Search Results - "Yang, Ceyuan"

Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis by Yang, Ceyuan, Shen, Yujun, Zhou, Bolei

“…Despite the great success of Generative Adversarial Networks (GANs) in synthesizing images, there lacks enough understanding of how photo-realistic images are…”
Get full text

When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs by Cheng, Gong, Yang, Ceyuan, Yao, Xiwen, Guo, Lei, Han, Junwei

“…Remote sensing image scene classification is an active and challenging task driven by many applications. More recently, with the advances of deep learning…”
Get full text

InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs by Shen, Yujun, Yang, Ceyuan, Tang, Xiaoou, Zhou, Bolei

“…Although generative adversarial networks (GANs) have made significant progress in face synthesis, there lacks enough understanding of what GANs have learned in…”
Get full text

Temporal Pyramid Network for Action Recognition by Yang, Ceyuan, Xu, Yinghao, Shi, Jianping, Dai, Bo, Zhou, Bolei

“…Visual tempo characterizes the dynamics and the temporal scale of an action. Modeling such visual tempos of different actions facilitates their recognition…”
Get full text

Instance Localization for Self-supervised Detection Pretraining by Yang, Ceyuan, Wu, Zhirong, Zhou, Bolei, Lin, Stephen

“…Prior research on self-supervised learning has led to considerable progress on image classification, but often with degraded transfer performance on object…”
Get full text

Generative Hierarchical Features from Synthesizing Images by Xu, Yinghao, Shen, Yujun, Zhu, Jiapeng, Yang, Ceyuan, Zhou, Bolei

“…Generative Adversarial Networks (GANs) have recently advanced image synthesis by learning the underlying distribution of the observed data. However, how the…”
Get full text

Adapting Object Detectors via Selective Cross-Domain Alignment by Zhu, Xinge, Pang, Jiangmiao, Yang, Ceyuan, Shi, Jianping, Lin, Dahua

“…State-of-the-art object detectors are usually trained on public datasets. They often face substantial difficulties when applied to a different domain, where…”
Get full text

3D-aware Image Synthesis via Learning Structural and Textural Representations by Xu, Yinghao, Peng, Sida, Yang, Ceyuan, Shen, Yujun, Zhou, Bolei

“…Making generative models 3D-aware bridges the 2D image space and the 3D physical world yet remains challenging. Recent attempts equip a Generative Adversarial…”
Get full text

GH-Feat: Learning Versatile Generative Hierarchical Features From GANs by Xu, Yinghao, Shen, Yujun, Zhu, Jiapeng, Yang, Ceyuan, Zhou, Bolei

“…Recent years witness the tremendous success of generative adversarial networks (GANs) in synthesizing photo-realistic images. GAN generator learns to compose…”
Get full text

Spatial Steerability of GANs via Self-Supervision from Discriminator by Wang, Jianyuan, Bhagat, Lalit, Yang, Ceyuan, Xu, Yinghao, Shen, Yujun, Li, Hongdong, Zhou, Bolei

“…Generative models make huge progress to the photorealistic image synthesis in recent years. To enable humans to steer the image generation process and…”
Get full text

Learning to Represent and Recreate Data by Yang, Ceyuan

“…Computer vision has been significantly advanced with the help of state-of-the-art algorithms, high-performance computing resources and the most important…”
Get full text

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition by Xu, Yinghao, Wei, Fangyun, Sun, Xiao, Yang, Ceyuan, Shen, Yujun, Dai, Bo, Zhou, Bolei, Lin, Stephen

“…Semi-supervised action recognition is a challenging but important task due to the high cost of data annotation. A common approach to this problem is to assign…”
Get full text

Improving GAN Equilibrium by Raising Spatial Awareness by Wang, Jianyuan, Yang, Ceyuan, Xu, Yinghao, Shen, Yujun, Li, Hongdong, Zhou, Bolei

“…The success of Generative Adversarial Networks (GANs) is largely built upon the adversarial training between a generator (G) and a discriminator (D). They are…”
Get full text

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis by Xu, Yinghao, Chai, Menglei, Shi, Zifan, Peng, Sida, Skorokhodov, Ivan, Siarohin, Aliaksandr, Yang, Ceyuan, Shen, Yujun, Lee, Hsin-Ying, Zhou, Bolei, Tulyakov, Sergey

“…Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene…”
Get full text

GLeaD: Improving GANs with A Generator-Leading Task by Bai, Qingyan, Yang, Ceyuan, Xu, Yinghao, Liu, Xihui, Yang, Yujiu, Shen, Yujun

“…Generative adversarial network (GAN) is formulated as a two-player game between a generator (G) and a discriminator (D), where D is asked to differentiate…”
Get full text

Scaling Laws For Diffusion Transformers by Liang, Zhengyang, He, Hao, Yang, Ceyuan, Dai, Bo

“…Diffusion transformers (DiT) have already achieved appealing synthesis and scaling properties in content recreation, e.g., image and video generation. However,…”
Get full text

GH-Feat: Learning Versatile Generative Hierarchical Features from GANs by Xu, Yinghao, Shen, Yujun, Zhu, Jiapeng, Yang, Ceyuan, Zhou, Bolei

“…Recent years witness the tremendous success of generative adversarial networks (GANs) in synthesizing photo-realistic images. GAN generator learns to compose…”
Get full text

Towards Smooth Video Composition by Zhang, Qihang, Yang, Ceyuan, Shen, Yujun, Xu, Yinghao, Zhou, Bolei

“…Video generation requires synthesizing consistent and persistent frames with dynamic content over time. This work investigates modeling the temporal relations…”
Get full text

BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation by Zhang, Qihang, Xu, Yinghao, Shen, Yujun, Dai, Bo, Zhou, Bolei, Yang, Ceyuan

“…Generating large-scale 3D scenes cannot simply apply existing 3D object synthesis technique since 3D scenes usually hold complex spatial configurations and…”
Get full text

3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting by Zhang, Qihang, Xu, Yinghao, Wang, Chaoyang, Lee, Hsin-Ying, Wetzstein, Gordon, Zhou, Bolei, Yang, Ceyuan

“…Scene image editing is crucial for entertainment, photography, and advertising design. Existing methods solely focus on either 2D individual object or 3D…”
Get full text