Selected Publications


Multi-task Learning with 3D-Aware Regularization.
Wei-Hong Li, Steven McDonagh, Ales Leonardis, Hakan Bilen.
ICLR 2024 / OpenReview / arXiv / Code

Universal Representations: A Unified Look at Multiple Task and Domain Learning.
Wei-Hong Li, Xialei Liu, Hakan Bilen.
IJCV 2023 / arXiv / Springer / Code

Learning universal representations across tasks and domains.
Wei-Hong Li
University of Edinburgh 2022 / PhD Thesis
The BMVA Sullivan Doctoral Thesis Prize Runner-Up

Learning Relation Models to Detect Important People in Still Images.
Yu-Kun Qiiu, Fa-Ting Hong, Wei-Hong Li, Wei-Shi Zheng.
TMM 2022 / paper

Learning Multiple Dense Prediction Tasks from Partially Annotated Data.
Wei-Hong Li, Xialei Liu, Hakan Bilen.
CVPR 2022 (Oral) / Website / CVF / supp / arXiv / Video / Code / Poster
Best Paper Nominee (33/8161)

Cross-domain Few-shot Learning with Task-specific Adapters.
Wei-Hong Li, Xialei Liu, Hakan Bilen.
CVPR 2022 / Website / CVF / supp / arXiv / Video / Code / Poster

Universal Representation Learning from Multiple Domains for Few-shot Classification.
Wei-Hong Li, Xialei Liu, Hakan Bilen.
ICCV 2021 / Website / CVF / supp / arXiv / Video / Code / Poster

Knowledge Distillation for Multi-task Learning.
Wei-Hong Li, Hakan Bilen.
ECCV Workshop 2020 / Website / arXiv / Video / Code

MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection.
Fa-Ting Hong, Xuanteng Huang, Wei-Hong Li, Wei-Shi Zheng.
ECCV 2020 / ECVA / supp / arXiv / Code

Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detection.
Fa-Ting Hong*, Wei-Hong Li*, Wei-Shi Zheng.
CVPR 2020 / Website / CVF / supp / arXiv / Code / EMS Dataset / ENCAA Dataset / Poster

Learning to Impute: A General Framework for Semi-supervised Learning.
Wei-Hong Li, Chuan-Sheng Foo, Hakan Bilen.
Preprint 2019 / Website / arXiv / Code

One-pass Person Re-identification by Sketched Online Discriminant Analysis.
Wei-Hong Li, Zhuowei Zhong, Wei-Shi Zheng.
PR 2019 / Website / arXiv

Learning to Learn Relation for Important People Detection in Still Images.
Wei-Hong Li*, Fa-Ting Hong*, Wei-Shi Zheng.
CVPR 2019 / Website / CVF / supp / arXiv

PersonRank: Detecting Important People in Images.
Wei-Hong Li, Benchao Li, Wei-Shi Zheng.
FG 2018 (Oral) / Website / paper / MS Dataset / NCAA Dataset

Correlation based Identity Filter: An Efficient Framework For Person Search.
Wei-Hong Li, Yafang Mao, Ancong Wu, Wei-Shi Zheng.
ICIG 2017 (Oral) / paper
Best Paper Award

Sketch metric learning.
Yuting Mai, Wei-Hong Li, Yongyi Tang, Xixi Bi, Wei-Shi Zheng.
IJCNN 2016 / paper

Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networks.
Xiang Li, Chan Lu, Danni Cheng, Wei-Hong Li, Mei Cao, Bo Liu, Jiechao Ma, Wei-Shi Zheng.
ICIG 2019 / paper

Large-Scale Visible Watermark Detection and Removal with Deep Convolutional Networks.
Danni Cheng, Xiang Li, Wei-Hong Li, Chan Lu, Fake Li, Hua Zhao, Wei-Shi Zheng.
PRCV 2018 (Oral) / paper / Dataset (baidu) / Dataset (onedrive)

A Delaunay-Based Temporal Coding Model for Micro-expression Recognition.
Zhaoyu Lu and Ziqi Luo and Huicheng Zheng and Jikai Chen and Wei-Hong Li.

ACCV Workshop 2014 / paper