Na Zhao

papers

533

total citations

papers (19)

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation

ECCV 2022arXiv

146

citations

Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image

ECCV 2024arXiv

citations

MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm

ICCV 2025arXiv

citations

Generalized Few-Shot Point Cloud Segmentation via Geometric Words

ICCV 2023arXiv

citations

AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring

AAAI 2025arXiv

citations

Dual-Perspective Knowledge Enrichment for Semi-supervised 3D Object Detection

AAAI 2024arXiv

citations

Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation

ICCV 2025arXiv

citations

AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models

NEURIPS 2025arXiv

citations

H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction

ICCV 2025arXiv

citations

Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection

CVPR 2025arXiv

citations

Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration

CVPR 2025

citations

Robust Visual Recognition with Class-Imbalanced Open-World Noisy Data

AAAI 2024

citations

Provably Secure Image Robust Steganography via Cross-modal Error Correction

AAAI 2025

citations

LASO: Language-guided Affordance Segmentation on 3D Object

CVPR 2024

citations

Geometric Alignment and Prior Modulation for View-Guided Point Cloud Completion on Unseen Categories

ICCV 2025

citations

Teaching with Soft Label Smoothing for Mitigating Noisy Labels in Facial Expressions

ECCV 2022

citations

Na Zhao

papers (19)

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation

SESS: Self-Ensembling Semi-Supervised 3D Object Detection

Few-Shot 3D Point Cloud Semantic Segmentation

Rethinking IoU-Based Optimization for Single-Stage 3D Object Detection

Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image

MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm

Generalized Few-Shot Point Cloud Segmentation via Geometric Words

AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring

Dual-Perspective Knowledge Enrichment for Semi-supervised 3D Object Detection

Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation

AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models

H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction

Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection

Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration

Robust Visual Recognition with Class-Imbalanced Open-World Noisy Data

Provably Secure Image Robust Steganography via Cross-modal Error Correction

LASO: Language-guided Affordance Segmentation on 3D Object

Geometric Alignment and Prior Modulation for View-Guided Point Cloud Completion on Unseen Categories

Teaching with Soft Label Smoothing for Mitigating Noisy Labels in Facial Expressions

papers (19)

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation

SESS: Self-Ensembling Semi-Supervised 3D Object Detection

Few-Shot 3D Point Cloud Semantic Segmentation

Rethinking IoU-Based Optimization for Single-Stage 3D Object Detection

Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image

MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm

Generalized Few-Shot Point Cloud Segmentation via Geometric Words

AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring

Dual-Perspective Knowledge Enrichment for Semi-supervised 3D Object Detection

Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation

AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models

H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction

Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection

Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration

Robust Visual Recognition with Class-Imbalanced Open-World Noisy Data

Provably Secure Image Robust Steganography via Cross-modal Error Correction

LASO: Language-guided Affordance Segmentation on 3D Object

Geometric Alignment and Prior Modulation for View-Guided Point Cloud Completion on Unseen Categories

Teaching with Soft Label Smoothing for Mitigating Noisy Labels in Facial Expressions