LonghuiWei's homepage

Brief Bio: I am a senior researcher at Huawei Cloud, and lead the multimodal frontier research and applications. Moreover, I also focus on visual pre-training. Before that, I received Doctor degree from USTC in 2023(Advised by Prof. Wengang Zhou and Prof. Qi Tian), received M.S. degree from PKU (Advised by Prof. Shiliang Zhang and Prof. Qi Tian), Beijing, China, in 2019. Currently, I'm interested in Multimodal&Visual Pre-training, Diffusion Model, Open-vocabulary Learning and some related fields.

I am looking for highly self-motivated interns or full-time employees. Please drop me an email with your CV, if you are insterested.

News

2024.02, Three papers about Multimodality has been accepted by CVPR'24.
2024.01, I have been assigned as the Area Chair of ACM MM'24.
2024.01, One paper about Diffusion Model work has been accepted by ICLR'24.
I have successfully defended my Doctor Thesis! Congratulations to myself!
2023.09, One paper about Multimodal Understanding for ReID has been accepted by TMM.
2023.07, One paper about Multimodal Generation work has been accepted by ACM MM'23.
2023.07, One paper about Multimodal Prompt Learning work has been accepted by ICCV'23.
2023.04, Two papers about Multimodal Continual Learning & Diffusion Model work has been accepted by ICML'23.
2023.03, One paper about Self-supervised Learning work has been accepted by CVPR'23.
2023.02, One paper about Self-supervised Learning work has been accepted by PR.
2022.11, One paper about Text-to-Image Generation work has been accepted by AAAI'23.
2022.09, One paper about Multimodal Pre-training work has been accepted by NeurIPS'22.
2022.07, One paper about Multimodality has been accepted by ACM MM'22.
2022.07, One paper about "MM-guided CV Pre-training"(called MVP) has been accepted by ECCV'22.
2022.03, One paper about NAS has been accepted by CVPR'22.
2022, One paper about NAS has been accepted by IJCV.
2021.12, One paper about NAS has been accepted by T-IP.
2021.12, One paper about Visual Pre-Training has been accepted by AAAI'22 as ORAL paper.
2021.10, One paper about Few-shot Learning has been accepted by NIPS'21.
One paper about Visual Pre-Training has been accepted by TMM.
One paper about Transformer has been accepted by ICCV'21.
One paper about NAS has been accepted by ACM Computing Surveys.
One paper about ReID has been accepted as ORAL paper by CVPR 2021.
One paper about ReID has been accepted by T-CSVT.
One paper about NAS has been accepted by AAAI 2021.
Two papers about ReID&AUTOML has been accepted by ECCV 2020, and one is accepted as Spotlight paper.
We ranked first in Webvision Challenge 2020.
One paper about NAS has been accepted by CVPR 2020.
One paper about ReID has been accepted by AAAI 2020.
I graduated from PKU in 2019, and achieved the honor of Excellent Graduate.
I achieved Gaotong Scholarship.
I achieved National Scholarship in Peking University.
One paper about ReID has been accepted by TMM 2018.
I achieved the Excellent Talents Scholarship of Cooperative Medianet Innovation Center.
The slides of our tutorial on FG 2018: Person Re-Identification: Recent Advances and Challenges have been released !
One paper accepted as Spotlight paper by CVPR 2018.
One paper about ReID has been accepted by ICMR 2018.
One paper about ReID has been accepted by ACM MM 2017.

Services

Area Chair of ACM MM.

Speaker of FG2018 Tutorial, ChinaMM'22 workshop, VALSE'23 workshop, GAMES‘23

Reviewer of ICCV, CVPR, ECCV, NeurIPS, ICML, AAAI

Reviewer of T-PAMI, IJCV, T-IP, T-MM, T-CSVT, Neurocomputing, IET computer vision, Multimedia System, etc.

Selected Publications

Inner Classifier-Free Guidance and Its Taylor Expansion for Diffusion Models

Shikun Sun, Longhui Wei, Zhicai Wang, Zixuan Wang, Junliang Xing, Jia Jia, Qi Tian.
ICLR, 2024

Multi-granularity Matching Transformer for Text-based Person Search

Liping Bao, Longhui Wei, Wengang Zhou, Lin Liu, Lingxi Xie, Houqiang Li, Qi Tian.
IEEE Trans. on Multimedia, 2023

Degeneration-Tuning: Using Scrambled Grid shield Unwanted Concepts from Stable Diffusion

Zixuan Ni, Longhui Wei, Jiacheng Li, Siliang Tang, Yueting Zhuang and Qi Tian.
ACM MM, 2023

Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models

Juncheng Li*, Minghe Gao*, Longhui Wei, and et. al. (* denotes equal contribution)
ICCV, 2023

Continual Vision-Language Representaion Learning with Off-Diagonal Information

Zixuan Ni, Longhui Wei, Siliang Tang, Yueting Zhuang and Qi Tian.
ICML, 2023

SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation

Shikun Sun, Longhui Wei, Junliang Xing, Jia Jia and Qi Tian.
ICML, 2023

Exploring the diversity and invariance in yourself for visual pre-training task

Longhui Wei, Lingxi Xie, Wengang Zhou, Houqiang Li and Qi Tian.
Pattern Recognition, 2023

Fine-Grained Semantically Aligned Vision-Language Pre-Training

Juncheng Li*, Xin He*, Longhui Wei* and et. al. (* denotes equal contribution)
NeurIPS, 2022

MVP: Multimodality-guided Visual Pre-Training

Longhui Wei and et. al.
ECCV, 2022

Can Semantic Labels Assist Self-Supervised Visual Representation Learning?

Longhui Wei and et. al.
AAAI, 2022

Rectifying the Shortcut Learning of Background: Shared Object Concentration for Few-Shot Image Recognition

Luo Xu, Longhui Wei and et. al.
NeurIPS, 2021

Visformer: The Vision-friendly Transformer

Zhengsu Chen, Lingxi Xie, Jianwei Niu, Xuefeng Liu, Longhui Wei, Qi Tian:.
ICCV, 2021

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification

Tianyu Zhang, Lingxi Xie, Longhui Wei, Zijie Zhuang, Yongfei Zhang, Bo Li and Qi Tian.
CVPR, 2021, ORAL

Camera-based Batch Normalization: An Effective Distribution Alignment Method for Person Re-identification

Zijie Zhuang, Longhui Wei, Lingxi Xie, Haizhou Ai and Qi Tian.
T-CSVT, 2021

Circumventing Outliers of AutoAugment with Knowledge Distillation

Longhui Wei, An Xiao, Lingxi Xie, Xin Chen, Xiaopeng Zhang and Qi Tian.
ECCV, 2020, Spotlight

Disassembling the Dataset: A Camera Alignment Mechanism for Multiple Tasks in Person Re-identification

Zijie Zhuang, Longhui Wei, and et al.
ECCV, 2020

Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio

Zhengsu Chen, Jianwei Niu, Lingxi Xie, Xuefeng Liu, Longhui Wei and Qi Tian.
CVPR, 2020

Single Camera Training for Person Re-Identification

Tianyu Zhang, Lingxi Xie, Longhui Wei, Yongfei Zhang, Bo Li and Qi Tian.
AAAI, 2020

GLAD: Global-Local-Alignement Descriptor for Scalable Person Re-Identification

Longhui Wei, Shiliang Zhang, Wen Gao and Qi Tian.
IEEE Trans. on Multimedia, 2018

VP-ReID: Vehicle and Person Re-Identification System

Longhui Wei, Xiaobin Liu, Jianing Zhang and Shiliang Zhang
In Proc. of the 2018 ACM on International Conference on Multimedia Retrieval(ICMR), 2018, demo paper

Person Transfer GAN to Bridge Domain Gap for Person Re-Identification

Longhui Wei, Shiliang Zhang, Wen Gao and Qi Tian.
In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, Spotlight

GLAD: Global-Local-Alignement Descriptor for Pedestrain Retrieval

Longhui Wei, Shiliang Zhang, Hantao Yao, Wen Gao and Qi Tian.
In Proc. ACM Conference on Multimedia (ACM MM), 2017, full paper