{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2105.07624","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","created":"2021-05-17","cited_by_count":408},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220},{"id":"2210.03849","title":"ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering","created":"2022-10-07","cited_by_count":196},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"id":"1909.07083","title":"Controllable Text-to-Image Generation","created":"2019-09-16","cited_by_count":187},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"2401.16423","title":"Synchformer: Efficient Synchronization from Sparse Cues","created":"2024-01-29","cited_by_count":97},{"id":"2106.03153","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","created":"2021-06-06","cited_by_count":93},{"id":"2303.04947","title":"InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning","created":"2023-03-08","cited_by_count":90},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85},{"id":"2312.06720","title":"Audio-Visual LLM for Video Understanding","created":"2023-12-11","cited_by_count":77},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72},{"id":"2412.02611","title":"AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?","created":"2024-12-03","cited_by_count":47},{"id":"2203.06667","title":"Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video","created":"2022-03-13","cited_by_count":43},{"id":"2402.13236","title":"Towards audio language modeling -- an overview","created":"2024-02-20","cited_by_count":40},{"id":"1911.09655","title":"Temporal Reasoning via Audio Question Answering","created":"2019-11-21","cited_by_count":39},{"id":"2108.01266","title":"More but Correct: Generating Diversified and Entity-revised Medical Response","created":"2021-08-03","cited_by_count":31},{"id":"2311.05152","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks","created":"2023-11-09","cited_by_count":31},{"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},{"id":"2307.07063","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","created":"2023-07-13","cited_by_count":28},{"id":"2501.04606","title":"Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware Inversion","created":"2025-01-08","cited_by_count":28},{"id":"2502.06020","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","created":"2025-02-09","cited_by_count":28},{"id":"2310.19752","title":"Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP","created":"2023-10-30","cited_by_count":27},{"id":"2210.07055","title":"Sparse in Space and Time: Audio-visual Synchronisation with Trainable Selectors","created":"2022-10-13","cited_by_count":26},{"id":"2007.02375","title":"Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training","created":"2020-07-05","cited_by_count":22},{"id":"2404.15655","title":"Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering","created":"2024-04-24","cited_by_count":21},{"id":"2212.08104","title":"The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies","created":"2022-12-08","cited_by_count":20},{"id":"2502.06710","title":"Learning Musical Representations for Music Performance Question Answering","created":"2025-02-10","cited_by_count":17},{"id":"2310.03291","title":"Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction","created":"2023-10-05","cited_by_count":15},{"id":"2403.03385","title":"Multi-modal Deep Learning","created":"2024-03-06","cited_by_count":15},{"id":"2411.03978","title":"Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning","created":"2024-11-06","cited_by_count":12},{"id":"2309.08738","title":"AV-MaskEnhancer: Enhancing Video Representations through Audio-Visual Masked Autoencoder","created":"2023-09-15","cited_by_count":11},{"id":"2502.13363","title":"Pretrained Image-Text Models are Secretly Video Captioners","created":"2025-02-19","cited_by_count":11},{"id":"2106.07857","title":"Bilateral Personalized Dialogue Generation with Contrastive Learning","created":"2021-06-15","cited_by_count":8},{"id":"2401.04579","title":"A Deep Network for Explainable Prediction of Non-Imaging Phenotypes using Anatomical Multi-View Data","created":"2024-01-09","cited_by_count":6},{"id":"2408.13074","title":"Hierarchical Spatio-Temporal State-Space Modeling for fMRI Analysis","created":"2024-08-23","cited_by_count":6},{"id":"2207.05875","title":"A Novel DeBERTa-based Model for Financial Question Answering Task","created":"2022-07-12","cited_by_count":5},{"id":"2403.06679","title":"Answering Diverse Questions via Text Attached with Key Audio-Visual Clues","created":"2024-03-11","cited_by_count":5},{"id":"2505.20638","title":"Music Audio-Visual Question Answering Requires Specialized Multimodal Designs","created":"2025-05-27","cited_by_count":4},{"id":"2404.12605","title":"GluMarker: A Novel Predictive Modeling of Glycemic Control Through Digital Biomarkers","created":"2024-04-19","cited_by_count":2}],"next_cursor":null}