Yuan Gao

33

Papers

94

Total Citations

Papers (33)

OneRestore: A Universal Restoration Framework for Composite Degradation

Enhancing Vision-Language Pre-training with Rich Supervisions

Anchor-based Robust Finetuning of Vision-Language Models

On the Convergence of Tâtonnement for Linear Fisher Markets

Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation

SD2Event:Self-supervised Learning of Dynamic Detectors and Contextual Descriptors for Event Cameras

Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation

Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding

DMTG: One-Shot Differentiable Multi-Task Grouping

Non-convex Stochastic Composite Optimization with Polyak Momentum

Efficient Denoising Diffusion via Probabilistic Masking

Exploiting Symmetry and/or Manhattan Properties for 3D Object Structure Estimation From Single and Multiple Images

NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction

Face Anti-Spoofing: Model Matters, so Does Data

MTL-NAS: Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task Learning

Semi-Supervised Video Semantic Segmentation With Inter-Frame Feature Reconstruction

Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap

D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers

Temporal Cue Guided Video Highlight Detection With Low-Rank Audio-Visual Fusion

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation

Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement

DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion

ProbMED: A Probabilistic Framework for Medical Multimodal Binding

Bridging Class Imbalance and Partial Labeling via Spectral-Balanced Energy Propagation for Skeleton-based Action Recognition

Locality Preserving Refinement for Shape Matching with Functional Maps

DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning

An Improved Analysis of Stochastic Gradient Descent with Momentum

First-Order Methods for Large-Scale Market Equilibrium Computation

Online Market Equilibrium with Application to Fair Division

Nonstationary Dual Averaging and Online Fair Allocation

Inferring Hybrid Neural Fluid Fields from Videos

Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis

Deep Generative Learning via Variational Gradient Flow