Wei-Hong Li is currently a research associate (postdoc) within the VICO Group led by Hakan Bilen in the School of Informatics at the University of Edinburgh. Prior to postdoc, he completed his PhD in the same group, supervised by Hakan Bilen and Timothy Hospedales. His research interests are in computer vision and machine learning, with a focus on multi-task/domain learning and learning visual models from limited human supervision. He has been a reviewer for top-tier conferences such as CVPR, ICCV, Neurips and journals such as TPAMI et al. He was invited to give talks at VGG, Sun Yat-sen University et al. His MTPSL paper was listed in the CVPR 2022 Best Paper Nominees.
Happy to chat about any topics, in particular research in Computer Vision! Feel free to send an email.
Before Edinburgh, he did his master and bachelor at Sun Yat-sen University, working with Wei-Shi Zheng who thankfully introduced him to computer vision. During the master program, he was lucky to visit Queen Mary University of London to work with Shaogang Gong.I'm on the job market. Feel free to contact me.
News (July 2023): Our Universal Representations paper is accepted by IJCV. Congrats to Xialei and Hakan!
News (July 2023): Giving a talk about our MTPSL paper at the IPAB Workshop.
News (June 2023): Presenting our TSA paper at the Affordable Machine Learning Workshop.
News (March 2023): Giving an invited talk (Learning universal representations across tasks and domains) at the Sun Yat-sen University, China.
News (December 2022): My PhD thesis titled "Learning universal representations across tasks and domains" has been released!
News (September 2022): We are organizing the Universal Representations for Computer Vision Workshop at BMVC 2022. We invite submissions of regular and short papers. See Call for Papers for more details!
News (September 2022): One paper accepted by TMM. Congrats to Yu-Kun, Fa-Ting, and Wei-Shi!
News (August 2022): I am excited to start my postdoc at the University of Edinburgh, working with Hakan Bilen!
News (August 2022): I have passed my PhD viva with my thesis "Learning Universal Representations Across Tasks and Domains". Great thanks to examiners Amir Zamir and Laura Sevilla and my supervisor Hakan Bilen!
News (July 2022): We've released the code of our Universal Representation Learning paper.
News (June 2022): We've released the code of our "Learning Multiple Dense Prediction Tasks from Partially Annotated Data" paper (CVPR 2022).
News (June 2022): Our "Learning Multiple Dense Prediction Tasks from Partially Annotated Data" paper is listed in the CVPR 2022 Best Paper Finalists.
News (April 2022): We've released a preprint of our work 'Universal Representations: A Unified Look at Multiple Task and Domain Learning'.
News (March 2022): We've released the code of our TSA paper (CVPR 2022).
News (March 2022): Two papers accepted to CVPR 2022. Congrats to Xialei and Hakan!
News (February 2022): Giving an invited presentation (Universal Representation Learning and Task-specific Adaptation for Few-shot Learning) in VGG, University of Oxford.
News (February 2022): I maintain an up-to-date list of works on Multi-task Learning here.
News (December 2021): We've released a preprint of our work on Multi-task Partially Supervised Learning.
News (October 2021): We've released the code of our URL paper (ICCV 2021).
News (July 2021): One paper to appear at ICCV 2021. Congrats to Xialei and Hakan!
News (July 2021): We've released a preprint of our recent work on 'Cross-domain Few-shot Learning with Task-specific Adapters'.
News (April 2021): We've released the code of semi-supervised important people detection (CVPR 2020).
News (March 2021): We've released a preprint of our recent work on 'Universal Representation Learning from Multiple Domains for Few-shot Classification'.
News (December 2020): Code for our "MINI-Net: Multiple Instance Ranking Network for Video Highlight Detection" paper is available.
News (September 2020): Code for our "Knowledge Distillation for Multi-task Learning" paper is now available.
News (August 2020): Attending and presenting our work at ECCV 2020.
News (July 2020): One paper to appear at ECCV 2020 and one at the IPCV Workshop.
News (June 2020): We've released the EMS and ENCAA datasets.
News (February 2020): One paper to appear at CVPR 2020. The paper and poster are now online.
News (January 2020): Attending the Informatics Workshop (Meta-learning) at University of Edinburgh.
News (December 2019): The paper and code of our recent work on semi-supervised learning are now available at our project page.
News (December 2019): Attending the Huawei Research Workshop in Shanghai.
News (November 2019): Attending the Amazon Research Day and presenting my recent work on semi-supervised learning.
News (September 2019): Pass my first annual review.
News (June 2019): Attending CVPR 2019 in Long Beach, USA, for presenting my recent paper on important people detection.
News (April 2019): The Paper, Code and Supplementary Material of our CVPR 2019 paper are available at our project page.
News (March 2019): The paper One-pass Person Re-identiﬁcation by Sketched Online Discriminant Analysis is accepted to be published in Pattern Recognition (PR). Congrats to Zhuowei Zhong and Wei-Shi Zheng.
News (February 2019): The paper Learning to Learn Relation for Important People Detection in Still Images is accepted by CVPR 2019. Congrats to Fa-Ting Hong and Wei-Shi Zheng.
News (February 2019): Our group page is now available.
News (October 2018): Two important people image datasets are available!
News (September 2018): I am excited to start my PhD study with Prof. Hakan Bilen.
News (January 2018): The paper PersonRank: Detecting Important People in Images is accepted by the FG 2018 as an oral paper.
News (December 2017): The paper One-pass Person Re-identiﬁcation by Sketched Online Discriminant Analysis is available on arXiv and the project page can be found here.
News (September 2017): The paper Correlation based Identity Filter: An Efficient Framework For Person Search is accepted by ICIG 2017 and is awarded The Best Paper Award.