Wenliang Zhao

16

Papers

68

Total Citations

Papers (16)

FlowIE: Efficient Image Enhancement via Rectified Flow

DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers

DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation

FADE: Frequency-Aware Diffusion Model Factorization for Video Editing

Unleashing Text-to-Image Diffusion Models for Visual Perception

AMixer: Adaptive Weight Mixing for Self-Attention Free Vision Transformers

Group-Aware Contrastive Regression for Action Quality Assessment

DenseCLIP: Language-Guided Dense Prediction With Context-Aware Prompting

DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation

DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion

Towards Interpretable Deep Metric Learning With Structural Matching

Global Filter Networks for Image Classification

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

NeurIPS 2021arXiv

HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions

UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models