{"total":61,"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":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2306.04387","title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","created":"2023-06-07","cited_by_count":126,"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":"2103.00823","title":"M6: A Chinese Multimodal Pretrainer","created":"2021-03-01","cited_by_count":91,"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":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72,"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":"2112.15283","title":"ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation","created":"2021-12-31","cited_by_count":41,"area":null},{"id":"2110.08515","title":"Multimodal Dialogue Response Generation","created":"2021-10-16","cited_by_count":32,"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":"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":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"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":"2110.00711","title":"Asking questions on handwritten document collections","created":"2021-10-02","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":"2109.08475","title":"GoG: Relation-aware Graph-over-Graph Network for Visual Dialog","created":"2021-09-17","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":"2105.00421","title":"A survey on VQA_Datasets and Approaches","created":"2021-05-02","cited_by_count":11,"area":null},{"id":"2109.08478","title":"Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation","created":"2021-09-17","cited_by_count":11,"area":null},{"id":"2109.06013","title":"Learning to Ground Visual Objects for Visual Dialog","created":"2021-09-13","cited_by_count":10,"area":null},{"id":"2207.02185","title":"CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representations","created":"2022-07-05","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":"2503.14421","title":"ExDDV: A New Dataset for Explainable Deepfake Detection in Video","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2109.05281","title":"COSMic: A Coherence-Aware Generation Metric for Image Descriptions","created":"2021-09-11","cited_by_count":9,"area":null},{"id":"2206.01017","title":"Structured Two-stream Attention Network for Video Question Answering","created":"2022-06-02","cited_by_count":9,"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":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2108.00061","title":"MTVR: Multilingual Moment Retrieval in Videos","created":"2021-07-30","cited_by_count":8,"area":null},{"id":"2202.07630","title":"Delving Deeper into Cross-lingual Visual Question Answering","created":"2022-02-15","cited_by_count":8,"area":null},{"id":"2206.01923","title":"From Pixels to Objects: Cubic Visual Attention for Visual Question Answering","created":"2022-06-04","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":"2404.10652","title":"ViTextVQA: A Large-Scale Visual Question Answering Dataset and a Novel Multimodal Feature Fusion Method for Vietnamese Text Comprehension in Images","created":"2024-04-16","cited_by_count":7,"area":null},{"id":"2302.11752","title":"EVJVQA Challenge: Multilingual Visual Question Answering","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2308.08628","title":"Learning the meanings of function words from grounded language using a visual question answering model","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2101.09915","title":"Weakly Supervised Thoracic Disease Localization via Disease Masks","created":"2021-01-25","cited_by_count":5,"area":null},{"id":"2211.08736","title":"AlignVE: Visual Entailment Recognition Based on Alignment Relations","created":"2022-11-16","cited_by_count":5,"area":null},{"id":"2411.15770","title":"Text-Guided Coarse-to-Fine Fusion Network for Robust Remote Sensing Visual Question Answering","created":"2024-11-24","cited_by_count":5,"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":"2208.03030","title":"ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding","created":"2022-08-05","cited_by_count":3,"area":null},{"id":"2510.01247","title":"Let's Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models' Understanding of Sports","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2104.10139","title":"Towards Solving Multimodal Comprehension","created":"2021-04-20","cited_by_count":2,"area":null},{"id":"2106.08914","title":"$C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2305.03971","title":"Adaptive loose optimization for robust question answering","created":"2023-05-06","cited_by_count":2,"area":null},{"id":"2409.01690","title":"Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2105.05999","title":"Designing Multimodal Datasets for NLP Challenges","created":"2021-05-12","cited_by_count":1,"area":null},{"id":"2210.16960","title":"Multilingual Multimodality: A Taxonomical Survey of Datasets, Techniques, Challenges and Opportunities","created":"2022-10-30","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},{"id":"2310.08187","title":"Visual Question Generation in Bengali","created":"2023-10-12","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":"2101.11266","title":"TorchPRISM: Principal Image Sections Mapping, a novel method for Convolutional Neural Network features visualization","created":"2021-01-27","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":"2208.05798","title":"Aesthetic Visual Question Answering of Photographs","created":"2022-08-10","cited_by_count":0,"area":null},{"id":"2301.07227","title":"Curriculum Script Distillation for Multilingual Visual Question Answering","created":"2023-01-17","cited_by_count":0,"area":null},{"id":"2303.12671","title":"Integrating Image Features with Convolutional Sequence-to-sequence Network for Multilingual Visual Question Answering","created":"2023-03-22","cited_by_count":0,"area":null},{"id":"2502.09285","title":"EmoAssist: Emotional Assistant for Visual Impairment Community","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2506.09953","title":"Outside Knowledge Conversational Video (OKCV) Dataset -- Dialoguing over Videos","created":"2025-06-11","cited_by_count":0,"area":null}],"next_cursor":null}