Chengming Xu

Orcid: 0000-0003-3891-2227

Affiliations:
  • Tencent, Youtu Lab, Shenzhen, China
  • Fudan University, School of Data Science, Shanghai, China


According to our database1, Chengming Xu authored at least 39 papers between 2018 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
From Large Angles to Consistent Faces: Identity-Preserving Video Generation via Mixture of Facial Experts.
CoRR, August, 2025

SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment.
CoRR, August, 2025

StrandDesigner: Towards Practical Strand Generation with Sketch Guidance.
CoRR, August, 2025

Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation.
CoRR, April, 2025

When Preferences Diverge: Aligning Diffusion Models with Minority-Aware Adaptive DPO.
CoRR, March, 2025

CrossVTON: Mimicking the Logic Reasoning on Cross-category Virtual Try-on guided by Tri-zone Priors.
CoRR, February, 2025

MagicFace: Slot-Driven High-Fidelity One-Shot Facial Appearance Editing.
IEEE Signal Process. Lett., 2025

SVFR: A Unified Framework for Generalized Video Face Restoration.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

CustAny: Customizing Anything from A Single Example.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024
FS-OreDet: Feature enhancement and relationship exploration for boosting few-shot object detector of ore images.
Eng. Appl. Artif. Intell., 2024

Exploring Real&Synthetic Dataset and Linear Attention in Image Restoration.
CoRR, 2024

FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on.
CoRR, 2024

Robust Network Learning via Inverse Scale Variational Sparsification.
CoRR, 2024

SVP: Style-Enhanced Vivid Portrait Talking Head Diffusion Model.
CoRR, 2024

PSPU: Enhanced Positive and Unlabeled Learning by Leveraging Pseudo Supervision.
CoRR, 2024

EFCNet: Every Feature Counts for Small Medical Object Segmentation.
CoRR, 2024

AnyMaker: Zero-shot General Object Customization via Decoupled Dual-Level ID Injection.
CoRR, 2024

VividPose: Advancing Stable Video Diffusion for Realistic Human Image Animation.
CoRR, 2024

StyleMaster: Towards Flexible Stylized Image Generation with Diffusion Models.
CoRR, 2024

Towards Global Optimal Visual In-Context Learning Prompt Selection.
CoRR, 2024

A Generalization Theory of Cross-Modality Distillation with Contrastive Learning.
CoRR, 2024

DiffFAE: Advancing High-fidelity One-shot Facial Appearance Editing with Space-sensitive Customization and Semantic Preservation.
CoRR, 2024

Towards Global Optimal Visual In-Context Learning Prompt Selection.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

PSPU: Enhanced Positive and Unlabeled Learning by Leveraging Pseudo Supervision.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2024

2023
Faster OreFSDet: A lightweight and effective few-shot object detector for ore images.
Pattern Recognit., September, 2023

PatchMix Augmentation to Identify Causal Features in Few-Shot Learning.
IEEE Trans. Pattern Anal. Mach. Intell., June, 2023

Worst-case Feature Risk Minimization for Data-Efficient Learning.
Trans. Mach. Learn. Res., 2023

2022
Exploring Efficient Few-shot Adaptation for Vision Transformers.
Trans. Mach. Learn. Res., 2022

Split-PU: Hardness-aware Training Strategy for Positive-Unlabeled Learning.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

2021
The Image Local Autoregressive Transformer.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Learning Salient Boundary Feature for Anchor-free Temporal Action Localization.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Learning Dynamic Alignment via Meta-Filter for Few-Shot Learning.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Learning a Few-shot Embedding Model with Contrastive Learning.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Pose-Guided Person Image Synthesis in the Non-Iconic Views.
IEEE Trans. Image Process., 2020

Learning to Score Figure Skating Sport Videos.
IEEE Trans. Circuits Syst. Video Technol., 2020

Instance Credibility Inference for Few-Shot Learning.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

An Embarrassingly Simple Baseline to One-shot Learning.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2018
Learning to score and summarize figure skating sport videos.
CoRR, 2018


  Loading...