WU , Hui-Yin

Understanding newspaper structure and design remains a challenging task due to the complex composition of pages with many visual and textual elements. Current approaches have focused on simple design types and analysed only broad classes for the components in a page. In this paper, we propose an approach to obtain a comprehensive understanding...

International audience

Virtual environments provide a rich and controlled setting for collecting detailed data on human behavior, offering unique opportunities for predicting human trajectories in dynamic scenes. However, most existing approaches have overlooked the potential of these environments, focusing instead on static contexts without considering userspecific...

Virtual reality (VR) provides a unique solution to improve current trajectory forecasting by capturing data in controlled, interactive scenarios, ensuring precision and inclusivity. Our work collects rich multimodal human data under VR scenarios considering the impact of low vision. We propose a novel model capable of handling multimodal data...

Scene context informing on spatio-temporal interactions between people and other entities significantly improves accuracy of activity recognition and motion forecasting tasks, such as human trajectory prediction, but is difficult to obtain. Virtual reality (VR) offers an opportunity to generate and simulate diverse scenes with contextual...

Low-vision conditions resulting in partial loss of the central visual field strongly affect patients' daily tasks and routines, and none more prominently than the ability to access text. Though vision aids such as magnifiers, digital screens, and text-to-speech devices can improve overall accessibility to text, news media, which is non-linear...

Special theme: Assistive Technologies for a More Accessible and Inclusive Society, Number 130

Low-vision conditions resulting in partial loss of the visual field strongly affect patients' daily tasks and routines, and none more prominently than the ability to access text. Though vision aids such as magnifiers, digital screens, and text-to-speech devices can improve overall accessibility to text, news media, which is non-linear and has...

Young women frequently face implicit behavioral biases – through unfriendly gaze, gestures, or speech – in all aspects of their daily lives. This is particularly true in the field of engineering, where women are a minority, making it emotionally difficult for them to fit in and feel at home, and deterring young women to enter these fields. Yet...

This work tackles the challenge of predicting human trajectories while carrying out complex tasks in contextually-rich virtual environments. We evaluate the CREATIVE3D multimodal dataset on human interaction and navigation in 3D virtual reality (VR). In the dataset, navigating traffic crossings with simulated visual impairments are used as an...

Identifying human characters and how they are portrayed on-screen is inherently linked to how we perceive and interpretthe story and artistic value of visual media. Building computational models sensible towards story will thus require a formalrepresentation of the character. Yet this kind of data is complex and tedious to annotate on a large...

Virtual Reality (VR) technologies enable strong emotions compared to traditional media, stimulating the brain in ways comparable to real-life interactions. This makes VR systems promising for research and applications in training or rehabilitation, to imitate realistic situations. Nonetheless, the evaluation of the user experience in immersive...

This report presents the work of a 6-month internship part of the MSc in Modeling for Neuronal and Cognitive systems. This work explores possible approaches in the use of simulated Retinal Waves (RWs) as pre-training for machine learning (ML) computer vision models in Optical Flow Estimation (OFE). Retinal Waves are one of the early processes...

Virtual reality (VR) offers opportunities in human-computer interaction research, to embody users in immersive environments and observe how they interact with 3D scenarios under well-controlled environments. VR content has stronger influences on users physical and emotional states as compared to traditional 2D media, however, a fuller...

The objective of this work is to develop a machine learning model for Optical Flow Estimation (OFE) that employs simulated stage II Retinal Waves as a training set. OFE is a crucial task in computer vision used to infer the motion between two consecutive frames in a video. Training data-driven OFE models is challenging, and the difficulty of...

La création d'un jeu sérieux en réalité virtuelle (VR) implique que les utilisatrices puissent interagir avec l'environnement et qu'elles aient un but bien défini permettant de les exposer à une expérience de jeu. Cela est utile pour divers domaines comme l'éducation ou encore de la réhabilitation. La mise en place d'un scénario de jeu peut...

Joint attention refers to the shared focal points of attention for occupants in a space. In this work, we introduce a computational definition of joint attention for the automated editing of meetings in multi-camera environments from the AMI corpus. Using extracted head pose and individual headset amplitude as features, we developed three...

This paper uses Mixed Reality (MR) technologies to provide a seamless integration of digital information in physical environments through human-made annotations. Creating digital annotations of physical objects evokes many challenges for performing (simple) tasks such as adding digital notes and connecting them to real-world objects. For that,...

Virtual Reality (VR) technology enables ``embodied interactions'' in realistic environments where users can freely move and interact, with deep physical and emotional states. However, a comprehensive understanding of the embodied user experience is currently limited by the extent to which one can make relevant observations, and the accuracy at...

Using Virtual Reality (VR) to investigate visual processing is a growing trend due to the high scientific potential of VR (allowing experiments in highly controlled environments and ecological scenarios), and to the increasing power of ever cheaper VR headsets. However, implementing VR experiments requires non-trivial programming skills that...

Virtual reality (VR) offers extraordinary opportunities in user behavior research to study and observe how people interact in immersive 3D environments. A major challenge of designing these 3D experiences and user tasks, however, lies in bridging the inter-relational gaps of perception between the designer, the user, and the 3D scene. Based on...

Introduction: Virtual Reality (VR) headsets are raising more and more interest from the low-vision research community since they offer a promising framework for low-vision aids and rehabilitation protocols. However, the study of VR accessibility to low vision is still in its early stages and designing efficient user interfaces for low-vision...

In this paper, we present an adaptive assisting interface for learning virtual filmmaking. The design of the system is based on the scaffolding theory, to provide timely guidance to the user in the form of visual and audio messages that are adapted to each person's skill level and performance. The system was developed on an existing virtual...

Virtual reality (VR) places players in immersive environments with which they can interact. This allows players to experience lifelike scenarios in various contexts. However, setting up a scenario in a game can turn out to be a long and complex process for the developer for two main reasons : (1) the large number of different objects composing...