Jianfeng Lu

21

Papers

4

Total Citations

Papers (21)

Multi-Label Test-Time Adaptation with Bound Entropy Minimization

TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning

FedCross: Intertemporal Federated Learning Under Evolutionary Games

Enhanced Fine-Grained Motion Diffusion for Text-Driven Human Motion Synthesis

Fast Adaptation for Human Pose Estimation via Meta-Optimization

MoML: Online Meta Adaptation for 3D Human Motion Prediction

Mind Your Neighbours: Image Annotation With Metadata Neighbourhood Graph Co-Attention Networks

Robust Single Image Reflection Removal Against Adversarial Attacks

DeFeeNet: Consecutive 3D Human Motion Prediction With Deviation Feedback

Test-time Personalizable Forecasting of 3D Human Poses

Gait Recognition from a Single Image using a Phase-Aware Gait Cycle Reconstruction Network

Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction

Consistency Posterior Sampling for Diverse Image Synthesis

A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions

MPNet: Masked and Permuted Pre-training for Language Understanding

On the Representation of Solutions to Elliptic PDEs in Barron Spaces

Convergence for score-based generative modeling with polynomial complexity

Deep Equilibrium Based Neural Operators for Steady-State PDEs

The probability flow ODE is provably fast

Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization

MASS: Masked Sequence to Sequence Pre-training for Language Generation