Wenzhe Hu
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
Research Subjects
Research Interests
Wenzhe Hu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Fanman Meng
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication - Heqian Qiu
University of Electronic Science and Technology of China
1 shared publication - Hiu Man Ho
City University of Hong Kong, Hong Kong, SAR
1 shared publication - Hongliang Li
University of Electronic Science and Technology of China
1 shared publication - Kexue Fu
School of Creative Media, City University of Hong Kong, Hong Kong, SAR, China
1 shared publication - Lanxiao Wang
University of Electronic Science and Technology of China, Chengdu, China
1 shared publication
Latest Publications
- Open Access
- 19 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
Crafting Memorable Science Stories: Harnessing the Power of Narrative Peaks in Online Science Video Narrative Design
Online platforms have made science communication accessible and engaging. However, infotainment risks weakening the depth of scientific communication. We investigate how narrative peaks can be constructed in online science video (OSV) narratives to support viewer engagement and memory. Combining a literature review with viewer-oriented annotations of OSVs, we developed a design space of linguistic and structural strategies for constructing narrative peaks. It organizes these strategies across textual levels and provides definitions and examples of their application. A workshop with eight experienced content creators showed that the design space can systematize an otherwise intuitive scripting process while revealing differences in implementation difficulty and patterns of strategy combination. A preliminary quantitative experiment with 36 viewers assessed the effects of different peak strategies on learning-related outcomes. This work establishes narrative peak design as an actionable, evidence-based writing practice from both creators’ and viewers’ perspectives by connecting science communication theory with HCI research.
- 19 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
Open AccessCrafting Memorable Science Stories: Harnessing the Power of Narrative Peaks in Online Science Video Narrative Design
Online platforms have made science communication accessible and engaging. However, infotainment risks weakening the depth of scientific communication. We investigate how narrative peaks can be constructed in online science video (OSV) narratives to support viewer engagement and memory. Combining a literature review with viewer-oriented annotations of OSVs, we developed a design space of linguistic and structural strategies for constructing narrative peaks. It organizes these strategies across textual levels and provides definitions and examples of their application. A workshop with eight experienced content creators showed that the design space can systematize an otherwise intuitive scripting process while revealing differences in implementation difficulty and patterns of strategy combination. A preliminary quantitative experiment with 36 viewers assessed the effects of different peak strategies on learning-related outcomes. This work establishes narrative peak design as an actionable, evidence-based writing practice from both creators’ and viewers’ perspectives by connecting science communication theory with HCI research.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Read and Reflect: Exploring How the Display of User-Generated Content Shapes In-Situ Museum Expression
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessRead and Reflect: Exploring How the Display of User-Generated Content Shapes In-Situ Museum Expression
- 20 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 5400-5412
What Happens in Crowd Scenes: A New Dataset About Crowd Scenes for Image Captioning
Making machines endowed with eyes and brains to effectively understand and analyze crowd scenes is of paramount importance for building a smart city to serve people. This is of far-reaching significance for the guidance of dense crowds and accident prevention, such as crowding and stampedes. As a typical multimodal scene understanding task, image captioning has always attracted widespread attention. However, crowd scene understanding captioning is rarely studied due to the unobtainability of related datasets. Therefore, it is difficult to know what happens in crowd scenes. In order to fill this research gap, we propose a crowd scenes caption dataset named CrowdCaption which has the advantages of crowd-topic scenes, comprehensive and complex caption descriptions, typical relationships and detailed grounding annotations. The complexity and diversity of the descriptions and the specificity of the crowd scenes make this dataset extremely challenging to most current methods. Thus, we propose a Multi-hierarchical Attribute Guided Crowd Caption Network (MAGC) based on crowd objects, actions, and status (such as position, dress, posture, etc.) aiming to generate crowd-specific detailed descriptions. We conduct extensive experiments on our CrowdCaption dataset, and our proposed method reaches the state-of-the-art (SoTA) performance. We hope the CrowdCaption dataset can assist future studies related to crowd scenes in the multimodal domain. Our dataset and the code of the benchmark method will be released at “https://ivipclab.github.io”.
- 20 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 5400-5412
What Happens in Crowd Scenes: A New Dataset About Crowd Scenes for Image Captioning
Making machines endowed with eyes and brains to effectively understand and analyze crowd scenes is of paramount importance for building a smart city to serve people. This is of far-reaching significance for the guidance of dense crowds and accident prevention, such as crowding and stampedes. As a typical multimodal scene understanding task, image captioning has always attracted widespread attention. However, crowd scene understanding captioning is rarely studied due to the unobtainability of related datasets. Therefore, it is difficult to know what happens in crowd scenes. In order to fill this research gap, we propose a crowd scenes caption dataset named CrowdCaption which has the advantages of crowd-topic scenes, comprehensive and complex caption descriptions, typical relationships and detailed grounding annotations. The complexity and diversity of the descriptions and the specificity of the crowd scenes make this dataset extremely challenging to most current methods. Thus, we propose a Multi-hierarchical Attribute Guided Crowd Caption Network (MAGC) based on crowd objects, actions, and status (such as position, dress, posture, etc.) aiming to generate crowd-specific detailed descriptions. We conduct extensive experiments on our CrowdCaption dataset, and our proposed method reaches the state-of-the-art (SoTA) performance. We hope the CrowdCaption dataset can assist future studies related to crowd scenes in the multimodal domain. Our dataset and the code of the benchmark method will be released at “https://ivipclab.github.io”.