Na Zhao

13

Papers

40

Total Citations

Papers (13)

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

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

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

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

LASO: Language-guided Affordance Segmentation on 3D Object

Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration

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

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

Provably Secure Image Robust Steganography via Cross-modal Error Correction

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