Xiaoyan Sun

papers

1,043

total citations

papers (21)

Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach

AAAI 2025arXiv

citations

DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene Rendering

ICCV 2025arXiv

citations

Incomplete Multi-modal Brain Tumor Segmentation via Learnable Sorting State Space Model

CVPR 2025

citations

Efficient Spiking Point Mamba for Point Cloud Analysis

ICCV 2025arXiv

citations

Exploiting Rigidity Constraints for LiDAR Scene Flow Estimation

CVPR 2022

citations

TMFormer: Token Merging Transformer for Brain Tumor Segmentation with Missing Modalities

AAAI 2024

citations

Xiaoyan Sun

papers (21)

Paint by Example: Exemplar-Based Image Editing With Diffusion Models

Tracking by Instance Detection: A Meta-Learning Approach

GET: Group Event Transformer for Event-Based Vision

Dual Progressive Prototype Network for Generalized Zero-Shot Learning

Scene Adaptive Sparse Transformer for Event-based Object Detection

MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation

Spatiotemporal Fusion in 3D CNNs: A Probabilistic View

Event-assisted Low-Light Video Object Segmentation

Image Captioning with Multi-Context Synthetic Data

Event-Adapted Video Super-Resolution

EvTexture: Event-driven Texture Enhancement for Video Super-Resolution

Spiking Point Transformer for Point Cloud Classification

Event-Enhanced Blurry Video Super-Resolution

Exploiting Dual-Correlation for Multi-frame Time-of-Flight Denoising

Panacea: Panoramic and Controllable Video Generation for Autonomous Driving

Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach

DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene Rendering

Incomplete Multi-modal Brain Tumor Segmentation via Learnable Sorting State Space Model

Efficient Spiking Point Mamba for Point Cloud Analysis

Exploiting Rigidity Constraints for LiDAR Scene Flow Estimation

TMFormer: Token Merging Transformer for Brain Tumor Segmentation with Missing Modalities

papers (21)

Paint by Example: Exemplar-Based Image Editing With Diffusion Models

Tracking by Instance Detection: A Meta-Learning Approach

GET: Group Event Transformer for Event-Based Vision

Dual Progressive Prototype Network for Generalized Zero-Shot Learning

Scene Adaptive Sparse Transformer for Event-based Object Detection

MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation

Spatiotemporal Fusion in 3D CNNs: A Probabilistic View

Event-assisted Low-Light Video Object Segmentation

Image Captioning with Multi-Context Synthetic Data

Event-Adapted Video Super-Resolution

EvTexture: Event-driven Texture Enhancement for Video Super-Resolution

Spiking Point Transformer for Point Cloud Classification

Event-Enhanced Blurry Video Super-Resolution

Exploiting Dual-Correlation for Multi-frame Time-of-Flight Denoising

Panacea: Panoramic and Controllable Video Generation for Autonomous Driving

Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach

DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene Rendering

Incomplete Multi-modal Brain Tumor Segmentation via Learnable Sorting State Space Model

Efficient Spiking Point Mamba for Point Cloud Analysis

Exploiting Rigidity Constraints for LiDAR Scene Flow Estimation

TMFormer: Token Merging Transformer for Brain Tumor Segmentation with Missing Modalities