I received the Ph.D. degree in Computer Science from the City University of Hong Kong (CityU), under supervision of Rynson Lau and Antoni Chan. I obtained the B.Eng. and M.Sc. in Software Engineering from Northeastern University (China). I was an intern at Microsoft Research Aisa (MSRA). I was a postdoctoral researcher in the Department of Computer Science at the CityU. |
My primary research interest is Data-driven Design Intelligence, which aims to answer a challenging question: how can computers learn to design from data and augment humans in the design process? The long-term goal of my research is to empower computers with design intelligence - the capabilities of machines to perceive, understand and create graphic designs (e.g., comics, webpages, posters, magazines, advertisement, etc.) like humans. I am particularly interested in learning rich models that describe the structure, style, semantics and functionality of designs, and exploring their potential use in the creative process. |
![]() |
Design Order Guided Visual Note Optimization
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2022
[Paper]
|
![]() |
Instance-aware Scene Layout Forecasting
International Journal of Computer Vision (IJCV), 2022
[Paper]
|
![]() |
Object-level Scene Context Prediction
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021
[Paper]
|
![]() |
Automatic Comic Generation with Stylistic Multi-page Layouts and Emotion-driven Balloon Generation
ACM Transactions on Multimedia Computing Communications and Applications, 2021
[Paper]
|
![]() |
Night-time Scene Parsing with a Large Real Dataset
IEEE Transactions on Image Processing, 2021
[Paper]
|
![]() |
Weakly-Supervised Salient Object Detection With Saliency Bounding Boxes
IEEE Transactions on Image Processing, 2021
[Paper]
|
![]() |
Selective Region-based Photo Color Adjustment for Graphic Designs
ACM Transactions on Graphics, 2020 (to be presented at SIGGRPAH 2021)
|
![]() |
Tactile Sketch Saliency
ACM Multimedia 2020
[Paper]
|
![]() |
Content-aware Generative Modeling of Graphic Design Layouts
ACM Transactions on Graphics (Proc. SIGGRAPH 2019)
|
![]() |
ButtonTips: Design Web Buttons with Suggestions
ICME 2019 (Oral)
|
![]() |
Tell Me Where I Am: Object-level Scene Context Prediction
CVPR 2019 (Oral)
|
![]() |
Distraction-Aware Shadow Detection
CVPR 2019
|
![]() |
Modeling Fonts in Context: Font Prediction on Web Designs
Computer Graphics Forum (Proc. Pacific Graphics 2018)
|
![]() |
Task-driven Webpage Saliency
ECCV 2018
|
![]() |
Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss
ECCV 2018
|
![]() |
What Characterizes Personalities of Graphic Designs?
ACM Transactions on Graphics (Proc. SIGGRAPH 2018)
|
![]() |
Mining Probabilistic Color Palettes for Summarizing Color Use in Artwork Collections
SIGGRAPH Asia 2017 Symposium on Visualization
|
![]() |
Directing User Attention via Visual Flow on Web Designs
ACM Transactions on Graphics (Proc. SIGGRAPH Asia 2016)
|
![]() |
DynamicManga: Animating Still Manga via Camera Movement
IEEE Transactions on Multimedia, 2016
|
![]() |
A Robust Panel Extraction Method for Manga
ACM Multimedia 2014
[PDF]
|
![]() |
Look Over Here: Attention-Directing Composition of Manga Elements
ACM Transactions on Graphics (Proc. SIGGRAPH 2014)
|
![]() |
Automatic Stylistic Manga Layout
ACM Transactions on Graphics (Proc. SIGGRAPH Asia 2012)
|