Guo-Jun Qi

31

Papers

63

Total Citations

Papers (31)

Towards Open Domain Text-Driven Synthesis of Multi-Person Motions

Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation

OmniMotionGPT: Animal Motion Generation with Limited Data

UltrAvatar: A Realistic Animatable 3D Avatar Diffusion Model with Authenticity Guided Textures

Hierarchically Gated Deep Networks for Semantic Segmentation

Global Versus Localized Generative Adversarial Nets

Interleaved Structured Sparse Convolutional Neural Networks

AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations Rather Than Data

Task Agnostic Meta-Learning for Few-Shot Learning

Rotation Equivariant Graph Convolutional Network for Spherical Image Classification

Transformation GAN for Unsupervised Image Synthesis and Representation Learning

WCP: Worst-Case Perturbations for Semi-Supervised Deep Learning

AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations From Self-Trained Negative Adversaries

OTAvatar: One-Shot Talking Face Avatar With Controllable Tri-Plane Rendering

High-Fidelity Clothed Avatar Reconstruction From a Single Image

FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER

POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery

Differential Recurrent Neural Networks for Action Recognition

Interleaved Group Convolutions

Few-Shot Image Recognition With Knowledge Transfer

AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations

Knowledge-Enriched Distributional Model Inversion Attacks

Multitask AET With Orthogonal Tangent Regularity for Dark Object Detection

Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver

Exploring Resolution and Degradation Clues As Self-Supervised Signal for Low Quality Object Detection

GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-Wise Transformations

BARET: Balanced Attention Based Real Image Editing Driven by Target-Text Inversion

Sparse Composite Quantization

Supervised Quantization for Similarity Search

CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces

State-Frequency Memory Recurrent Neural Networks