{"total":61,"rows":[{"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":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63,"area":null},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58,"area":null},{"id":"2409.18313","title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","created":"2024-09-26","cited_by_count":44,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"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":"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":"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":"2412.09582","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","created":"2024-12-12","cited_by_count":25,"area":null},{"id":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24,"area":null},{"id":"2207.12783","title":"Equivariant and Invariant Grounding for Video Question Answering","created":"2022-07-26","cited_by_count":22,"area":null},{"id":"2307.12058","title":"Discovering Spatio-Temporal Rationales for Video Question Answering","created":"2023-07-22","cited_by_count":21,"area":null},{"id":"2312.02310","title":"VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding","created":"2023-12-04","cited_by_count":18,"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":"2506.00717","title":"Vid2Coach: Transforming How-To Videos into Task Assistants","created":"2025-05-31","cited_by_count":12,"area":null},{"id":"2404.16222","title":"Step Differences in Instructional Video","created":"2024-04-24","cited_by_count":11,"area":null},{"id":"2409.04388","title":"Question-Answering Dense Video Events","created":"2024-09-06","cited_by_count":11,"area":null},{"id":"2410.05267","title":"Grounding Partially-Defined Events in Multimodal Data","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2209.06650","title":"WildQA: In-the-Wild Video Question Answering","created":"2022-09-14","cited_by_count":9,"area":null},{"id":"2305.06472","title":"ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2306.08889","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2312.10728","title":"Benchmarks for Physical Reasoning AI","created":"2023-12-17","cited_by_count":8,"area":null},{"id":"2506.02448","title":"VidEvent: A Large Dataset for Understanding Dynamic Evolution of Events in Videos","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2308.03267","title":"Redundancy-aware Transformer for Video Question Answering","created":"2023-08-07","cited_by_count":7,"area":null},{"id":"2212.13163","title":"MRTNet: Multi-Resolution Temporal Network for Video Sentence Grounding","created":"2022-12-26","cited_by_count":6,"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":"2404.04728","title":"Navigating the Landscape of Hint Generation Research: From the Past to the Future","created":"2024-04-06","cited_by_count":6,"area":null},{"id":"2408.11490","title":"DocTabQA: Answering Questions from Long Documents Using Tables","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2306.09922","title":"Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions","created":"2023-06-16","cited_by_count":5,"area":null},{"id":"2310.19516","title":"Generating Context-Aware Natural Answers for Questions in 3D Scenes","created":"2023-10-30","cited_by_count":5,"area":null},{"id":"2402.07402","title":"BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind","created":"2024-02-12","cited_by_count":5,"area":null},{"id":"2409.17702","title":"Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2508.13428","title":"Mitigating Easy Option Bias in Multiple-Choice Question Answering","created":"2025-08-19","cited_by_count":4,"area":null},{"id":"2307.09329","title":"Towards a performance analysis on pre-trained Visual Question Answering models for autonomous driving","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2307.13250","title":"Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2401.17343","title":"YTCommentQA: Video Question Answerability in Instructional Videos","created":"2024-01-30","cited_by_count":3,"area":null},{"id":"2406.18538","title":"VideoQA-SC: Adaptive Semantic Communication for Video Question Answering","created":"2024-05-17","cited_by_count":3,"area":null},{"id":"2410.09379","title":"Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2505.13429","title":"Understanding Complexity in VideoQA via Visual Program Generation","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2505.17423","title":"VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2404.13530","title":"Listen Then See: Video Alignment with Speaker Attention","created":"2024-04-21","cited_by_count":2,"area":null},{"id":"2503.06820","title":"Towards Fine-Grained Video Question Answering","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2503.15887","title":"DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2607.27826","title":"Sign Language Question Answering: A New Task, Benchmark, and Baseline for Sign Language Understanding","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2305.09107","title":"Is a Video worth $n\\times n$ Images? A Highly Efficient Approach to Transformer-based Video Question Answering","created":"2023-05-16","cited_by_count":1,"area":null},{"id":"2403.14430","title":"Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels","created":"2024-03-21","cited_by_count":1,"area":null},{"id":"2508.11163","title":"MobQA: A Benchmark Dataset for Semantic Understanding of Human Mobility Data through Question Answering","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2509.24445","title":"Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2601.14895","title":"SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2602.07689","title":"Process-of-Thought Reasoning for Videos","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2605.24703","title":"TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2606.24797","title":"EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2305.08059","title":"Semantic-aware Dynamic Retrospective-Prospective Reasoning for Event-level Video Question Answering","created":"2023-05-14","cited_by_count":0,"area":null},{"id":"2310.10586","title":"VidCoM: Fast Video Comprehension through Large Language Models with Multimodal Tools","created":"2023-10-16","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":"2412.09230","title":"Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2504.05783","title":"Video Flow as Time Series: Discovering Temporal Consistency and Variability for VideoQA","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2507.22369","title":"Exploring the Application of Visual Question Answering (VQA) for Classroom Activity Monitoring","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2606.06338","title":"StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":null}