{"total":68,"rows":[{"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":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141,"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":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86,"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":"2103.15538","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","created":"2021-03-29","cited_by_count":84,"area":null},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"id":"2209.06192","title":"StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation","created":"2022-09-13","cited_by_count":74,"area":null},{"id":"2406.11303","title":"VideoVista: A Versatile Benchmark for Video Understanding and Reasoning","created":"2024-06-17","cited_by_count":72,"area":"mllm"},{"id":"2211.10950","title":"Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models","created":"2022-11-20","cited_by_count":70,"area":"diffusion"},{"id":"2401.01256","title":"VideoStudio: Generating Consistent-Content and Multi-Scene Videos","created":"2024-01-02","cited_by_count":64,"area":"diffusion"},{"id":"2110.10834","title":"Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization","created":"2021-10-21","cited_by_count":52,"area":null},{"id":"2105.10026","title":"Improving Generation and Evaluation of Visual Stories via Semantic Consistency","created":"2021-05-20","cited_by_count":43,"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":"2106.13432","title":"Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering","created":"2021-06-25","cited_by_count":29,"area":null},{"id":"2308.11606","title":"StoryBench: A Multifaceted Benchmark for Continuous Story Visualization","created":"2023-08-22","cited_by_count":29,"area":null},{"id":"2212.09993","title":"Are Deep Neural Networks SMARTer than Second Graders?","created":"2022-12-20","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":"2208.02341","title":"Word-Level Fine-Grained Story Visualization","created":"2022-08-03","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":"2404.05979","title":"StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion","created":"2024-04-09","cited_by_count":20,"area":null},{"id":"2107.12270","title":"Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference","created":"2021-07-26","cited_by_count":18,"area":null},{"id":"2208.00934","title":"Video Question Answering with Iterative Video-Text Co-Tokenization","created":"2022-08-01","cited_by_count":16,"area":null},{"id":"2204.07190","title":"Measuring Compositional Consistency for Video Question Answering","created":"2022-04-14","cited_by_count":15,"area":null},{"id":"2305.02519","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","created":"2023-05-04","cited_by_count":15,"area":null},{"id":"2410.06244","title":"Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2101.05954","title":"Recent Advances in Video Question Answering: A Review of Datasets and Methods","created":"2021-01-15","cited_by_count":12,"area":null},{"id":"2104.04182","title":"FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework","created":"2021-04-09","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":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2209.06650","title":"WildQA: In-the-Wild Video Question Answering","created":"2022-09-14","cited_by_count":9,"area":null},{"id":"2406.13763","title":"Through the Theory of Mind's Eye: Reading Minds with Multimodal Video Large Language Models","created":"2024-06-19","cited_by_count":9,"area":"mllm"},{"id":"2203.05711","title":"Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding","created":"2022-03-11","cited_by_count":8,"area":null},{"id":"2104.05166","title":"Object-Centric Representation Learning for Video Question Answering","created":"2021-04-12","cited_by_count":7,"area":null},{"id":"2209.01621","title":"Interactive Question Answering Systems: Literature Review","created":"2022-09-04","cited_by_count":7,"area":null},{"id":"2308.07575","title":"Story Visualization by Online Text Augmentation with Context Memory","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2311.01233","title":"Long Story Short: a Summarize-then-Search Method for Long Video Question Answering","created":"2023-11-02","cited_by_count":7,"area":null},{"id":"2405.10122","title":"Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks","created":"2024-05-16","cited_by_count":6,"area":null},{"id":"2410.13754","title":"MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures","created":"2024-10-17","cited_by_count":6,"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":"2202.04015","title":"NEWSKVQA: Knowledge-Aware News Video Question Answering","created":"2022-02-08","cited_by_count":4,"area":null},{"id":"2306.14644","title":"PTVD: A Large-Scale Plot-Oriented Multimodal Dataset Based on Television Dramas","created":"2023-06-26","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":"2108.04542","title":"TrUMAn: Trope Understanding in Movies and Animations","created":"2021-08-10","cited_by_count":3,"area":null},{"id":"2211.07289","title":"Learning to Model Multimodal Semantic Alignment for Story Visualization","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2304.00436","title":"Instance-Level Trojan Attacks on Visual Question Answering via Adversarial Learning in Neuron Activation Space","created":"2023-04-02","cited_by_count":3,"area":null},{"id":"2406.02748","title":"Story Generation from Visual Inputs: Techniques, Related Tasks, and Challenges","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2101.07632","title":"Situation and Behavior Understanding by Trope Detection on Films","created":"2021-01-19","cited_by_count":2,"area":null},{"id":"2406.13092","title":"Multilingual Synopses of Movie Narratives: A Dataset for Vision-Language Story Understanding","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2108.05158","title":"Mounting Video Metadata on Transformer-based Language Model for Open-ended Video Question Answering","created":"2021-08-11","cited_by_count":1,"area":null},{"id":"2208.06662","title":"Self-Contained Entity Discovery from Captioned Videos","created":"2022-08-13","cited_by_count":1,"area":null},{"id":"2309.12224","title":"Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2311.06553","title":"Visual Commonsense based Heterogeneous Graph Contrastive Learning","created":"2023-11-11","cited_by_count":1,"area":null},{"id":"2412.17022","title":"FriendsQA: A New Large-Scale Deep Video Understanding Dataset with Fine-grained Topic Categorization for Story Videos","created":"2024-12-22","cited_by_count":1,"area":null},{"id":"2412.20619","title":"Audiopedia: Audio QA with Knowledge","created":"2024-12-29","cited_by_count":1,"area":null},{"id":"2504.15182","title":"Tiger200K: Manually Curated High Visual Quality Video Dataset from UGC Platform","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2603.06828","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","created":"2026-03-06","cited_by_count":1,"area":"mllm"},{"id":"2109.09906","title":"Audio Interval Retrieval using Convolutional Neural Networks","created":"2021-09-21","cited_by_count":0,"area":null},{"id":"2209.03609","title":"Frame-Subtitle Self-Supervision for Multi-Modal Video Question Answering","created":"2022-09-08","cited_by_count":0,"area":null},{"id":"2406.05318","title":"Integrating Text and Image Pre-training for Multi-modal Algorithmic Reasoning","created":"2024-06-08","cited_by_count":0,"area":null},{"id":"2409.09348","title":"QTG-VQA: Question-Type-Guided Architectural for VideoQA Systems","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2603.24484","title":"Video-Only ToM: Enhancing Theory of Mind in Multimodal Large Language Models","created":"2026-03-25","cited_by_count":0,"area":"mllm"},{"id":"2605.04733","title":"Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2607.18716","title":"Continual Video-MLLM Adaptation over Evolving Domains","created":"2026-07-21","cited_by_count":0,"area":"mllm"}],"next_cursor":null}