Yandong Guo

papers

1,473

total citations

papers (22)

CRIS: CLIP-Driven Referring Image Segmentation

CVPR 2022arXiv

462

citations

Structured Local Radiance Fields for Human Avatar Modeling

CVPR 2022arXiv

132

citations

LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding

AAAI 2025arXiv

116

citations

Discriminative Multi-Modality Speech Recognition

CVPR 2020arXiv

113

citations

PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

CVPR 2023arXiv

citations

Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning

CVPR 2023arXiv

citations

BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks

CVPR 2023arXiv

citations

Adaptive Patch Exiting for Scalable Single Image Super-Resolution

ECCV 2022arXiv

citations

CloSET: Modeling Clothed Humans on Continuous Surface With Explicit Template Decomposition

CVPR 2023arXiv

citations

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation

CVPR 2024arXiv

citations

Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning

NEURIPS 2025

citations

Box-Level Active Detection

CVPR 2023arXiv

citations

Efficient Meta-Tuning for Content-Aware Neural Video Delivery

ECCV 2022arXiv

citations

CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network With Large Input

CVPR 2023arXiv

citations

NTO3D: Neural Target Object 3D Reconstruction with Segment Anything

CVPR 2024arXiv

citations

Debiased Novel Category Discovering and Localization

AAAI 2024arXiv

citations

Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction

ICCV 2021arXiv

citations

Single-Stage Is Enough: Multi-Person Absolute 3D Pose Estimation

CVPR 2022

citations

Neural Reconstruction of Relightable Human Model from Monocular Video

ICCV 2023

citations

Yandong Guo

papers (22)

CRIS: CLIP-Driven Referring Image Segmentation

Structured Local Radiance Fields for Human Avatar Modeling

LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding

Discriminative Multi-Modality Speech Recognition

PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

View-Guided Point Cloud Completion

Personalized Image Aesthetics Assessment With Rich Attributes

Self-Distillation From the Last Mini-Batch for Consistency Regularization

Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning

BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks

Adaptive Patch Exiting for Scalable Single Image Super-Resolution

CloSET: Modeling Clothed Humans on Continuous Surface With Explicit Template Decomposition

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation

Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning

Box-Level Active Detection

Efficient Meta-Tuning for Content-Aware Neural Video Delivery

CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network With Large Input

NTO3D: Neural Target Object 3D Reconstruction with Segment Anything

Debiased Novel Category Discovering and Localization

Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction

Single-Stage Is Enough: Multi-Person Absolute 3D Pose Estimation

Neural Reconstruction of Relightable Human Model from Monocular Video

papers (22)

CRIS: CLIP-Driven Referring Image Segmentation

Structured Local Radiance Fields for Human Avatar Modeling

LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding

Discriminative Multi-Modality Speech Recognition

PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

View-Guided Point Cloud Completion

Personalized Image Aesthetics Assessment With Rich Attributes

Self-Distillation From the Last Mini-Batch for Consistency Regularization

Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning

BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks

Adaptive Patch Exiting for Scalable Single Image Super-Resolution

CloSET: Modeling Clothed Humans on Continuous Surface With Explicit Template Decomposition

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation

Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning

Box-Level Active Detection

Efficient Meta-Tuning for Content-Aware Neural Video Delivery

CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network With Large Input

NTO3D: Neural Target Object 3D Reconstruction with Segment Anything

Debiased Novel Category Discovering and Localization

Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction

Single-Stage Is Enough: Multi-Person Absolute 3D Pose Estimation

Neural Reconstruction of Relightable Human Model from Monocular Video