{"total":154,"rows":[{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680,"area":null},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"area":null},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484,"area":null},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293,"area":"lr"},{"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":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213,"area":null},{"id":"2111.12681","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","created":"2021-11-24","cited_by_count":188,"area":null},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179,"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":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135,"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":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95,"area":null},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","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":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74,"area":null},{"id":"2107.09609","title":"QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries","created":"2021-07-20","cited_by_count":72,"area":null},{"id":"2406.09396","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","created":"2024-06-13","cited_by_count":68,"area":null},{"id":"2503.11495","title":"V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning","created":"2025-03-14","cited_by_count":68,"area":"lr"},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2304.14407","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","created":"2023-04-27","cited_by_count":65,"area":null},{"id":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63,"area":null},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58,"area":"agents"},{"id":"2102.13558","title":"Natural Language Video Localization: A Revisit in Span-based Question Answering Framework","created":"2021-02-26","cited_by_count":55,"area":null},{"id":"2212.09522","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","created":"2022-12-19","cited_by_count":55,"area":null},{"id":"2106.02192","title":"Grounding 'Grounding' in NLP","created":"2021-06-04","cited_by_count":44,"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":"2103.08849","title":"Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models","created":"2021-03-16","cited_by_count":41,"area":"mllm"},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2202.04800","title":"The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning","created":"2022-02-10","cited_by_count":38,"area":"lr"},{"id":"2201.08071","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","created":"2022-01-20","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":"2510.25760","title":"Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks","created":"2025-10-29","cited_by_count":33,"area":"lr"},{"id":"2203.04203","title":"AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant","created":"2022-03-08","cited_by_count":32,"area":null},{"id":"2110.08020","title":"Multimodal Emotion-Cause Pair Extraction in Conversations","created":"2021-10-15","cited_by_count":31,"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":"2209.10918","title":"CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding","created":"2022-09-22","cited_by_count":27,"area":null},{"id":"2201.12888","title":"A Dataset for Medical Instructional Video Classification and Question Answering","created":"2022-01-30","cited_by_count":26,"area":null},{"id":"2312.04817","title":"LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering","created":"2023-12-08","cited_by_count":25,"area":null},{"id":"2403.16998","title":"Understanding Long Videos with Multimodal Language Models","created":"2024-03-25","cited_by_count":25,"area":"mllm"},{"id":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24,"area":null},{"id":"2408.12763","title":"Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models","created":"2024-08-22","cited_by_count":23,"area":"mllm"},{"id":"2105.04836","title":"Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules","created":"2021-05-11","cited_by_count":22,"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":"2112.01194","title":"Video-Text Pre-training with Learned Regions","created":"2021-12-02","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":"2205.06907","title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","created":"2022-05-13","cited_by_count":16,"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":"2410.23828","title":"Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection","created":"2024-10-31","cited_by_count":15,"area":null},{"id":"2412.09601","title":"TimeRefine: Temporal Grounding with Time Refining Video LLM","created":"2024-12-12","cited_by_count":15,"area":null},{"id":"2509.18056","title":"TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs","created":"2025-09-22","cited_by_count":15,"area":"mllm"},{"id":"2511.08521","title":"UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist","created":"2025-11-11","cited_by_count":15,"area":"agents"},{"id":"2112.00475","title":"Weakly-Supervised Video Object Grounding via Causal Intervention","created":"2021-12-01","cited_by_count":13,"area":null},{"id":"2211.03779","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","created":"2022-11-07","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":"2402.19467","title":"TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning","created":"2024-02-29","cited_by_count":12,"area":"lr"},{"id":"2408.02687","title":"Compositional Physical Reasoning of Objects and Events from Videos","created":"2024-08-02","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":"2310.03635","title":"CLEVRER-Humans: Describing Physical and Causal Events the Human Way","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2412.17574","title":"HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks","created":"2024-12-23","cited_by_count":11,"area":"mllm"},{"id":"2210.05423","title":"Learning to Locate Visual Answer in Video Corpus Using Question","created":"2022-10-11","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":"2406.19131","title":"CELLO: Causal Evaluation of Large Vision-Language Models","created":"2024-06-27","cited_by_count":10,"area":"lr"},{"id":"2209.06650","title":"WildQA: In-the-Wild Video Question Answering","created":"2022-09-14","cited_by_count":9,"area":null},{"id":"2308.05822","title":"Encode-Store-Retrieve: Augmenting Human Memory through Language-Encoded Egocentric Perception","created":"2023-08-10","cited_by_count":9,"area":null},{"id":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2504.07519","title":"VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding","created":"2025-04-10","cited_by_count":9,"area":null},{"id":"2511.17952","title":"Multi-speaker Attention Alignment for Multimodal Social Interaction","created":"2025-11-22","cited_by_count":9,"area":null},{"id":"2305.00607","title":"Boosting Weakly-Supervised Temporal Action Localization with Text Information","created":"2023-05-01","cited_by_count":8,"area":null},{"id":"2405.19723","title":"Encoding and Controlling Global Semantics for Long-form Video Question Answering","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2506.09445","title":"TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2103.14517","title":"On the hidden treasure of dialog in video question answering","created":"2021-03-26","cited_by_count":7,"area":null},{"id":"2211.04534","title":"Going for GOAL: A Resource for Grounded Football Commentaries","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2310.14670","title":"Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond","created":"2023-10-23","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":"2401.01823","title":"Detours for Navigating Instructional Videos","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2510.03584","title":"FrameOracle: Learning What to See and How Much to See in Videos","created":"2025-10-04","cited_by_count":7,"area":"mllm"},{"id":"2209.07518","title":"Distribution Aware Metrics for Conditional Natural Language Generation","created":"2022-09-15","cited_by_count":6,"area":null},{"id":"2304.03754","title":"Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering","created":"2023-04-07","cited_by_count":6,"area":null},{"id":"2404.04007","title":"Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering","created":"2024-04-05","cited_by_count":6,"area":"lr"},{"id":"2210.14512","title":"End-to-End Multimodal Representation Learning for Video Dialog","created":"2022-10-26","cited_by_count":5,"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":"2303.03131","title":"Video Question Answering Using CLIP-Guided Visual-Text Attention","created":"2023-03-06","cited_by_count":5,"area":null},{"id":"2310.18359","title":"DeSIQ: Towards an Unbiased, Challenging Benchmark for Social Intelligence Understanding","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2409.14319","title":"Scene-Text Grounding for Text-Based Video Question Answering","created":"2024-09-22","cited_by_count":5,"area":null},{"id":"2108.02365","title":"Hybrid Reasoning Network for Video-based Commonsense Captioning","created":"2021-08-05","cited_by_count":4,"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":"2202.04015","title":"NEWSKVQA: Knowledge-Aware News Video Question Answering","created":"2022-02-08","cited_by_count":4,"area":null},{"id":"2312.02483","title":"EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model","created":"2023-12-05","cited_by_count":4,"area":"mllm"},{"id":"2312.17429","title":"Commonsense for Zero-Shot Natural Language Video Localization","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2410.21414","title":"CT2C-QA: Multimodal Question Answering over Chinese Text, Table and Chart","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2505.17536","title":"Multimodal Conversation Structure Understanding","created":"2025-05-23","cited_by_count":4,"area":"mllm"},{"id":"2603.14659","title":"VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting","created":"2026-03-15","cited_by_count":4,"area":"distill"},{"id":"2105.06160","title":"Relation-aware Hierarchical Attention Framework for Video Question Answering","created":"2021-05-13","cited_by_count":3,"area":null},{"id":"2309.02290","title":"ATM: Action Temporality Modeling for Video Question Answering","created":"2023-09-05","cited_by_count":3,"area":"lr"}],"next_cursor":"100"}