Ceyuan Yang


PhD Student
Department of Information Engineering
The Chinese University of Hong Kong

E-mail  /  Google Scholar  /  Github

Full Publications [Home]

*equal contribution +corresponding author
Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis,
Learning Modulated Transformation in GANs,
Revisiting the Evaluation of Image Synthesis with GANs,
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning,
One-Shot Generative Domain Adaptation,
LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis,
DiscoScene: Spatially Disentangled Generative Radiance Field for Controllable 3D-aware Scene Synthesis,
Highlight Presentation
GLeaD: Improving GANs with A Generator-Leading Task,
Towards Smooth Video Composition,
Improving GANs with A Dynamic Discriminator,
Accelerating Diffusion Models via Early Stop of the Diffusion Process,
Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation,
3D-aware Image Synthesis via Learning Structural and Textural Representations,
Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition,
Oral Presentation
Improving GAN Equilibrium by Raising Spatial Awareness,
Data-Efficient Instance Generation from Instance Discrimination,
Ceyuan Yang, Yujun Shen, Yinghao Xu, Bolei Zhou.
Instance Localization for Self-supervised Detection Pretraining,
Generative Hierarchical Features from Synthesizing Images,
Oral Presentation
Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis,
Ceyuan Yang*, Yujun Shen*, Bolei Zhou.
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs,
Yujun Shen, Ceyuan Yang, Bolei Zhou.
Learning Motion Priors for Efficient Video Object Detection,
Unsupervised Landmark Learning from Unpaired Data,
Video Representation Learning with Visual Tempo Consistency,
Ceyuan Yang, Yinghao Xu, Bo Dai, Bolei Zhou.
Temporal Pyramid Network for Action Recognition,
Adapting Object Detectors via Selective Cross-Domain Alignment,
Pose Guided Human Video Generation,
Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation,
Remote Sensing Image Scene Classification via Learning Discriminative CNNs,