{"total":95,"rows":[{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161,"area":"diffusion"},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2504.15271","title":"Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models","created":"2025-04-21","cited_by_count":64,"area":"mllm"},{"id":"2406.18070","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","created":"2024-06-26","cited_by_count":44,"area":null},{"id":"2512.10863","title":"MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence","created":"2025-12-11","cited_by_count":38,"area":null},{"id":"2406.08877","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding","created":"2024-06-13","cited_by_count":36,"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":"2506.05904","title":"Proactive Assistant Dialogue Generation from Streaming Egocentric Videos","created":"2025-06-06","cited_by_count":28,"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":"2410.07177","title":"MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA","created":"2024-10-09","cited_by_count":24,"area":"mllm"},{"id":"2503.14935","title":"FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding","created":"2025-03-19","cited_by_count":24,"area":"mllm"},{"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":"2512.06810","title":"MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning","created":"2025-12-07","cited_by_count":22,"area":"mllm"},{"id":"2412.11149","title":"A Comprehensive Survey of Action Quality Assessment: Method and Benchmark","created":"2024-12-15","cited_by_count":20,"area":null},{"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":"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":"2504.11732","title":"EgoExo-Gen: Ego-centric Video Prediction by Watching Exo-centric Videos","created":"2025-04-16","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":"2407.06628","title":"Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition","created":"2024-07-09","cited_by_count":18,"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":"2511.03929","title":"NVIDIA Nemotron Nano V2 VL","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2511.20186","title":"Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis","created":"2025-11-25","cited_by_count":15,"area":null},{"id":"2512.16842","title":"OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction","created":"2025-12-18","cited_by_count":15,"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":"2510.23981","title":"TeleEgo: Benchmarking Egocentric AI Assistants in the Wild","created":"2025-10-28","cited_by_count":11,"area":null},{"id":"2512.09327","title":"UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking","created":"2025-12-10","cited_by_count":11,"area":null},{"id":"2602.14122","title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","created":"2026-02-15","cited_by_count":11,"area":"mllm"},{"id":"2410.06195","title":"EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective","created":"2024-10-08","cited_by_count":10,"area":null},{"id":"2512.13674","title":"Towards Interactive Intelligence for Digital Humans","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2410.19989","title":"On-Robot Reinforcement Learning with Goal-Contrastive Rewards","created":"2024-10-25","cited_by_count":8,"area":"deeprl"},{"id":"2411.16761","title":"Is 'Right' Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning","created":"2024-11-24","cited_by_count":8,"area":"mllm"},{"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":"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":"2506.06277","title":"ExAct: A Video-Language Benchmark for Expert Action Analysis","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2603.05484","title":"Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline","created":"2026-03-05","cited_by_count":8,"area":"agents"},{"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":"2502.02817","title":"A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2410.20621","title":"Egocentric and Exocentric Methods: A Short Survey","created":"2024-10-27","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":"2411.17130","title":"TechCoach: Towards Technical-Point-Aware Descriptive Action Coaching","created":"2024-11-26","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":"2505.08665","title":"SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimation","created":"2025-05-13","cited_by_count":6,"area":null},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2506.04996","title":"PATS: Proficiency-Aware Temporal Sampling for Multi-View Sports Skill Assessment","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2509.02949","title":"ProMQA-Assembly: Multimodal Procedural QA Dataset on Assembly","created":"2025-09-03","cited_by_count":5,"area":null},{"id":"2510.26113","title":"EgoExo-Con: Exploring View-Invariant Video Temporal Understanding","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2603.09827","title":"MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents","created":"2026-03-10","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":"2501.05711","title":"From My View to Yours: Learning Egocentric Cues from Exocentric Video using Privileged Egocentric Supervision","created":"2025-01-10","cited_by_count":4,"area":"mllm"},{"id":"2506.06631","title":"PhysLab: A Benchmark Dataset for Multi-Granularity Visual Parsing of Physics Experiments","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2509.26278","title":"ProfVLM: A lightweight video-language model for multi-view proficiency estimation","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"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":"2602.20597","title":"Interaction-aware Representation Modeling with Co-occurrence Consistency for Egocentric Hand-Object Parsing","created":"2026-02-24","cited_by_count":4,"area":null},{"id":"2606.08615","title":"Harnessing Streaming Video in the Wild","created":"2026-06-07","cited_by_count":4,"area":"mllm"},{"id":"2407.09503","title":"PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos","created":"2024-06-14","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":"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":"2505.24389","title":"Leadership Assessment in Pediatric Intensive Care Unit Team Training","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2605.07299","title":"EgoPro-Bench: Benchmarking Personalized Proactive Interaction in Egocentric Video Streams","created":"2026-05-08","cited_by_count":3,"area":"mllm"},{"id":"2605.10936","title":"Personal Visual Context Learning in Large Multimodal Models","created":"2026-05-11","cited_by_count":3,"area":"mllm"},{"id":"2607.29401","title":"OSEF: One-Step Evidence Fusion for Cross-Video Scene Procedure Planning","created":"2026-07-31","cited_by_count":3,"area":null},{"id":"2405.12789","title":"Anticipating Object State Changes in Long Procedural Videos","created":"2024-05-21","cited_by_count":2,"area":null},{"id":"2505.06557","title":"Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining","created":"2025-05-10","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":"2506.01353","title":"EgoBrain: Synergizing Minds and Eyes For Human Action Understanding","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2508.00374","title":"Bidirectional Action Sequence Learning for Long-term Action Anticipation with Large Language Models","created":"2025-08-01","cited_by_count":2,"area":null},{"id":"2603.09798","title":"Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2603.14252","title":"MistExit: Learning to Exit for Early Mistake Detection in Procedural Videos","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2409.20469","title":"PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkit","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2511.18127","title":"SFHand: Learning Embodied Manipulation by Streaming Egocentric 3D Hand Forecasting","created":"2025-11-22","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":"2604.13793","title":"From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2606.25317","title":"ESTANet: Efficient Online Error Detection in Procedural Videos via Prediction Inconsistency","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.02991","title":"GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video","created":"2026-07-03","cited_by_count":1,"area":"mllm"},{"id":"2411.15557","title":"Semantically Guided Action Anticipation","created":"2024-11-23","cited_by_count":0,"area":null},{"id":"2504.02512","title":"Towards Generalizing Temporal Action Segmentation to Unseen Views","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2510.20285","title":"DMC$^3$: Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.09894","title":"EgoEMS: A High-Fidelity Multimodal Egocentric Dataset for Cognitive Assistance in Emergency Medical Services","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2512.07474","title":"Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels","created":"2025-12-08","cited_by_count":0,"area":"agents"},{"id":"2512.07668","title":"EgoCampus: Egocentric Pedestrian Eye Gaze Model and Dataset","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2512.11393","title":"The N-Body Problem: Parallel Execution from Single-Person Egocentric Video","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2601.01818","title":"Robust Egocentric Visual Attention Prediction Through Language-guided Scene Context-aware Learning","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2601.20661","title":"ProSkill: Segment-Level Skill Assessment in Procedural Videos","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2603.22321","title":"From Instructions to Assistance: a Dataset Aligning Instruction Manuals with Assembly Videos for Evaluating Multimodal LLMs","created":"2026-03-20","cited_by_count":0,"area":"mllm"},{"id":"2603.26400","title":"SHANDS: A Multi-View Dataset and Benchmark for Surgical Hand-Gesture and Error Recognition Toward Medical Training","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.23803","title":"Bringing a Personal Point of View: Evaluating Dynamic 3D Gaussian Splatting for Egocentric Scene Reconstruction","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2607.15890","title":"Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.25736","title":"Moving Beyond More Views: Redundancy-Aware Ego-Exo Fusion for Proficiency Estimation","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.23492","title":"CE$^4$L: Continual Ego, Exo, and Ego-Exo Learning","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.35368","title":"Ego-Forge: Text and Geometric-Attention Free Exo-to-Egocentric Video Generation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.03099","title":"Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04506","title":"EgoExo-Next:Benchmarking Vision-Language Models on Visual-Option Next-State and Cross-View Reasoning","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}