{"total":133,"rows":[{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458,"area":"wm"},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406,"area":"mllm"},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"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":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"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":"2306.15724","title":"REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction","created":"2023-06-27","cited_by_count":175,"area":null},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108,"area":"ssm"},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82,"area":null},{"id":"2301.02508","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","created":"2023-01-06","cited_by_count":78,"area":null},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"id":"2409.18111","title":"E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding","created":"2024-09-26","cited_by_count":70,"area":null},{"id":"2205.14022","title":"Future Transformer for Long-term Action Anticipation","created":"2022-05-27","cited_by_count":58,"area":null},{"id":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","cited_by_count":57,"area":null},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"area":null},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","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":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46,"area":null},{"id":"2309.13925","title":"Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges","created":"2023-09-25","cited_by_count":42,"area":null},{"id":"2305.00355","title":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","created":"2023-04-29","cited_by_count":40,"area":null},{"id":"2309.02999","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","created":"2023-09-06","cited_by_count":39,"area":null},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2404.07610","title":"Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval","created":"2024-04-11","cited_by_count":36,"area":null},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35,"area":null},{"id":"2203.14040","title":"Visual Abductive Reasoning","created":"2022-03-26","cited_by_count":30,"area":"lr"},{"id":"2501.13919","title":"Temporal Preference Optimization for Long-Form Video Understanding","created":"2025-01-23","cited_by_count":29,"area":"mllm"},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2204.08121","title":"End-to-end Dense Video Captioning as Sequence Generation","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2211.15103","title":"VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning","created":"2022-11-28","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":"2409.17647","title":"MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning","created":"2024-09-26","cited_by_count":23,"area":"lr"},{"id":"2308.06009","title":"ViGT: Proposal-free Video Grounding with Learnable Token in Transformer","created":"2023-08-11","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":"2502.14801","title":"AVD2: Accident Video Diffusion for Accident Video Description","created":"2025-02-20","cited_by_count":20,"area":null},{"id":"2508.10922","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","created":"2025-08-07","cited_by_count":20,"area":"mllm"},{"id":"2204.00486","title":"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval","created":"2022-04-01","cited_by_count":19,"area":null},{"id":"2206.12972","title":"VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning","created":"2022-06-26","cited_by_count":19,"area":null},{"id":"2303.02961","title":"Models See Hallucinations: Evaluating the Factuality in Video Captioning","created":"2023-03-06","cited_by_count":19,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2403.16276","title":"Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding","created":"2024-03-24","cited_by_count":18,"area":"mllm"},{"id":"2207.08625","title":"Unifying Event Detection and Captioning as Sequence Generation via Pre-Training","created":"2022-07-18","cited_by_count":17,"area":null},{"id":"2311.02538","title":"Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols","created":"2023-11-05","cited_by_count":17,"area":null},{"id":"2407.15350","title":"WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2409.17523","title":"EAGLE: Egocentric AGgregated Language-video Engine","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2506.07371","title":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","created":"2025-06-09","cited_by_count":16,"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":"2508.01699","title":"TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding","created":"2025-08-03","cited_by_count":14,"area":"moe"},{"id":"2512.15153","title":"Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning","created":"2025-12-17","cited_by_count":14,"area":"lr"},{"id":"2504.01020","title":"Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation","created":"2025-04-01","cited_by_count":13,"area":null},{"id":"2210.04615","title":"EmbryosFormer: Deformable Transformer and Collaborative Encoding-Decoding for Embryos Stage Development Classification","created":"2022-10-07","cited_by_count":12,"area":null},{"id":"2411.18180","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2204.12974","title":"CapOnImage: Context-driven Dense-Captioning on Image","created":"2022-04-27","cited_by_count":11,"area":null},{"id":"2311.16444","title":"Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos","created":"2023-11-28","cited_by_count":11,"area":null},{"id":"2602.08711","title":"TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions","created":"2026-02-09","cited_by_count":11,"area":null},{"id":"2301.05997","title":"Exploiting Auxiliary Caption for Video Grounding","created":"2023-01-15","cited_by_count":10,"area":null},{"id":"2306.11729","title":"Dense Video Object Captioning from Disjoint Supervision","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2403.07469","title":"A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes","created":"2024-03-12","cited_by_count":10,"area":null},{"id":"2504.05541","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2404.08229","title":"Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysis","created":"2024-04-12","cited_by_count":9,"area":null},{"id":"2405.11483","title":"MICap: A Unified Model for Identity-aware Movie Descriptions","created":"2024-05-19","cited_by_count":9,"area":null},{"id":"2501.06761","title":"VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning","created":"2025-01-12","cited_by_count":9,"area":"alignment"},{"id":"2504.00072","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","created":"2025-03-31","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":"2303.06378","title":"Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos","created":"2023-03-11","cited_by_count":8,"area":null},{"id":"2412.12791","title":"Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2501.19061","title":"EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real World","created":"2025-01-31","cited_by_count":8,"area":"offlinerl"},{"id":"2211.02178","title":"Zero-shot Video Moment Retrieval With Off-the-Shelf Models","created":"2022-11-03","cited_by_count":7,"area":null},{"id":"2408.11687","title":"Interpretable Long-term Action Quality Assessment","created":"2024-08-21","cited_by_count":7,"area":null},{"id":"2403.08049","title":"TutoAI: A Cross-domain Framework for AI-assisted Mixed-media Tutorial Creation on Physical Tasks","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2411.17130","title":"TechCoach: Towards Technical-Point-Aware Descriptive Action Coaching","created":"2024-11-26","cited_by_count":6,"area":null},{"id":"2112.08455","title":"Dense Video Captioning Using Unsupervised Semantic Information","created":"2021-12-15","cited_by_count":5,"area":null},{"id":"2206.11826","title":"Toward Clinically Assisted Colorectal Polyp Recognition via Structured Cross-modal Representation Consistency","created":"2022-06-23","cited_by_count":5,"area":null},{"id":"2212.06206","title":"Contextual Explainable Video Representation: Human Perception-based Understanding","created":"2022-12-12","cited_by_count":5,"area":null},{"id":"2410.08860","title":"Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2501.07227","title":"MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning","created":"2025-01-13","cited_by_count":5,"area":"lr"},{"id":"2507.04815","title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2510.18054","title":"HouseTour: A Virtual Real Estate A(I)gent","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2209.15501","title":"A Closer Look at Temporal Ordering in the Segmentation of Instructional Videos","created":"2022-09-30","cited_by_count":4,"area":null},{"id":"2307.02682","title":"Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2312.15720","title":"Set Prediction Guided by Semantic Concepts for Diverse Video Captioning","created":"2023-12-25","cited_by_count":4,"area":null},{"id":"2503.11392","title":"Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2509.04602","title":"Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2509.16538","title":"VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis","created":"2025-09-20","cited_by_count":4,"area":"mllm"},{"id":"2207.01050","title":"Exploiting Context Information for Generic Event Boundary Captioning","created":"2022-07-03","cited_by_count":3,"area":null},{"id":"2207.11838","title":"SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions","created":"2022-07-24","cited_by_count":3,"area":null},{"id":"2210.00434","title":"Music-to-Text Synaesthesia: Generating Descriptive Text from Music Recordings","created":"2022-10-02","cited_by_count":3,"area":null},{"id":"2310.02894","title":"Human-centric Behavior Description in Videos: New Benchmark and Model","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2403.19221","title":"Towards Multimodal Video Paragraph Captioning Models Robust to Missing Modality","created":"2024-03-28","cited_by_count":3,"area":null},{"id":"2408.02272","title":"COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2412.11467","title":"Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-learning","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2508.21809","title":"VoCap: Video Object Captioning and Segmentation from Any Prompt","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2207.02583","title":"PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning","created":"2022-07-06","cited_by_count":2,"area":null},{"id":"2209.10134","title":"Recipe Generation from Unsegmented Cooking Videos","created":"2022-09-21","cited_by_count":2,"area":null},{"id":"2406.14206","title":"Live Video Captioning","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2503.09027","title":"Measure Twice, Cut Once: A Semantic-Oriented Approach to Video Temporal Localization with Video LLMs","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2512.05277","title":"From Segments to Scenes: Temporal Understanding for Agentic Autonomous Driving via Vision-Language Models","created":"2025-12-04","cited_by_count":2,"area":"mllm"}],"next_cursor":"100"}