Yan Xia

papers

539

total citations

papers (16)

SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud Based Place Recognition

CVPR 2021arXiv

187

citations

Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks

NEURIPS 2023arXiv

citations

L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection

AAAI 2025arXiv

citations

Extensible Prompts for Language Models on Zero-shot Language Style Customization

NEURIPS 2023arXiv

citations

Reconstructing Humans with a Biomechanically Accurate Skeleton

CVPR 2025arXiv

citations

CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving

ICCV 2025arXiv

citations

SparseAlign: a Fully Sparse Framework for Cooperative Object Detection

CVPR 2025arXiv

citations

Localizing Events in Videos with Multimodal Queries

CVPR 2025arXiv

citations

Open-set Cross Modal Generalization via Multimodal Unified Representation

ICCV 2025arXiv

citations

Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations

ICCV 2025arXiv

citations

TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes

ICCV 2025arXiv

citations

Cross-Modal Background Suppression for Audio-Visual Event Localization

CVPR 2022

citations

Achieving Cross Modal Generalization with Multimodal Unified Representation

NEURIPS 2023

citations

Yan Xia

papers (16)

SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud Based Place Recognition

Imagine While Reasoning in Space: Multimodal Visualization-of-Thought

CASSPR: Cross Attention Single Scan Place Recognition

Text2Loc: 3D Point Cloud Localization from Natural Language

Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks

L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection

Extensible Prompts for Language Models on Zero-shot Language Style Customization

Reconstructing Humans with a Biomechanically Accurate Skeleton

CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving

SparseAlign: a Fully Sparse Framework for Cooperative Object Detection

Localizing Events in Videos with Multimodal Queries

Open-set Cross Modal Generalization via Multimodal Unified Representation

Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations

TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes

Cross-Modal Background Suppression for Audio-Visual Event Localization

Achieving Cross Modal Generalization with Multimodal Unified Representation

papers (16)

SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud Based Place Recognition

Imagine While Reasoning in Space: Multimodal Visualization-of-Thought

CASSPR: Cross Attention Single Scan Place Recognition

Text2Loc: 3D Point Cloud Localization from Natural Language

Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks

L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection

Extensible Prompts for Language Models on Zero-shot Language Style Customization

Reconstructing Humans with a Biomechanically Accurate Skeleton

CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving

SparseAlign: a Fully Sparse Framework for Cooperative Object Detection

Localizing Events in Videos with Multimodal Queries

Open-set Cross Modal Generalization via Multimodal Unified Representation

Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations

TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes

Cross-Modal Background Suppression for Audio-Visual Event Localization

Achieving Cross Modal Generalization with Multimodal Unified Representation