Research Projects

Showcase of my research projects in computer vision and machine learning, featuring key publications and their contributions to the field.

Back to Home

Featured Research Projects

GazePrime Framework

Prime and Reach: Synthesising Body Motion for Gaze-Primed Object Reach

Masashi Hatano, Saptarshi Sinha, Jacob Chalk, Wei-Hong Li, Hideo Saito, Dima Damen

Preprint

A dataset and framework for modeling the prime and reach human ability for realistic human motion synthesis.

CrossView3DMTL Framework

3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding

Xiaoye Wang, Chen Tang, Xiangyu Yue, Wei-Hong Li 📧

CVPR 2026

A framework for integrating correlations across views, i.e., cost volume, as geometric consistency in the MTL network.

UniSTD Framework

UniSTD: Towards Unified Spatio-Temporal Prediction across Diverse Disciplines

Chen Tang, Xinzhu Ma, Encheng Su, Xiufeng Song, Xiaohong Liu, Wei-Hong Li, Lei Bai, Wanli Ouyang, Xiangyu Yue

CVPR 2025

A framework for learning universal representations through a single network over multiple spatio-temporal tasks across diverse disciplines.

FairGen Framework

FairGen: Enhancing Fairness in Text-to-Image Diffusion Models via Self-Discovering Latent Directions

Yilei Jiang, Wei-Hong Li 📧, Yiyuan Zhang, Minghong Cai, Xiangyu Yue 📧

ICCV 2025

A framework for debiasing stable diffusion models by learning attribute-specific adapters and noise compositing.

Bifröst Framework

Bifröst: 3D-Aware Image compositing with Language Instructions

Lingxiao Li, Kaixiong Gong, Wei-Hong Li 📧, Xili Dai, Tao Chen, Xiaojun Yuan, Xiangyu Yue 📧

NeurIPS 2024

A framework for enabling 3D-aware image compositing.

3DMTL Framework

Multi-task Learning with 3D-Aware Regularization

Wei-Hong Li, Steven McDonagh, Ales Leonardis, Hakan Bilen

ICLR 2024

A framework for learning structured representations that valid for multiple dense prediction tasks by a 3D-aware regularizer via neural rendering.

Universal Representations Framework

Universal Representations: A Unified Look at Multiple Task and Domain Learning

Wei-Hong Li 📧, Xialei Liu, Hakan Bilen

IJCV 2023

A framework for learning a single universal neural network that effectively works across multiple tasks and domains.

MTPSL Framework

Learning Multiple Dense Prediction Tasks from Partially Annotated Data

Wei-Hong Li, Xialei Liu, Hakan Bilen

CVPR 2022 (Oral, Best Paper Nominee)

A framework for learning multiple dense prediction tasks when only partial annotations are available for each task.

Cross-domain Few-shot Learning

Cross-domain Few-shot Learning with Task-specific Adapters

Wei-Hong Li, Xialei Liu, Hakan Bilen

CVPR 2022

Task-specific adapters enable effective few-shot learning across different domains with minimal parameter updates.

Universal Representation Learning

Universal Representation Learning from Multiple Domains for Few-shot Classification

Wei-Hong Li, Xialei Liu, Hakan Bilen

ICCV 2021

Learning universal feature representations that generalize across multiple domains for few-shot classification tasks.

Learning to Impute

Learning to Impute: A General Framework for Semi-supervised Learning

Wei-Hong Li, Chuan-Sheng Foo, Hakan Bilen

Preprint 2019

A general framework that learns to impute missing features for semi-supervised learning scenarios.

Knowledge Distillation MTL

Knowledge Distillation for Multi-task Learning

Wei-Hong Li, Hakan Bilen

ECCV Workshop 2020

Applying knowledge distillation techniques to improve multi-task learning performance and efficiency.

POINT Framework

Learning to Learn Relation for Important People Detection in Still Images

Wei-Hong Li, Fa-Ting Hong, Wei-Shi Zheng

CVPR 2019

Meta-learning approach for detecting important people in images by learning relational patterns.

PersonRank

PersonRank: Detecting Important People in Images

Wei-Hong Li, Benchao Li, Wei-Shi Zheng

FG 2018 (Oral)

A ranking-based approach for automatically identifying the most important people in group photos.

SoDA

One-pass Person Re-identification by Sketched Online Discriminant Analysis

Wei-Hong Li, Zhuowei Zhong, Wei-Shi Zheng

PR 2019

Efficient online person re-identification using sketched discriminant analysis for real-time applications.