{"total":333,"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":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857,"area":null},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781,"area":null},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758,"area":null},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"area":null},{"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":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412,"area":null},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292,"area":null},{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262,"area":null},{"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":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225,"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":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"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":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184,"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":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169,"area":null},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"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":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"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":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133,"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":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114,"area":null},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"id":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109,"area":null},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107,"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":"2106.11013","title":"Interventional Video Grounding with Dual Contrastive Learning","created":"2021-06-21","cited_by_count":94,"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":"2103.08109","title":"Boundary Proposal Network for Two-Stage Natural Language Video Localization","created":"2021-03-15","cited_by_count":88,"area":null},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87,"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":"2403.10228","title":"HawkEye: Training Video-Text LLMs for Grounding Text in Videos","created":"2024-03-15","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":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83,"area":null},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"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":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73,"area":null},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68,"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":"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":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2104.14085","title":"Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering","created":"2021-04-29","cited_by_count":56,"area":null},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","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":"2108.08121","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","created":"2021-08-18","cited_by_count":52,"area":null},{"id":"2207.01203","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","created":"2022-07-04","cited_by_count":50,"area":null},{"id":"2310.06838","title":"AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description","created":"2023-10-10","cited_by_count":49,"area":null},{"id":"2210.08604","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","created":"2022-10-16","cited_by_count":48,"area":null},{"id":"2107.05624","title":"End-to-end Multi-modal Video Temporal Grounding","created":"2021-07-12","cited_by_count":47,"area":null},{"id":"2311.17058","title":"Panoptic Video Scene Graph Generation","created":"2023-11-28","cited_by_count":46,"area":null},{"id":"2203.06667","title":"Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video","created":"2022-03-13","cited_by_count":43,"area":null},{"id":"2410.19100","title":"VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web Tasks","created":"2024-10-24","cited_by_count":43,"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":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2407.12679","title":"Goldfish: Vision-Language Understanding of Arbitrarily Long Videos","created":"2024-07-17","cited_by_count":40,"area":null},{"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":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37,"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":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2201.09168","title":"Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval","created":"2022-01-23","cited_by_count":34,"area":null},{"id":"2109.10016","title":"CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval","created":"2021-09-21","cited_by_count":33,"area":null},{"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":"2205.01652","title":"Episodic Memory Question Answering","created":"2022-05-03","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":"2103.16848","title":"Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding","created":"2021-03-31","cited_by_count":29,"area":null},{"id":"2109.08039","title":"A Survey on Temporal Sentence Grounding in Videos","created":"2021-09-16","cited_by_count":29,"area":null},{"id":"2505.05456","title":"SITE: towards Spatial Intelligence Thorough Evaluation","created":"2025-05-08","cited_by_count":29,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2108.10576","title":"Support-Set Based Cross-Supervision for Video Grounding","created":"2021-08-24","cited_by_count":28,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28,"area":null},{"id":"2109.09920","title":"Survey: Transformer based Video-Language Pre-training","created":"2021-09-21","cited_by_count":27,"area":null},{"id":"2109.10678","title":"Natural Language Video Localization with Learnable Moment Proposals","created":"2021-09-22","cited_by_count":27,"area":null},{"id":"2110.05717","title":"Relation-aware Video Reading Comprehension for Temporal Language Grounding","created":"2021-10-12","cited_by_count":27,"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":"2507.09313","title":"ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models","created":"2025-07-12","cited_by_count":27,"area":null},{"id":"2106.10446","title":"Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering","created":"2021-06-19","cited_by_count":26,"area":null},{"id":"2109.04275","title":"M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining","created":"2021-09-09","cited_by_count":26,"area":null}],"next_cursor":"100"}