{"total":174,"rows":[{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719,"area":null},{"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":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708,"area":null},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412,"area":null},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321,"area":null},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302,"area":null},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267,"area":null},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267,"area":null},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213,"area":null},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180,"area":null},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144,"area":null},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135,"area":null},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135,"area":null},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120,"area":null},{"id":"2308.01907","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","created":"2023-08-03","cited_by_count":116,"area":null},{"id":"2302.11154","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","created":"2023-02-22","cited_by_count":113,"area":null},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109,"area":null},{"id":"2405.11985","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","created":"2024-05-20","cited_by_count":93,"area":null},{"id":"2402.19474","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","created":"2024-02-29","cited_by_count":90,"area":null},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85,"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":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68,"area":null},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64,"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":"2303.11568","title":"Large AI Models in Health Informatics: Applications, Challenges, and the Future","created":"2023-03-21","cited_by_count":61,"area":null},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","cited_by_count":55,"area":null},{"id":"2306.15681","title":"ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram","created":"2023-06-21","cited_by_count":54,"area":null},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"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":"2109.04014","title":"Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering","created":"2021-09-09","cited_by_count":50,"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":"2202.06511","title":"GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges","created":"2022-02-14","cited_by_count":46,"area":null},{"id":"2101.12059","title":"VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs","created":"2021-01-28","cited_by_count":42,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"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":"2306.07196","title":"Retrieval-Enhanced Contrastive Vision-Text Models","created":"2023-06-12","cited_by_count":36,"area":null},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2112.05136","title":"PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning","created":"2021-12-09","cited_by_count":34,"area":null},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"area":null},{"id":"2302.12248","title":"Learning Visual Representations via Language-Guided Sampling","created":"2023-02-23","cited_by_count":32,"area":null},{"id":"2103.09591","title":"Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA","created":"2021-03-17","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":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","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":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2109.10540","title":"Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing","created":"2021-09-22","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":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28,"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":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"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":"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":"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":"2402.01512","title":"Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation","created":"2024-02-02","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":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","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":"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":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2406.18048","title":"ScanFormer: Referring Expression Comprehension by Iteratively Scanning","created":"2024-06-26","cited_by_count":18,"area":null},{"id":"2307.11558","title":"Advancing Visual Grounding with Scene Knowledge: Benchmark and Method","created":"2023-07-21","cited_by_count":17,"area":null},{"id":"2511.03929","title":"NVIDIA Nemotron Nano V2 VL","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2205.06907","title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","created":"2022-05-13","cited_by_count":16,"area":null},{"id":"2211.14739","title":"MNER-QG: An End-to-End MRC framework for Multimodal Named Entity Recognition with Query Grounding","created":"2022-11-27","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":"2410.23828","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":"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":"2205.07548","title":"A Neuro-Symbolic ASP Pipeline for Visual Question Answering","created":"2022-05-16","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":"2402.17205","title":"Measuring Vision-Language STEM Skills of Neural Models","created":"2024-02-27","cited_by_count":14,"area":null},{"id":"2407.03200","title":"SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding","created":"2024-07-03","cited_by_count":14,"area":null},{"id":"2503.11519","title":"Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models","created":"2025-03-14","cited_by_count":14,"area":null},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14,"area":null},{"id":"2101.00151","title":"DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue","created":"2021-01-01","cited_by_count":13,"area":null},{"id":"2110.11852","title":"Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation","created":"2021-10-22","cited_by_count":13,"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":"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":"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":"2406.08398","title":"cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers","created":"2024-06-12","cited_by_count":11,"area":null},{"id":"2601.16093","title":"SAMTok: Representing Any Mask with Two Words","created":"2026-01-22","cited_by_count":11,"area":null},{"id":"2110.09599","title":"Label-Descriptive Patterns and Their Application to Characterizing Classification Errors","created":"2021-10-18","cited_by_count":10,"area":null},{"id":"2207.14227","title":"Visual Recognition by Request","created":"2022-07-28","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":"2309.16511","title":"Toloka Visual Question Answering Benchmark","created":"2023-09-28","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":"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":"2204.09957","title":"Self-paced Multi-grained Cross-modal Interaction Modeling for Referring Expression Comprehension","created":"2022-04-21","cited_by_count":8,"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}],"next_cursor":"100"}