Chongyang Zhong
YOU?
Author Swipe
View article: AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation
AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation Open
Recently, large-scale generative models have demonstrated outstanding text-to-image generation capabilities. However, generating high-fidelity personalized images with specific subjects still presents challenges, especially in cases involv…
View article: VirtualModel: Generating Object-ID-retentive Human-object Interaction Image by Diffusion Model for E-commerce Marketing
VirtualModel: Generating Object-ID-retentive Human-object Interaction Image by Diffusion Model for E-commerce Marketing Open
Due to the significant advances in large-scale text-to-image generation by diffusion model (DM), controllable human image generation has been attracting much attention recently. Existing works, such as Controlnet [36], T2I-adapter [20] and…
View article: Multi‐Interface Engineering of Self‐Supported Nickel/Yttrium Oxide Electrode Enables Kinetically Accelerated and Ultra‐Stable Alkaline Hydrogen Evolution at Industrial‐Level Current Density
Multi‐Interface Engineering of Self‐Supported Nickel/Yttrium Oxide Electrode Enables Kinetically Accelerated and Ultra‐Stable Alkaline Hydrogen Evolution at Industrial‐Level Current Density Open
The development of highly active and robust non‐noble‐metal electrocatalysts for alkaline hydrogen evolution reaction (HER) at industrial‐level current density is the key for industrialization of alkaline water electrolysis. Herein, a supe…
View article: AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism
AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism Open
Generating 3D human motion based on textual descriptions has been a research focus in recent years. It requires the generated motion to be diverse, natural, and conform to the textual description. Due to the complex spatio-temporal nature …
View article: Unpaired Multi-domain Attribute Translation of 3D Facial Shapes with a Square and Symmetric Geometric Map
Unpaired Multi-domain Attribute Translation of 3D Facial Shapes with a Square and Symmetric Geometric Map Open
While impressive progress has recently been made in image-oriented facial attribute translation, shape-oriented 3D facial attribute translation remains an unsolved issue. This is primarily limited by the lack of 3D generative models and in…
View article: Pose-Aware Attention Network for Flexible Motion Retargeting by Body Part
Pose-Aware Attention Network for Flexible Motion Retargeting by Body Part Open
Motion retargeting is a fundamental problem in computer graphics and computer vision. Existing approaches usually have many strict requirements, such as the source-target skeletons needing to have the same number of joints or share the sam…
View article: Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction
Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction Open
Predicting future motion based on historical motion sequence is a fundamental problem in computer vision, and it has wide applications in autonomous driving and robotics. Some recent works have shown that Graph Convolutional Networks(GCN) …
View article: Emodin reverses 5-Fu resistance in human colorectal cancer via downregulation of PI3K/Akt signaling pathway.
Emodin reverses 5-Fu resistance in human colorectal cancer via downregulation of PI3K/Akt signaling pathway. Open
Our research revealed that emodin could reverse 5-Fu resistance in CRC through inactivating PI3K/Akt signaling pathway in vitro and in vivo. Thus, this finding might provide a molecular basis for treating 5-Fu resistant CRC.