Hui-Yin Wu

About

I am a research scientist (Starting Faculty Position) in the Biovision team ➚ of Centre Inria d'Université Côte d'Azur. My ongoing research concerns tools and algorithms for interactive and multimedia storytelling, notably for 3D immersive environments and film, with projects focusing on:

designing accessible multimedia technologies for people with low vision,
study and modelling of user attention and behavior in immersive 3D environments,
content generation and assisted creativity for extended reality, and
methods for the automated analysis of visual media, notably film narrative.

I defended my thesis on Cinematic Discourse for Interactive 3D Storytelling ➚ in October, 2016.

News & Updates

[SEP 2024] Our two papers on human trajectory prediction in rich virtual reality contexts have been accepted to 2024 ECCV workshop on Computer Vision for Metaverse! It is the work of PhD student Franz Franco Gallo, co-supervised with L. Sassatelli. Come find us in Milan on 29th September!
[MAY 2024] Our paper "AMD Journee: A Patient Co-designed VR Experience to Raise Awareness Towards the Impact of AMD on Social Interactions ➚" has been accepted at ACM IMX 2024! It is the work of PhD student Johanna Delachambre, co-supervised with P. Kornprobst.
[APR 2024] Our paper "Human Trajectory Forecasting in 3D Environments: Navigating Complexity under Low Vision ➚" has been accepted at the MMSys 2024 MMVE workshop! It is the work of PhD student Franz Franco Gallo, co-supervised with L. Sassatelli on the ANR CREATTIVE3D ➚ project.
[FEB 2024] Our paper "Visual Objectification in Films: Towards a New AI Task for Video Interpretation ➚" has been accepted at CVPR 2024! It is the work of PhD student Julie Tores and partners in computer and social scientists on the ANR TRACTIVE ➚ project.
[JAN 2024] We have two papers accepted to IEEE VR 2024! Read the pre-prints: "Task-based methodology to characterise immersive user experience with multivariate data" ➚ by F. Robert, H.-Y. Wu, L. Sassatelli, and M. Winckler. "HandyNotes: using the hands to create semantic representations of contextually aware real-world objects" ➚ by C. Quéré, A. Menin, R. Julien, H.-Y. Wu, and M. Winckler. Come meet us in Florida!
[JAN 2024] Preprint for our new open dataset on multimodal user street crossings in VR is now available Exploring, walking, and interacting in virtual reality with simulated low vision: a living contextual dataset ➚.