Empowers, Excess Distracts: Visual Question Answering With Dynamically Infused Knowledge In Language Models","created":"2024-06-14","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":"2410.13662","title":"ActionCOMET: A Zero-shot Approach to Learn Image-specific Commonsense Concepts about Actions","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2511.22843","title":"Breaking the Visual Shortcuts in Multimodal Knowledge-Based Visual Question Answering","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2512.01827","title":"CauSight: Learning to Supersense for Visual Causal Discovery","created":"2025-12-01","cited_by_count":2,"area":null},{"id":"2109.04735","title":"Temporal Pyramid Transformer with Multimodal Interaction for Video Question Answering","created":"2021-09-10","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}],"next_cursor":"100"}