CV

Download CV (PDF) (coming soon)

Education

• Ph.D in Computer Science, University of Technology Sydney, Australia, 2021. Supervised by Prof. Yi Yang.
• B.S. in Electronic and Information Engineering, University of Science and Technology of China, 2018.

Publications

H²FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-domain Weakly Supervised Object Detection

In-N-Out Generative Learning for Dense Unsupervised Video Segmentation

Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation

Decompose to Generalize: Species-Generalized Animal Pose Estimation

ProD: Prompting-to-disentangle Domain Knowledge for Cross-domain Few-shot Image Classification

Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation

FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation

Co-Learning Meets Stitch-Up for Noisy Multi-Label Visual Recognition

Pyramid Diffusion Models For Low-light Image Enhancement

Video Object Segmentation in Panoptic Wild Scenes

Segment and Track Anything

JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery

TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering

Efficient Emotional Adaptation for Audio-driven Talking-Head Generation

Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation

Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion

GD²-NeRF: Generative Detail Compensation via GAN and Diffusion for One-shot Generalizable Neural Radiance Fields

Human101: Training 100+ FPS Human Gaussians in 100s from 1 View

SEEAvatar: Photorealistic Text-to-3D Avatar Generation with Constrained Geometry and Appearance

SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction

HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting

DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting

Few-shot Incremental Learning via Foreground Aggregation and Knowledge Transfer for Audio-Visual Semantic Segmentation

Few-shot Incremental Learning via Foreground Aggregation and Knowledge Transfer for Audio-Visual Semantic Segmentation

Very Long Natural Scenery Image Prediction by Outpainting

Gated Channel Transformation for Visual Recognition

Collaborative Video Object Segmentation by Foreground-Background Integration

DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistency

Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration

Associating Objects with Transformers for Video Object Segmentation

Decoupling Features in Hierarchical Propagation for Video Object Segmentation

Controllable 3D Face Generation with Conditional Style Code Diffusion

Scalable Video Object Segmentation with Identification Mechanism

DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)

MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis

Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge

3DIS: Depth-driven decoupled instance synthesis for text-to-image generation

DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models

Insert Anything: Image Insertion via In-Context Editing in DiT

In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

MedSAM2: Segment Anything in 3D Medical Images and Videos

CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation

Service and leadership

• Currently signed in to 43 different slack teams