{"total":151,"rows":[{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"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":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2307.16715","title":"UniVTG: Towards Unified Video-Language Temporal Grounding","created":"2023-07-31","cited_by_count":190,"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":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135,"area":null},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116,"area":null},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110,"area":null},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95,"area":null},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64,"area":null},{"id":"2403.11050","title":"Endora: Video Generation Models as Endoscopy Simulators","created":"2024-03-17","cited_by_count":55,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2308.14746","title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","created":"2023-08-28","cited_by_count":52,"area":null},{"id":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51,"area":null},{"id":"2312.05269","title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","created":"2023-12-07","cited_by_count":51,"area":null},{"id":"2503.06220","title":"StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition","created":"2025-03-08","cited_by_count":46,"area":null},{"id":"2406.18070","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","created":"2024-06-26","cited_by_count":44,"area":null},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42,"area":null},{"id":"2308.07893","title":"Memory-and-Anticipation Transformer for Online Action Understanding","created":"2023-08-15","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":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37,"area":null},{"id":"2404.16038","title":"A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming","created":"2024-01-30","cited_by_count":37,"area":null},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","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":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34,"area":null},{"id":"2301.01380","title":"Ego-Only: Egocentric Action Detection without Exocentric Transferring","created":"2023-01-03","cited_by_count":31,"area":null},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","cited_by_count":31,"area":null},{"id":"2401.03717","title":"Universal Time-Series Representation Learning: A Survey","created":"2024-01-08","cited_by_count":30,"area":null},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26,"area":null},{"id":"2503.09143","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","created":"2025-03-12","cited_by_count":25,"area":null},{"id":"2501.00358","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","created":"2024-12-31","cited_by_count":24,"area":null},{"id":"2510.12422","title":"VideoLucy: Deep Memory Backtracking for Long Video Understanding","created":"2025-10-14","cited_by_count":22,"area":null},{"id":"2301.09209","title":"Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation","created":"2023-01-22","cited_by_count":21,"area":null},{"id":"2407.16658","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","created":"2024-07-23","cited_by_count":21,"area":null},{"id":"2308.11489","title":"Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition","created":"2023-08-22","cited_by_count":20,"area":null},{"id":"2309.16669","title":"Training a Large Video Model on a Single Machine in a Day","created":"2023-09-28","cited_by_count":20,"area":null},{"id":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17,"area":null},{"id":"2402.17128","title":"OSCaR: Object State Captioning and State Change Representation","created":"2024-02-27","cited_by_count":16,"area":null},{"id":"2410.10450","title":"KBLaM: Knowledge Base augmented Language Model","created":"2024-10-14","cited_by_count":16,"area":null},{"id":"2404.05559","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","created":"2024-04-08","cited_by_count":15,"area":null},{"id":"2405.09592","title":"A Survey of Generative Techniques for Spatial-Temporal Data Mining","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2503.18223","title":"MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps","created":"2025-03-23","cited_by_count":14,"area":null},{"id":"2306.02728","title":"Background-aware Moment Detection for Video Moment Retrieval","created":"2023-06-05","cited_by_count":13,"area":null},{"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":"2404.05206","title":"SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos","created":"2024-04-08","cited_by_count":11,"area":null},{"id":"2404.16222","title":"Step Differences in Instructional Video","created":"2024-04-24","cited_by_count":11,"area":null},{"id":"2405.17719","title":"Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?","created":"2024-05-28","cited_by_count":11,"area":null},{"id":"2409.19650","title":"Grounding 3D Scene Affordance From Egocentric Interactions","created":"2024-09-29","cited_by_count":11,"area":null},{"id":"2502.20879","title":"egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Tasks","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2505.04270","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","created":"2025-05-07","cited_by_count":11,"area":null},{"id":"2510.21356","title":"Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding","created":"2025-10-24","cited_by_count":11,"area":null},{"id":"2307.10922","title":"Language-based Action Concept Spaces Improve Video Self-Supervised Learning","created":"2023-07-20","cited_by_count":10,"area":null},{"id":"2310.11699","title":"MISAR: A Multimodal Instructional System with Augmented Reality","created":"2023-10-18","cited_by_count":10,"area":null},{"id":"2311.01025","title":"Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2312.14055","title":"Multi-Sentence Grounding for Long-term Instructional Video","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2504.20041","title":"Learning Streaming Video Representation via Multitask Training","created":"2025-04-28","cited_by_count":10,"area":null},{"id":"2403.03037","title":"A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2406.15771","title":"HCQA @ Ego4D EgoSchema Challenge 2024","created":"2024-06-22","cited_by_count":9,"area":null},{"id":"2506.07886","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2407.03788","title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2407.07478","title":"EA-VTR: Event-Aware Video-Text Retrieval","created":"2024-07-10","cited_by_count":8,"area":null},{"id":"2407.17792","title":"Harnessing Temporal Causality for Advanced Temporal Action Detection","created":"2024-07-25","cited_by_count":8,"area":null},{"id":"2402.19366","title":"Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2503.09402","title":"VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary","created":"2025-03-12","cited_by_count":7,"area":null},{"id":"2505.12911","title":"HiERO: understanding the hierarchy of human behavior enhances reasoning on egocentric videos","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2311.18572","title":"Source-free Video Domain Adaptation by Learning from Noisy Labels","created":"2023-11-30","cited_by_count":6,"area":null},{"id":"2403.16128","title":"Enhancing Video Transformers for Action Understanding with VLM-aided Training","created":"2024-03-24","cited_by_count":6,"area":null},{"id":"2505.24848","title":"Reading Recognition in the Wild","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2311.16673","title":"Large Language Models Meet Computer Vision: A Brief Survey","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2312.00055","title":"LEAP: LLM-Generation of Egocentric Action Programs","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2502.02487","title":"Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectives","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2503.15470","title":"EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2504.17213","title":"MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding","created":"2025-04-24","cited_by_count":5,"area":null},{"id":"2507.00033","title":"Moment Sampling in Video LLMs for Long-Form Video QA","created":"2025-06-18","cited_by_count":5,"area":null},{"id":"2605.17423","title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","created":"2026-05-17","cited_by_count":5,"area":null},{"id":"2607.11523","title":"Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos","created":"2026-07-13","cited_by_count":5,"area":null},{"id":"2403.05535","title":"Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videos","created":"2024-03-08","cited_by_count":4,"area":null},{"id":"2405.01090","title":"Learning Multiple Object States from Actions via Large Language Models","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2409.15172","title":"Skills Made to Order: Efficient Acquisition of Robot Cooking Skills Guided by Multiple Forms of Internet Data","created":"2024-09-23","cited_by_count":4,"area":null},{"id":"2410.14238","title":"Storyboard guided Alignment for Fine-grained Video Action Recognition","created":"2024-10-18","cited_by_count":4,"area":null},{"id":"2506.05274","title":"From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2507.14784","title":"LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2507.18374","title":"Towards Effective Human-in-the-Loop Assistive AI Agents","created":"2025-07-24","cited_by_count":4,"area":null},{"id":"2509.20851","title":"Poisoning Prompt-Guided Sampling in Video Large Language Models","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2511.21681","title":"Seeing without Pixels: Perception from Camera Trajectories","created":"2025-11-26","cited_by_count":4,"area":null},{"id":"2410.01180","title":"UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2410.11702","title":"It's Just Another Day: Unique Video Captioning by Discriminative Prompting","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2411.13683","title":"Extending Video Masked Autoencoders to 128 frames","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2412.03567","title":"Streaming Detection of Queried Event Start","created":"2024-12-04","cited_by_count":3,"area":null},{"id":"2504.03948","title":"ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2505.10671","title":"GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encoding","created":"2025-05-15","cited_by_count":3,"area":null}],"next_cursor":"100"}