Shu Zhong

Shu Zhong

Auto-generated profile, based on publicly available information

Shu Zhong

Computer Science, University College London, United Kingdom

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 April 2023
Verified
Conference Paper
Open access
MVMadhan Kumar Vasudevan
Madhan Kumar Vasudevan
SZShu Zhong
Shu Zhong
JKJan Kučera
Jan Kučera
DCDesiree Cho
Desiree Cho
MOMarianna Obrist
Marianna Obrist

5 July 2025
Verified
Conference Paper
Open access
SZShu Zhong
Shu Zhong
BABon Adriel Aseniero
Bon Adriel Aseniero
AGAllin Irving Groom
Allin Irving Groom
AHArthur Harsuvanakit
Arthur Harsuvanakit
BLBrian Joon Lee
Brian Joon Lee
DBDavid Benjamin
David Benjamin

4 November 2024
Verified
Conference Paper
Open access
SZShu Zhong
Shu Zhong
The rise of Machine Learning (ML) is gradually digitalizing and reshaping the fashion industry, which is under pressure to achieve Net Zero. However, the integration of ML/AI for sustainable and circular practices remains limited due to a lack of domain-specific knowledge and data. My doctoral research aims to bridge this gap by designing digital multisensory textile experiences that enhance the understanding of the textile domain for both AI systems and humans. To this end, I develop TextileNet, the first fashion dataset using textile taxonomies for textile materials identification and classification via computer vision, and TextileBot, a domain-specific conversational agent. TextileBot integrates textile taxonomies with large language models (LLMs) to engage consumers in sustainable practices. Additionally, my research explores how multisensory experiences can improve user understanding and how AI perceives textiles. The overarching goal is to embed human expertise into machines, design immersive multisensory experiences, and facilitate natural human-AI interactions that promote sustainable practices.

4 November 2024
Verified
Conference Paper
Open access
SZShu Zhong
Shu Zhong
EGElia Gatti
Elia Gatti
Youngjun ChoYoungjun Cho
Youngjun Cho
MOMarianna Obrist
Marianna Obrist
Human-artificial intelligence (AI) alignment ensures that AI systems align with human goals and behaviors. This paper introduces perceptual alignment as a critical aspect of this alignment, focusing on the concurrence between human judgments and AI evaluations across sensory modalities. We particularly explore how Multimodal Large Language Models (MLLMs), which process both visual and textual data, interpret the tactile qualities of textiles—a significant challenge in online shopping environments. Our research analyzes six vision-based MLLMs to see how they describe the tactile experience of textiles and compares these AI-generated descriptions with human assessments. Through semantic similarity measures and in-person evaluations, we investigate the extent of alignment between human perceptions and AI descriptions. Our findings indicate significant variability in the AI’s ability to interpret different textiles, highlighting both the potential and limitations of current AI models in achieving perceptual alignment. This work contributes to understanding the complexities of aligning AI capabilities with human touch sensory experiences.

20 February 2026 in International Journal of Human-Computer Studies
Verified
Journal Article
Open access
SZShu Zhong
Shu Zhong
EGElia Gatti
Elia Gatti
Youngjun ChoYoungjun Cho
Youngjun Cho
MOMarianna Obrist
Marianna Obrist

1 May 2025 in Digital Health
Verified
Journal Article
Open access
MVMadhan Kumar Vasudevan
Madhan Kumar Vasudevan
CBCeylan Besevli
Ceylan Besevli
PNPreetham Madapura Nagaraj
Preetham Madapura Nagaraj
SZShu Zhong
Shu Zhong
MMManivannan Muniyandi
Manivannan Muniyandi
MOMarianna Obrist
Marianna Obrist
Objective: Healthy ageing and well-being are deeply connected to our sensory experiences, which shape how we interact with the world. As sensory decline is a natural aspect of ageing, it opens opportunities for designing digital technologies that enhance the quality of life. Our objective is to explore how mindful tactile technologies can support healthy ageing by addressing sensory decline in older adults, with a particular focus on cross-cultural insights and user-led design approaches. Methods: We conducted four co-production workshops: two in India and two in the UK, bringing together older adult attendees from diverse socio-economic backgrounds. These workshops used participatory design methods to gather perspectives on sensory challenges, and emotional well-being and envisioned future technologies related to touch and mindfulness. Results: Our findings revealed strong connections between sensory experiences, mindfulness, and well-being, as well as distinct cultural differences in how these are experienced and valued. Indian attendees emphasised collective well-being and spiritual practices, while UK attendees focused more on personal autonomy and self-care. These insights informed four key design implications for developing tactile technologies that are culturally adaptive and age-inclusive. Conclusion: Our work highlights the potential of co-produced, sensory-based digital technologies to enhance the quality of life in older adults. By grounding design in cultural values and lived sensory experiences, our work lays the foundation for future digital health interventions that are both meaningful and inclusive across global ageing populations.