Yanchao Yang

papers

1,574

total citations

papers (20)

Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization

CVPR 2025arXiv

citations

Learning to Manipulate Individual Objects in an Image

CVPR 2020arXiv

citations

Learning Semantic-Aware Dynamics for Video Prediction

CVPR 2021arXiv

citations

VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization

CVPR 2023arXiv

citations

JacobiNeRF: NeRF Shaping With Mutual Information Gradients

CVPR 2023arXiv

citations

SpOT: Spatiotemporal Modeling for 3D Object Tracking

ECCV 2022arXiv

citations

InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization

ICML 2024arXiv

citations

HuMoCon: Concept Discovery for Human Motion Understanding

CVPR 2025arXiv

citations

COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos

ICCV 2023arXiv

citations

DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping

CVPR 2021arXiv

citations

MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery

ECCV 2024arXiv

citations

$\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks

NEURIPS 2025

citations

Structure-Aware Surface Reconstruction via Primitive Assembly

ICCV 2023

citations

ADeLA: Automatic Dense Labeling With Attention for Viewpoint Shift in Semantic Segmentation

CVPR 2022

citations

Gaze-VLM: Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding

NEURIPS 2025

citations

Yanchao Yang

papers (20)

FDA: Fourier Domain Adaptation for Semantic Segmentation

Phase Consistent Ecological Domain Adaptation

GIMO: Gaze-Informed Human Motion Prediction in Context

SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos

Domain Adaptation on Point Clouds via Geometry-Aware Implicits

Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization

Learning to Manipulate Individual Objects in an Image

Learning Semantic-Aware Dynamics for Video Prediction

VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization

JacobiNeRF: NeRF Shaping With Mutual Information Gradients

SpOT: Spatiotemporal Modeling for 3D Object Tracking

InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization

HuMoCon: Concept Discovery for Human Motion Understanding

COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos

DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping

MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery

$\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks

Structure-Aware Surface Reconstruction via Primitive Assembly

ADeLA: Automatic Dense Labeling With Attention for Viewpoint Shift in Semantic Segmentation

Gaze-VLM: Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding

papers (20)

FDA: Fourier Domain Adaptation for Semantic Segmentation

Phase Consistent Ecological Domain Adaptation

GIMO: Gaze-Informed Human Motion Prediction in Context

SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos

Domain Adaptation on Point Clouds via Geometry-Aware Implicits

Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization

Learning to Manipulate Individual Objects in an Image

Learning Semantic-Aware Dynamics for Video Prediction

VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization

JacobiNeRF: NeRF Shaping With Mutual Information Gradients

SpOT: Spatiotemporal Modeling for 3D Object Tracking

InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization

HuMoCon: Concept Discovery for Human Motion Understanding

COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos

DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping

MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery

$\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks

Structure-Aware Surface Reconstruction via Primitive Assembly

ADeLA: Automatic Dense Labeling With Attention for Viewpoint Shift in Semantic Segmentation

Gaze-VLM: Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding