activity
20222025
most citedDefense against Backdoor Attacks via Identifying and Purifying Bad Neurons

4 citations · 9 across the 15 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2024

ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning

Zhongjie Duan, Wenmeng Zhou, Cen Chen +2

Recently, advancements in video synthesis have attracted significant attention. Video synthesis models such as AnimateDiff and Stable Video Diffusion have demonstrated the practica…

cs.CV20241 cited

Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models

Zhongjie Duan, Chengyu Wang, Cen Chen +2

Toon shading is a type of non-photorealistic rendering task of animation. Its primary purpose is to render objects with a flat and stylized appearance. As diffusion models have asc…

cs.CV2023

FastBlend: a Powerful Model-Free Toolkit Making Video Stylization Easier

Zhongjie Duan, Chengyu Wang, Cen Chen +3

With the emergence of diffusion models and rapid development in image processing, it has become effortless to generate fancy images in tasks such as style transfer and image editin…

cs.CV20231 cited

DualToken-ViT: Position-aware Efficient Vision Transformer with Dual Token Fusion

Zhenzhen Chu, Jiayu Chen, Cen Chen +4

Self-attention-based vision transformers (ViTs) have emerged as a highly competitive architecture in computer vision. Unlike convolutional neural networks (CNNs), ViTs are capable…

cs.CV2023

DiffSynth: Latent In-Iteration Deflickering for Realistic Video Synthesis

Zhongjie Duan, Lizhou You, Chengyu Wang +4

In recent years, diffusion models have emerged as the most powerful approach in image synthesis. However, applying these models directly to video synthesis presents challenges, as…

cs.CV20232 cited

CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation

Lizhao Liu, Zhuangwei Zhuang, Shangxin Huang +5

We study the task of weakly-supervised point cloud semantic segmentation with sparse annotations (e.g., less than 0.1% points are labeled), aiming to reduce the expensive cost of d…