{"total":69,"rows":[{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99,"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":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","cited_by_count":81,"area":null},{"id":"2103.03433","title":"Goal-Oriented Gaze Estimation for Zero-Shot Learning","created":"2021-03-05","cited_by_count":68,"area":null},{"id":"2402.16117","title":"RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis","created":"2024-02-25","cited_by_count":58,"area":null},{"id":"2208.04464","title":"In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation","created":"2022-08-08","cited_by_count":51,"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":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36,"area":null},{"id":"2207.05515","title":"Compound Prototype Matching for Few-shot Action Recognition","created":"2022-07-12","cited_by_count":35,"area":null},{"id":"2303.14644","title":"Affordance Grounding from Demonstration Video to Target Image","created":"2023-03-26","cited_by_count":34,"area":null},{"id":"2108.05675","title":"Learning Visual Affordance Grounding from Demonstration Videos","created":"2021-08-12","cited_by_count":25,"area":null},{"id":"2312.04817","title":"LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering","created":"2023-12-08","cited_by_count":25,"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":"2208.13196","title":"Grounded Affordance from Exocentric View","created":"2022-08-28","cited_by_count":22,"area":null},{"id":"2112.08189","title":"ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery","created":"2021-12-10","cited_by_count":20,"area":null},{"id":"2305.03907","title":"Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation","created":"2023-05-06","cited_by_count":20,"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":"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":"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":"2303.16024","title":"Egocentric Auditory Attention Localization in Conversations","created":"2023-03-28","cited_by_count":18,"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":"2303.16292","title":"XAIR: A Framework of Explainable AI in Augmented Reality","created":"2023-03-28","cited_by_count":17,"area":null},{"id":"2302.03292","title":"Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos","created":"2023-02-07","cited_by_count":15,"area":null},{"id":"2406.08379","title":"Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities","created":"2024-06-12","cited_by_count":15,"area":null},{"id":"2409.06210","title":"INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding","created":"2024-09-10","cited_by_count":12,"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":"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":"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":"2506.23088","title":"Where, What, Why: Towards Explainable Driver Attention Prediction","created":"2025-06-29","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":"2506.07886","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","created":"2025-06-09","cited_by_count":9,"area":null},{"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":"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":"2103.04019","title":"Indoor Future Person Localization from an Egocentric Wearable Camera","created":"2021-03-06","cited_by_count":5,"area":null},{"id":"2112.01034","title":"Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data","created":"2021-12-02","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":"2112.01038","title":"Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips","created":"2021-12-02","cited_by_count":4,"area":null},{"id":"2510.17384","title":"Closed-Loop Transfer for Weakly-supervised Affordance Grounding","created":"2025-10-20","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":"2203.13166","title":"Self-supervised Video-centralised Transformer for Video Face Clustering","created":"2022-03-24","cited_by_count":3,"area":null},{"id":"2312.14154","title":"Virtual Pets: Animatable Animal Generation in 3D Scenes","created":"2023-12-21","cited_by_count":3,"area":null},{"id":"2404.07351","title":"A Transformer-Based Model for the Prediction of Human Gaze Behavior on Videos","created":"2024-04-10","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":"2310.05511","title":"Proposal-based Temporal Action Localization with Point-level Supervision","created":"2023-10-09","cited_by_count":2,"area":null},{"id":"2501.13878","title":"Eye Gaze as a Signal for Conveying User Attention in Contextual AI Systems","created":"2025-01-23","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":"2511.18470","title":"Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2203.04752","title":"Human Gaze Guided Attention for Surgical Activity Recognition","created":"2022-03-09","cited_by_count":1,"area":null},{"id":"2405.02929","title":"Unified Dynamic Scanpath Predictors Outperform Individually Trained Neural Models","created":"2024-05-05","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":"2602.05132","title":"ARGaze: Autoregressive Transformers for Online Egocentric Gaze Estimation","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2105.09544","title":"Egocentric Activity Recognition and Localization on a 3D Map","created":"2021-05-20","cited_by_count":0,"area":null},{"id":"2206.05424","title":"Precise Affordance Annotation for Egocentric Action Video Datasets","created":"2022-06-11","cited_by_count":0,"area":null},{"id":"2502.18123","title":"Personalized Federated Learning for Egocentric Video Gaze Estimation with Comprehensive Parameter Frezzing","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2503.07828","title":"Neural Radiance and Gaze Fields for Visual Attention Modeling in 3D Environments","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2510.10742","title":"Seeing My Future: Predicting Situated Interaction Behavior in Virtual Reality","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2511.02468","title":"HAGI++: Head-Assisted Gaze Imputation and Generation","created":"2025-11-04","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":"2602.11669","title":"Egocentric Gaze Estimation via Neck-Mounted Camera","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.04098","title":"Real Eyes Realize Faster: Gaze Stability and Pupil Novelty for Efficient Egocentric Learning","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2607.01437","title":"How Much Future Helps? A Controlled Study of Future-Privileged Supervision for Causal Egocentric Gaze Estimation","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.04017","title":"SAGE: Synchronized Action-Gaze Recognition and Anticipation for Human Behavior Understanding","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.08929","title":"Zero-shot 2D Grounding with Novel Affordance Types","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2609.38519","title":"GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}