{"total":53,"rows":[{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361,"area":null},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263,"area":"mllm"},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149,"area":null},{"id":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116,"area":null},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"area":null},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63,"area":null},{"id":"2210.06031","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","created":"2022-10-12","cited_by_count":59,"area":null},{"id":"2207.07885","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","created":"2022-07-16","cited_by_count":41,"area":null},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37,"area":null},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2302.13668","title":"Contrastive Video Question Answering via Video Graph Transformer","created":"2023-02-27","cited_by_count":32,"area":null},{"id":"2205.05019","title":"Learning to Answer Visual Questions from Web Videos","created":"2022-05-10","cited_by_count":30,"area":null},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"area":null},{"id":"2306.11732","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","created":"2023-06-15","cited_by_count":27,"area":null},{"id":"2111.01300","title":"Masking Modalities for Cross-modal Video Retrieval","created":"2021-11-01","cited_by_count":23,"area":null},{"id":"2308.08414","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","created":"2023-08-16","cited_by_count":22,"area":null},{"id":"2403.17935","title":"OmniVid: A Generative Framework for Universal Video Understanding","created":"2024-03-26","cited_by_count":22,"area":null},{"id":"2210.02081","title":"Locate before Answering: Answer Guided Question Localization for Video Question Answering","created":"2022-10-05","cited_by_count":19,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2210.11929","title":"LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling","created":"2022-10-21","cited_by_count":16,"area":null},{"id":"2304.08682","title":"Learning Situation Hyper-Graphs for Video Question Answering","created":"2023-04-18","cited_by_count":16,"area":null},{"id":"2509.08621","title":"AdsQA: Towards Advertisement Video Understanding","created":"2025-09-10","cited_by_count":13,"area":null},{"id":"2312.04552","title":"Generating Illustrated Instructions","created":"2023-12-07","cited_by_count":7,"area":null},{"id":"2305.10049","title":"TG-VQA: Ternary Game of Video Question Answering","created":"2023-05-17","cited_by_count":6,"area":null},{"id":"2301.02307","title":"What You Say Is What You Show: Visual Narration Detection in Instructional Videos","created":"2023-01-05","cited_by_count":5,"area":null},{"id":"2302.09736","title":"STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training","created":"2023-02-20","cited_by_count":5,"area":null},{"id":"2303.03131","title":"Video Question Answering Using CLIP-Guided Visual-Text Attention","created":"2023-03-06","cited_by_count":5,"area":null},{"id":"2307.04192","title":"Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models","created":"2023-07-09","cited_by_count":5,"area":null},{"id":"2311.08151","title":"Rethink Cross-Modal Fusion in Weakly-Supervised Audio-Visual Video Parsing","created":"2023-11-14","cited_by_count":5,"area":null},{"id":"2403.06679","title":"Answering Diverse Questions via Text Attached with Key Audio-Visual Clues","created":"2024-03-11","cited_by_count":5,"area":null},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2111.14547","title":"LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering","created":"2021-11-29","cited_by_count":4,"area":null},{"id":"2302.02136","title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer","created":"2023-02-04","cited_by_count":4,"area":null},{"id":"2304.02080","title":"Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data","created":"2023-04-04","cited_by_count":3,"area":null},{"id":"2306.12559","title":"Exploring the Role of Audio in Video Captioning","created":"2023-06-21","cited_by_count":3,"area":null},{"id":"2210.03941","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2406.03857","title":"MuJo: Multimodal Joint Feature Space Learning for Human Activity Recognition","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2303.16341","title":"Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding","created":"2023-03-28","cited_by_count":1,"area":null},{"id":"2401.17773","title":"SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2404.12013","title":"Sequential Compositional Generalization in Multimodal Models","created":"2024-04-18","cited_by_count":1,"area":null},{"id":"2204.10938","title":"A Multi-level Alignment Training Scheme for Video-and-Language Grounding","created":"2022-04-22","cited_by_count":0,"area":null},{"id":"2310.12724","title":"Query-aware Long Video Localization and Relation Discrimination for Deep Video Understanding","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2311.12866","title":"Modular Blended Attention Network for Video Question Answering","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2311.17267","title":"E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2407.11677","title":"Video-Language Alignment via Spatio-Temporal Graph Transformer","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2510.23253","title":"A Video Is Not Worth a Thousand Words","created":"2025-10-27","cited_by_count":0,"area":"mllm"}],"next_cursor":null}