Jiayi Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jiayi Zhou has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Huamin Qu
The Hong Kong University of Science and Technology, Hong Kong Sar, China
5 shared publications - Anyi Rao
The Hong Kong University of Science and Technology, Hong Kong Sar, China
3 shared publications - Junxiu Tang
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
3 shared publications - Yingcai Wu
Zhejiang University, Hangzhou, China
3 shared publications - Haotian Li
Microsoft Research Asia, Beijing, China
2 shared publications - Liwenhan Xie
The Hong Kong University of Science and Technology, Hong Kong Sar, China
2 shared publications
Latest Publications
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Collascope: Supporting Serendipitous Asset Exploration for Collage-Based Storytelling
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessCollascope: Supporting Serendipitous Asset Exploration for Collage-Based Storytelling
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-15
RemiAssist: A Therapist-Supporting System for Photo-Based Reminiscence Therapy in Dementia Care
Despite growing interest in applying AI to photo-based reminiscence therapy (PRT) for people with dementia (PwD), existing systems primarily focus on PwD-AI interaction and often overlook therapists’ critical role in practical PRT delivery. We present RemiAssist, a system that supports therapist-in-the-loop PRT through AI-assisted planning and real-time facilitation. RemiAssist incorporates two core techniques: (1) a Memory Graph, which organizes key life events from a PwD’s photo collection into a hierarchical graph to support theme-centered intervention planning; and (2) a Context-Aware Guiding Strategy, which provides real-time suggestions to help therapists guide reminiscence conversations and respond to sensitive situations. A field study with eight therapist–PwD dyads suggests that RemiAssist was associated with a 44% improvement in planning efficiency, a 54% increase in conversation duration, and timely support for handling sensitive situations. We highlight opportunities for AI systems to empower therapists and enable more personalized reminiscence therapy in dementia care.
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessRemiAssist: A Therapist-Supporting System for Photo-Based Reminiscence Therapy in Dementia Care
Despite growing interest in applying AI to photo-based reminiscence therapy (PRT) for people with dementia (PwD), existing systems primarily focus on PwD-AI interaction and often overlook therapists’ critical role in practical PRT delivery. We present RemiAssist, a system that supports therapist-in-the-loop PRT through AI-assisted planning and real-time facilitation. RemiAssist incorporates two core techniques: (1) a Memory Graph, which organizes key life events from a PwD’s photo collection into a hierarchical graph to support theme-centered intervention planning; and (2) a Context-Aware Guiding Strategy, which provides real-time suggestions to help therapists guide reminiscence conversations and respond to sensitive situations. A field study with eight therapist–PwD dyads suggests that RemiAssist was associated with a 44% improvement in planning efficiency, a 54% increase in conversation duration, and timely support for handling sensitive situations. We highlight opportunities for AI systems to empower therapists and enable more personalized reminiscence therapy in dementia care.
- Open Access
- 13 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 4815-4833
DataSway: Vivifying Metaphoric Visualization with Animation Clip Generation and Coordination
- 13 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 4815-4833
Open AccessDataSway: Vivifying Metaphoric Visualization with Animation Clip Generation and Coordination
- Top Cited PapersOpen Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
How Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Top Cited PapersOpen AccessHow Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters
- Top Cited PapersOpen Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Collaposer: Transforming Photo Collections into Visual Assets for Storytelling with Collages
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Top Cited PapersOpen AccessCollaposer: Transforming Photo Collections into Visual Assets for Storytelling with Collages
- Open Access
- 23 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1
Loss of Sonnet 18
This project is an explorative digital art installation that delves into the phenomenon of generation loss in digital signal processing - the inevitable degradation of information (e.g., words) quality through copying and propagation. It transcends the technical realm to probe how this concept applies to the transmission and transformation of words and meanings through time and technology. It consists of a series of videos illustrating the loss of words themselves and their meaning, combined with real-time interpretation from both humans and AI. The project allows the audience to find a border of loss, beyond which, information of words might change.
- 23 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1
Open AccessLoss of Sonnet 18
This project is an explorative digital art installation that delves into the phenomenon of generation loss in digital signal processing - the inevitable degradation of information (e.g., words) quality through copying and propagation. It transcends the technical realm to probe how this concept applies to the transmission and transformation of words and meanings through time and technology. It consists of a series of videos illustrating the loss of words themselves and their meaning, combined with real-time interpretation from both humans and AI. The project allows the audience to find a border of loss, beyond which, information of words might change.
- Top Cited PapersOpen Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Understanding Nonlinear Collaboration between Human and AI Agents: A Co-design Framework for Creative Design
Creative design is a nonlinear process where designers generate diverse ideas in the pursuit of an open-ended goal and converge towards consensus through iterative remixing. In contrast, AI-powered design tools often employ a linear sequence of incremental and precise instructions to approximate design objectives. Such operations violate customary creative design practices and thus hinder AI agents’ ability to complete creative design tasks. To explore better human-AI co-design tools, we first summarize human designers’ practices through a formative study with 12 design experts. Taking graphic design as a representative scenario, we formulate a nonlinear human-AI co-design framework and develop a proof-of-concept prototype, OptiMuse. We evaluate OptiMuse and validate the nonlinear framework through a comparative study. We notice a subconscious change in people’s attitudes towards AI agents, shifting from perceiving them as mere executors to regarding them as opinionated colleagues. This shift effectively fostered the exploration and reflection processes of individual designers.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Top Cited PapersOpen AccessUnderstanding Nonlinear Collaboration between Human and AI Agents: A Co-design Framework for Creative Design
Creative design is a nonlinear process where designers generate diverse ideas in the pursuit of an open-ended goal and converge towards consensus through iterative remixing. In contrast, AI-powered design tools often employ a linear sequence of incremental and precise instructions to approximate design objectives. Such operations violate customary creative design practices and thus hinder AI agents’ ability to complete creative design tasks. To explore better human-AI co-design tools, we first summarize human designers’ practices through a formative study with 12 design experts. Taking graphic design as a representative scenario, we formulate a nonlinear human-AI co-design framework and develop a proof-of-concept prototype, OptiMuse. We evaluate OptiMuse and validate the nonlinear framework through a comparative study. We notice a subconscious change in people’s attitudes towards AI agents, shifting from perceiving them as mere executors to regarding them as opinionated colleagues. This shift effectively fostered the exploration and reflection processes of individual designers.
- Open Access
- 26 February 2024
- Published by Elsevier in Cell Reports Physical Science
- Vol. 5 (3)
Potential to transform words to watts with large language models in battery research
- 26 February 2024
- Published by Elsevier in Cell Reports Physical Science
- Vol. 5 (3)
Open AccessPotential to transform words to watts with large language models in battery research
- 26 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 30 (12) , 7687-7701
A Comparative Study on Fixed-Order Event Sequence Visualizations: Gantt, Extended Gantt, and Stringline Charts
We conduct two in-lab experiments (N=93) to evaluate the effectiveness of Gantt charts, extended Gantt charts, and stringline charts for visualizing fixed-order event sequence data. We first formulate five types of event sequences and define three types of sequence elements: point events, interval events, and the temporal gaps between them. Our two experiments focus on event sequences with a pre-defined, fixed order, and measure task error rates and completion time. The first experiment shows single sequences and assesses the three charts' performance in comparing event duration or gap. The second experiment shows multiple sequences and evaluates how well the charts reveal temporal patterns. The results suggest that when visualizing single fixed-order event sequences, 1) Gantt and extended Gantt charts lead to comparable error rates in the duration-comparing task; 2) Gantt charts exhibit either shorter or equal completion time than extended Gantt charts; 3) both Gantt and extended Gantt charts demonstrate shorter completion times than stringline charts; 4) however, stringline charts outperform the other two charts with fewer errors in the comparing task when event type counts are high. Additionally, when visualizing multiple point-based fixed-order event sequences, stringline charts require less time than Gantt charts for people to find temporal patterns. Based on these findings, we discuss design opportunities for visualizing fixed-order event sequences and discuss future avenues for optimizing these charts.
- 26 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 30 (12) , 7687-7701
A Comparative Study on Fixed-Order Event Sequence Visualizations: Gantt, Extended Gantt, and Stringline Charts
We conduct two in-lab experiments (N=93) to evaluate the effectiveness of Gantt charts, extended Gantt charts, and stringline charts for visualizing fixed-order event sequence data. We first formulate five types of event sequences and define three types of sequence elements: point events, interval events, and the temporal gaps between them. Our two experiments focus on event sequences with a pre-defined, fixed order, and measure task error rates and completion time. The first experiment shows single sequences and assesses the three charts' performance in comparing event duration or gap. The second experiment shows multiple sequences and evaluates how well the charts reveal temporal patterns. The results suggest that when visualizing single fixed-order event sequences, 1) Gantt and extended Gantt charts lead to comparable error rates in the duration-comparing task; 2) Gantt charts exhibit either shorter or equal completion time than extended Gantt charts; 3) both Gantt and extended Gantt charts demonstrate shorter completion times than stringline charts; 4) however, stringline charts outperform the other two charts with fewer errors in the comparing task when event type counts are high. Additionally, when visualizing multiple point-based fixed-order event sequences, stringline charts require less time than Gantt charts for people to find temporal patterns. Based on these findings, we discuss design opportunities for visualizing fixed-order event sequences and discuss future avenues for optimizing these charts.