{"total":130,"rows":[{"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":"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":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"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":"2411.00785","title":"IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI","created":"2024-10-17","cited_by_count":72,"area":"wm"},{"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":"2408.16730","title":"VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation","created":"2024-08-29","cited_by_count":55,"area":"mllm"},{"id":"2312.12423","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","created":"2023-12-19","cited_by_count":53,"area":"mllm"},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44,"area":null},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2311.17944","title":"PALM: Predicting Actions through Language Models","created":"2023-11-29","cited_by_count":29,"area":null},{"id":"2411.19083","title":"ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives","created":"2024-11-28","cited_by_count":29,"area":null},{"id":"2312.03849","title":"LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning","created":"2023-12-06","cited_by_count":28,"area":"diffusion"},{"id":"2406.01486","title":"Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos","created":"2024-06-03","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":"2312.08367","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","created":"2023-12-13","cited_by_count":23,"area":null},{"id":"2507.18342","title":"EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs","created":"2025-07-24","cited_by_count":23,"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":"2503.08221","title":"EgoBlind: Towards Egocentric Visual Assistance for the Blind","created":"2025-03-11","cited_by_count":21,"area":"mllm"},{"id":"2508.10729","title":"EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering","created":"2025-08-14","cited_by_count":21,"area":"mllm"},{"id":"2503.00986","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","created":"2025-03-02","cited_by_count":20,"area":null},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2403.08755","title":"DAM: Dynamic Adapter Merging for Continual Video QA Learning","created":"2024-03-13","cited_by_count":19,"area":null},{"id":"2412.21080","title":"Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model","created":"2024-12-30","cited_by_count":19,"area":"mllm"},{"id":"2504.13915","title":"Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2510.06218","title":"EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark","created":"2025-10-07","cited_by_count":19,"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":"2501.06835","title":"X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding","created":"2025-01-12","cited_by_count":15,"area":null},{"id":"2406.01194","title":"AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation","created":"2024-06-03","cited_by_count":14,"area":null},{"id":"2411.18428","title":"MM-Path: Multi-modal, Multi-granularity Path Representation Learning -- Extended Version","created":"2024-11-27","cited_by_count":14,"area":null},{"id":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12,"area":"mllm"},{"id":"2510.17023","title":"Enrich and Detect: Video Temporal Grounding with Multimodal LLMs","created":"2025-10-19","cited_by_count":12,"area":"mllm"},{"id":"2512.04451","title":"StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios","created":"2025-12-04","cited_by_count":12,"area":null},{"id":"2603.20169","title":"EgoForge: Goal-Directed Egocentric World Simulator","created":"2026-03-20","cited_by_count":12,"area":"wm"},{"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":"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":"2505.04270","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","created":"2025-05-07","cited_by_count":11,"area":null},{"id":"2508.00518","title":"Fine-grained Spatiotemporal Grounding on Egocentric Videos","created":"2025-08-01","cited_by_count":11,"area":null},{"id":"2512.16793","title":"PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence","created":"2025-12-18","cited_by_count":11,"area":"mllm"},{"id":"2602.14122","title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","created":"2026-02-15","cited_by_count":11,"area":"mllm"},{"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":"2403.18074","title":"Every Shot Counts: Using Exemplars for Repetition Counting in Videos","created":"2024-03-26","cited_by_count":9,"area":null},{"id":"2404.09933","title":"HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision","created":"2024-04-15","cited_by_count":9,"area":"mllm"},{"id":"2405.19794","title":"Video Question Answering for People with Visual Impairments Using an Egocentric 360-Degree Camera","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2406.13123","title":"ViLCo-Bench: VIdeo Language COntinual learning Benchmark","created":"2024-06-19","cited_by_count":9,"area":null},{"id":"2412.00932","title":"FIction: 4D Future Interaction Prediction from Video","created":"2024-12-01","cited_by_count":9,"area":null},{"id":"2401.10039","title":"GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition","created":"2024-01-18","cited_by_count":8,"area":"mllm"},{"id":"2503.04250","title":"An Egocentric Vision-Language Model based Portable Real-time Smart Assistant","created":"2025-03-06","cited_by_count":8,"area":"mllm"},{"id":"2506.06253","title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2401.11470","title":"Exploring Missing Modality in Multimodal Egocentric Datasets","created":"2024-01-21","cited_by_count":7,"area":null},{"id":"2407.05576","title":"CaRe-Ego: Contact-aware Relationship Modeling for Egocentric Interactive Hand-object Segmentation","created":"2024-07-08","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":"2604.01966","title":"Ego-Grounding for Personalized Question-Answering in Egocentric Videos","created":"2026-04-02","cited_by_count":7,"area":"mllm"},{"id":"2403.19811","title":"X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization","created":"2024-03-28","cited_by_count":6,"area":"mllm"},{"id":"2410.01341","title":"Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2411.08753","title":"Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos","created":"2024-11-13","cited_by_count":6,"area":null},{"id":"2503.19706","title":"Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2505.21955","title":"Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs","created":"2025-05-28","cited_by_count":6,"area":"mllm"},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2409.11513","title":"Mamba Fusion: Learning Actions Through Questioning","created":"2024-09-17","cited_by_count":5,"area":"ssm"},{"id":"2410.05343","title":"EgoOops: A Dataset for Mistake Action Detection from Egocentric Videos referring to Procedural Texts","created":"2024-10-07","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":"2511.12878","title":"Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views","created":"2025-11-17","cited_by_count":5,"area":null},{"id":"2511.13261","title":"Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges","created":"2025-11-17","cited_by_count":5,"area":"mllm"},{"id":"2605.24481","title":"OmniEgo-R$^2$: A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026","created":"2026-05-23","cited_by_count":5,"area":"lr"},{"id":"2606.01113","title":"R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking","created":"2026-05-31","cited_by_count":5,"area":null},{"id":"2503.11345","title":"EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2505.17114","title":"RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2506.12258","title":"EgoPrivacy: What Your First-Person Camera Says About You?","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2506.21080","title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","created":"2025-06-26","cited_by_count":4,"area":null},{"id":"2511.13993","title":"Learning Skill-Attributes for Transferable Assessment in Video","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2511.19629","title":"SkillSight: Efficient First-Person Skill Assessment with Gaze","created":"2025-11-24","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":"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},{"id":"2506.14356","title":"EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2508.16512","title":"Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation","created":"2025-08-22","cited_by_count":3,"area":"wm"},{"id":"2602.06139","title":"EgoAVU: Egocentric Audio-Visual Understanding","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2406.09462","title":"SViTT-Ego: A Sparse Video-Text Transformer for Egocentric Video","created":"2024-06-13","cited_by_count":2,"area":"mllm"},{"id":"2502.17753","title":"Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos","created":"2025-02-25","cited_by_count":2,"area":null},{"id":"2505.14346","title":"Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2508.10745","title":"Agentic Design Review System","created":"2025-08-14","cited_by_count":2,"area":"agents"},{"id":"2604.19564","title":"EgoSelf: From Memory to Personalized Egocentric Assistant","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2402.02335","title":"Video Editing for Video Retrieval","created":"2024-02-04","cited_by_count":1,"area":null},{"id":"2404.03161","title":"BioVL-QR: Egocentric Biochemical Vision-and-Language Dataset Using Micro QR Codes","created":"2024-04-04","cited_by_count":1,"area":null},{"id":"2406.03447","title":"FILS: Self-Supervised Video Feature Prediction In Semantic Language Space","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2407.19520","title":"Ego-VPA: Egocentric Video Understanding with Parameter-efficient Adaptation","created":"2024-07-28","cited_by_count":1,"area":null},{"id":"2408.02336","title":"Infusing Environmental Captions for Long-Form Video Language Grounding","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2411.15628","title":"ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos","created":"2024-11-23","cited_by_count":1,"area":"mllm"},{"id":"2503.13821","title":"Stitch-a-Demo: Video Demonstrations from Multistep Descriptions","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2504.08578","title":"Multimodal Knowledge Distillation for Egocentric Action Recognition Robust to Missing Modalities","created":"2025-04-11","cited_by_count":1,"area":"distill"},{"id":"2602.14837","title":"Integrating Affordances and Attention models for Short-Term Object Interaction Anticipation","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2603.25163","title":"SportSkills: Physical Skill Learning from Sports Instructional Videos","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2605.20388","title":"How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction","created":"2026-05-19","cited_by_count":1,"area":null}],"next_cursor":"100"}