Xiaohua Xie

16

Papers

197

Total Citations

Papers (16)

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

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

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

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

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

ViSpeak: Visual Instruction Feedback in Streaming Videos

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

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

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

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

GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting

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

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

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

MMA: Multi-Modal Adapter for Vision-Language Models

Training-Free Class Purification for Open-Vocabulary Semantic Segmentation