Cover Image

HumanNet: Scaling Human-centric Video Learning to One Million Hours

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Deng, Yufan, Zhou, Daquan
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rethinking Video Generation Model for the Embodied World
by: Deng, Yufan, et al.
Published: (2026)

StableVLA: Towards Robust Vision-Language-Action Models without Extra Data
by: Fu, Yiyang, et al.
Published: (2026)

Robot Learning from Human Videos: A Survey
by: Ma, Junyi, et al.
Published: (2026)

You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations
by: Zhou, Huayi, et al.
Published: (2025)

CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos
by: Zhang, Chubin, et al.
Published: (2026)

Object-centric 3D Motion Field for Robot Learning from Human Videos
by: Yin, Zhao-Heng, et al.
Published: (2025)

CEDex: Cross-Embodiment Dexterous Grasp Generation at Scale from Human-like Contact Representations
by: Wu, Zhiyuan, et al.
Published: (2025)

UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories
by: Mei, Yanghong, et al.
Published: (2025)

From Generated Human Videos to Physically Plausible Robot Trajectories
by: Ni, James, et al.
Published: (2025)

AoE: Always-on Egocentric Human Video Collection for Embodied AI
by: Yang, Bowen, et al.
Published: (2026)

World Models for Learning Dexterous Hand-Object Interactions from Human Videos
by: Goswami, Raktim Gautam, et al.
Published: (2025)

Kimodo: Scaling Controllable Human Motion Generation
by: Rempe, Davis, et al.
Published: (2026)

UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
by: Kim, Hanjung, et al.
Published: (2025)

GLOVER++: Unleashing the Potential of Affordance Learning from Human Behaviors for Robotic Manipulation
by: Ma, Teli, et al.
Published: (2025)

Learning Priors of Human Motion With Vision Transformers
by: Falqueto, Placido, et al.
Published: (2025)

One-shot Video Imitation via Parameterized Symbolic Abstraction Graphs
by: Wang, Jianren, et al.
Published: (2024)

Slot-Level Robotic Placement via Visual Imitation from Single Human Video
by: Shan, Dandan, et al.
Published: (2025)

HumanSAM: Classifying Human-centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly
by: Liu, Chang, et al.
Published: (2025)

Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
by: Luo, Hao, et al.
Published: (2025)

HRDexDB: A Large-Scale Dataset of Dexterous Human and Robotic Hand Grasps
by: Lim, Jongbin, et al.
Published: (2026)

EgoMimic: Scaling Imitation Learning via Egocentric Video
by: Kareer, Simar, et al.
Published: (2024)

VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation
by: Chen, Hanzhi, et al.
Published: (2025)

Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning
by: Shibata, Yuto, et al.
Published: (2026)

Generate, Transfer, Adapt: Learning Functional Dexterous Grasping from a Single Human Demonstration
by: He, Xingyi, et al.
Published: (2026)

Bayesian-Optimized One-Step Diffusion Model with Knowledge Distillation for Real-Time 3D Human Motion Prediction
by: Tian, Sibo, et al.
Published: (2024)

DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos
by: Hsieh, Jhen, et al.
Published: (2025)

Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations
by: Huang, Wei-Jin, et al.
Published: (2026)

Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction
by: Chen, Hongyi, et al.
Published: (2026)

CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
by: Liu, Xinhao, et al.
Published: (2024)

VizFlyt: Perception-centric Pedagogical Framework For Autonomous Aerial Robots
by: Srivastava, Kushagra, et al.
Published: (2025)

MetricNet: Recovering Metric Scale in Generative Navigation Policies
by: Nayak, Abhijeet, et al.
Published: (2025)

HHI-Assist: A Dataset and Benchmark of Human-Human Interaction in Physical Assistance Scenario
by: Saadatnejad, Saeed, et al.
Published: (2025)

HOH: Markerless Multimodal Human-Object-Human Handover Dataset with Large Object Count
by: Wiederhold, Noah, et al.
Published: (2023)

Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos
by: Zhai, Albert J., et al.
Published: (2026)

FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulation
by: Tang, Chao, et al.
Published: (2025)

ViViDex: Learning Vision-based Dexterous Manipulation from Human Videos
by: Chen, Zerui, et al.
Published: (2024)

2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos
by: Heidinger, Marvin, et al.
Published: (2025)

AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations
by: Gong, Litian, et al.
Published: (2025)

Cosmos-H-Surgical: Learning Surgical Robot Policies from Videos via World Modeling
by: He, Yufan, et al.
Published: (2025)

Certified Human Trajectory Prediction
by: Bahari, Mohammadhossein, et al.
Published: (2024)