Xiaohua Xie

papers

673

total citations

papers (26)

Self-Supervised Image-Specific Prototype Exploration for Weakly Supervised Semantic Segmentation

CVPR 2022arXiv

179

citations

CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution

ICCV 2023arXiv

citations

The Enemy of My Enemy Is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training

CVPR 2023arXiv

citations

View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network

CVPR 2024arXiv

citations

LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models

CVPR 2025arXiv

citations

MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation

AAAI 2024arXiv

citations

Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis

ICCV 2025arXiv

citations

Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models

CVPR 2024arXiv

citations

ViSpeak: Visual Instruction Feedback in Streaming Videos

ICCV 2025arXiv

citations

Formulating Discrete Probability Flow Through Optimal Transport

NEURIPS 2023arXiv

citations

Unsupervised Group Re-identification via Adaptive Clustering-Driven Progressive Learning

AAAI 2024

citations

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

ICCV 2023arXiv

citations

Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners

CVPR 2024

citations

GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting

CVPR 2025arXiv

citations

Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking

CVPR 2025arXiv

citations

Spike-Temporal Latent Representation for Energy-Efficient Event-to-Video Reconstruction

ECCV 2024

citations

Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation

ICCV 2025arXiv

citations

SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation

ICCV 2025arXiv

citations

Training-Free Class Purification for Open-Vocabulary Semantic Segmentation

ICCV 2025arXiv

citations

Modeling 3D Layout for Group Re-Identification

CVPR 2022

citations

Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection

CVPR 2020

citations

Improving Adversarially Robust Few-Shot Image Classification With Generalizable Representations

CVPR 2022

citations

MMA: Multi-Modal Adapter for Vision-Language Models

CVPR 2024

citations

Xiaohua Xie

papers (26)

Self-Supervised Image-Specific Prototype Exploration for Weakly Supervised Semantic Segmentation

Exploring Dual-Task Correlation for Pose Guided Person Image Generation

Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis

Texture-Guided Saliency Distilling for Unsupervised Salient Object Detection

CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution

The Enemy of My Enemy Is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training

View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network

LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models

MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation

Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis

Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models

ViSpeak: Visual Instruction Feedback in Streaming Videos

Formulating Discrete Probability Flow Through Optimal Transport

Unsupervised Group Re-identification via Adaptive Clustering-Driven Progressive Learning

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners

GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting

Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking

Spike-Temporal Latent Representation for Energy-Efficient Event-to-Video Reconstruction

Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation

SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation

Training-Free Class Purification for Open-Vocabulary Semantic Segmentation

Modeling 3D Layout for Group Re-Identification

Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection

Improving Adversarially Robust Few-Shot Image Classification With Generalizable Representations

MMA: Multi-Modal Adapter for Vision-Language Models

papers (26)

Self-Supervised Image-Specific Prototype Exploration for Weakly Supervised Semantic Segmentation

Exploring Dual-Task Correlation for Pose Guided Person Image Generation

Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis

Texture-Guided Saliency Distilling for Unsupervised Salient Object Detection

CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution

The Enemy of My Enemy Is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training

View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network

LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models

MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation

Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis

Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models

ViSpeak: Visual Instruction Feedback in Streaming Videos

Formulating Discrete Probability Flow Through Optimal Transport

Unsupervised Group Re-identification via Adaptive Clustering-Driven Progressive Learning

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners

GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting

Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking

Spike-Temporal Latent Representation for Energy-Efficient Event-to-Video Reconstruction

Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation

SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation

Training-Free Class Purification for Open-Vocabulary Semantic Segmentation

Modeling 3D Layout for Group Re-Identification

Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection

Improving Adversarially Robust Few-Shot Image Classification With Generalizable Representations

MMA: Multi-Modal Adapter for Vision-Language Models