pith. sign in

arxiv: 2507.22051 · v3 · submitted 2025-07-29 · 💻 cs.HC

DataSway: Vivifying Metaphoric Visualization with Animation Clip Generation and Coordination

Liwenhan Xie , Jiayi Zhou , Anyi Rao , Huamin Qu , Xinhuan Shu This is my paper

Pith reviewed 2026-05-19 02:12 UTC · model grok-4.3

classification 💻 cs.HC
keywords metaphoric visualizationanimationhuman-AI co-creationvision-language modelsSVGdata visualizationtimeline coordinationuser study
0
0 comments X

The pith

A human-AI workflow uses vision-language models to generate and coordinate animation clips for metaphoric visualizations.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tries to establish that a human-AI co-creation workflow can help creators animate SVG-based metaphoric visualizations effectively. Users start by getting animation clips for data elements from vision-language models and then coordinate the timelines using entity order, attribute values, spatial layout, or randomness. This matters because it can make abstract data more understandable and engaging through motion that fits the metaphors. The authors tested this idea with a formative study of eight designers and a user study of fourteen participants who used their DataSway prototype. They also showed seven example cases in web hypermedia to illustrate the results.

Core claim

We propose a human-AI co-creation workflow that facilitates creating animations for SVG-based metaphoric visualizations. Users can initially derive animation clips for data elements from vision-language models and subsequently coordinate their timelines based on entity order, attribute values, spatial layout, or randomness. This workflow was informed by a formative study with experienced designers and implemented in the DataSway prototype, which was evaluated in a user study for creativity support and usability, with a gallery of seven cases demonstrating its applications.

What carries the argument

The human-AI co-creation workflow using vision-language models for animation clip generation and data-driven timeline coordination for SVG metaphoric visualizations.

If this is right

  • Animations can align semantically with metaphors while keeping data accurate.
  • Timelines can be coordinated flexibly based on multiple data or layout factors.
  • The system supports adding interactivity to the animations.
  • It enables practical use in web-based hypermedia as shown by the seven cases.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This could reduce the skill barrier for creating animated visualizations.
  • Coordination rules might be extended to support storytelling sequences in data presentations.
  • The approach may apply to other visualization types beyond metaphoric ones.

Load-bearing premise

Vision-language models can reliably produce animation clips whose motions align semantically with the chosen metaphors while preserving faithful data representation during animation.

What would settle it

A controlled viewing test measuring whether audiences correctly interpret the underlying data values or perceive the intended metaphor after seeing the generated animations.

Figures

Figures reproduced from arXiv: 2507.22051 by Anyi Rao, Huamin Qu, Jiayi Zhou, Liwenhan Xie, Xinhuan Shu.

Figure 1
Figure 1. Figure 1: A VLM-powered workflow to create animated metaphoric visualizations. In Stage I, a VLM interprets the visualization [PITH_FULL_IMAGE:figures/full_fig_p006_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The user interface of DataSway. (A) SVG preview panel. Users can also impose layout-centric coordination using direct [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: An illustration of spatial coordination supported [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: A gallery of animated metaphoric visualizations made by DataSway. [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Usability ratings on DataSway based on a 7-point [PITH_FULL_IMAGE:figures/full_fig_p012_5.png] view at source ↗
read the original abstract

Animating metaphoric visualizations brings data to life, enhancing the comprehension of abstract data encodings and fostering deeper engagement. However, creators face significant challenges in designing these animations, such as crafting motions that align semantically with the metaphors, maintaining faithful data representation during animation, and seamlessly integrating interactivity. We propose a human-AI co-creation workflow that facilitates creating animations for SVG-based metaphoric visualizations. Users can initially derive animation clips for data elements from vision-language models (VLMs) and subsequently coordinate their timelines based on entity order, attribute values, spatial layout, or randomness. Our design decisions were informed by a formative study with experienced designers (N=8). We further developed a prototype, DataSway, and conducted a user study (N=14) to evaluate its creativity support and usability. A gallery with seven cases demonstrates its capabilities and applications in web-based hypermedia. We conclude with implications for future research on bespoke data visualization animation.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper introduces DataSway, a human-AI co-creation workflow and prototype for animating SVG-based metaphoric visualizations. Users generate animation clips for data elements via vision-language models (VLMs) to align with metaphors, then coordinate clip timelines using strategies such as entity order, attribute values, spatial layout, or randomness. Design choices draw from a formative study (N=8) with experienced designers; the prototype is evaluated in a user study (N=14) on creativity support and usability, illustrated by a gallery of seven cases in web-based hypermedia.

Significance. If the workflow and evaluation hold, the work offers moderate significance for visualization and HCI by tackling semantic alignment and data fidelity in metaphoric animation design through an accessible AI-assisted process. It provides a concrete prototype and empirical feedback from designers, with potential to inform tools that enhance engagement in data-driven web content. The human-AI coordination focus and gallery examples are constructive contributions.

major comments (2)
  1. [§5 and §6] §5 (System Description) and §6 (User Study): The central claim that VLM-derived clips maintain faithful data representation (position, size, color encodings) while matching metaphors lacks any described validation step, constraint, or post-generation check. Without this, timeline coordination alone cannot guarantee fidelity if a clip alters mapped attributes, directly undermining the workflow's core promise of preserving data integrity during animation.
  2. [§6] §6 (User Study): The evaluation reports qualitative feedback on creativity support and usability from N=14 participants but provides no details on specific measures, controls, interview protocols, or analysis methods. This absence makes it impossible to assess whether the results robustly support the workflow's effectiveness claims.
minor comments (2)
  1. [Abstract and §4] The abstract and §4 (Formative Study) could more explicitly link specific designer pain points (e.g., motion crafting) to the four coordination strategies introduced later.
  2. [Gallery section] Figure captions and the gallery section would benefit from clearer indication of which coordination strategy is used in each of the seven cases.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive feedback on our manuscript. We address the major comments point by point below, and we will incorporate revisions where appropriate to improve the clarity and rigor of the paper.

read point-by-point responses

  1. Referee: [§5 and §6] §5 (System Description) and §6 (User Study): The central claim that VLM-derived clips maintain faithful data representation (position, size, color encodings) while matching metaphors lacks any described validation step, constraint, or post-generation check. Without this, timeline coordination alone cannot guarantee fidelity if a clip alters mapped attributes, directly undermining the workflow's core promise of preserving data integrity during animation.

    Authors: We acknowledge the validity of this concern. The current version of the manuscript does not explicitly describe a validation step or post-generation check for maintaining data fidelity in the VLM-generated animation clips. To strengthen the paper, we will revise §5 to include a detailed explanation of the prompt engineering strategies used to guide the VLM in preserving the visual encodings (such as specifying in prompts to keep position, size, and color unchanged while applying metaphoric motion). We will also add discussion of this aspect and potential limitations in the revised manuscript. This revision will better support the core promise of the workflow. revision: yes

  2. Referee: [§6] §6 (User Study): The evaluation reports qualitative feedback on creativity support and usability from N=14 participants but provides no details on specific measures, controls, interview protocols, or analysis methods. This absence makes it impossible to assess whether the results robustly support the workflow's effectiveness claims.

    Authors: We agree that additional details are necessary for a thorough evaluation of the user study. In the revised version, we will expand the description in §6 to specify the measures employed (including any standardized scales for creativity support and usability), the controls in the study design, the full interview protocol with example questions, and the qualitative analysis methods used (such as the process for thematic analysis). These additions will provide the necessary transparency to assess the robustness of our claims. revision: yes

Circularity Check

0 steps flagged

No circularity: workflow proposal validated by independent user studies

full rationale

The paper describes a human-AI co-creation workflow for generating and coordinating animation clips in SVG metaphoric visualizations, drawing on a formative study (N=8) to inform design decisions and a subsequent user study (N=14) plus gallery cases to evaluate creativity support and usability. No equations, fitted parameters, predictions, or first-principles derivations appear in the provided text; claims rest on empirical participant feedback and prototype demonstration rather than any reduction to self-referential inputs or self-citation chains. The contribution is self-contained as a design artifact evaluated against external benchmarks (user performance and qualitative responses).

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the domain assumption that designers encounter the listed challenges (semantic alignment, data fidelity, interactivity) and that VLMs plus simple coordination rules can address them; no free parameters or invented physical entities are introduced.

axioms (1)
  • domain assumption Creators face significant challenges in designing animations for metaphoric visualizations such as crafting semantically aligned motions, maintaining data representation, and integrating interactivity.
    Stated in the abstract as motivation and informed by the formative study with N=8 designers.

pith-pipeline@v0.9.0 · 5701 in / 1277 out tokens · 17742 ms · 2026-05-19T02:12:13.138683+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ReVis: Towards Reusable Image-Based Visualizations with MLLMs

    cs.HC 2026-04 unverdicted novelty 7.0

    ReVis parses image-based visualizations into a reusable DSL via an MLLM pipeline and supports reproduction, data updates, and customization through an interactive interface.

Reference graph

Works this paper leans on

85 extracted references · 85 canonical work pages · cited by 1 Pith paper · 1 internal anchor

  1. [1]

    Adobe Inc. 2025. After Effects. Retrieved April 1, 2025 from https://www.adobe. com/products/aftereffects.html

    work page 2025

  2. [2]

    Bilal Alsallakh, Wolfgang Aigner, Silvia Miksch, and M Eduard Gröller. 2012. Reinventing the contingency wheel: Scalable visual analytics of large categorical data. IEEE Transactions on Visualization and Computer Graphics 18, 12 (2012), 2849–2858. doi:10.1109/TVCG.2012.254

    work page doi:10.1109/tvcg.2012.254 2012

  3. [3]

    Fereshteh Amini, Nathalie Henry Riche, Bongshin Lee, Jason Leboe-McGowan, and Pourang Irani. 2018. Hooked on data videos: Assessing the effect of anima- tion and pictographs on viewer engagement. In Proceedings of the International Conference on Advanced Visual Interfaces (A VI). ACM, New York, NY, USA, Article 21, 9 pages. doi:10.1145/3206505.3206552

    work page doi:10.1145/3206505.3206552 2018

  4. [4]

    Fereshteh Amini, Nathalie Henry Riche, Bongshin Lee, Andres Monroy- Hernandez, and Pourang Irani. 2017. Authoring data-driven videos with Dat- aClips. IEEE Transactions on Visualization and Computer Graphics 23, 1 (2017), 501–510. doi:10.1109/TVCG.2016.2598647

    work page doi:10.1109/tvcg.2016.2598647 2017

  5. [5]

    Michael Behrisch, Michael Blumenschein, Nam Wook Kim, Lin Shao, Mennatallah El-Assady, Johannes Fuchs, Daniel Seebacher, Alexandra Diehl, Ulrik Brandes, Hanspeter Pfister, Tobias Schreck, Daniel Weiskopf, and Daniel Keim. 2018. Quality metrics for information visualization. Computer Graphics Forum 37, 3 (2018), 625–662. doi:10.1111/cgf.13446

    work page doi:10.1111/cgf.13446 2018

  6. [6]

    Rita Borgo, Johannes Kehrer, David HS Chung, Eamonn Maguire, Robert S Laramee, Helwig Hauser, Matthew Ward, and Min Chen. 2013. Glyph-based visualization: Foundations, design guidelines, techniques and applications. In Eurographics–State of the Art Reports . The Eurographics Association, Eindhoven, Netherlands, 39–63. doi:10.2312/conf/EG2013/stars/039-063

    work page doi:10.2312/conf/eg2013/stars/039-063 2013

  7. [7]

    Michelle A Borkin, Azalea A Vo, Zoya Bylinskii, Phillip Isola, Shashank Sunkavalli, Aude Oliva, and Hanspeter Pfister. 2013. What makes a visual- ization memorable? IEEE Transactions on Visualization and Computer Graphics 19, 12 (2013), 2306–2315. doi:10.1109/TVCG.2013.234

    work page doi:10.1109/tvcg.2013.234 2013

  8. [8]

    Michael Bostock, Vadim Ogievetsky, and Jeffrey Heer. 2011. D 3: Data-driven documents. IEEE Transactions on Visualization and Computer Graphics 17, 12 (2011), 2301–2309. doi:10.1109/TVCG.2011.185

    work page doi:10.1109/tvcg.2011.185 2011

  9. [9]

    Samuelle Bourgault, Li-Yi Wei, Jennifer Jacobs, and Rubaiat Habib Kazi. 2025. Narrative Motion Blocks: Combining Direct Manipulation and Natural Language Interactions for Animation Creation. In Proceedings of the ACM Conference on Designing Interactive Systems (DIS). ACM, New York, NY, USA, 1366–1386. doi:10. 1145/3715336.3735766

    work page arXiv 2025

  10. [10]

    Yining Cao, Jane L E, Zhu-Tian Chen, and Haijun Xia. 2023. DataParticles: Block-based and language-oriented authoring of animated unit visualizations. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI) . ACM, New York, NY, USA, Article 808, 15 pages. doi:10.1145/3544548.3581472

    work page doi:10.1145/3544548.3581472 2023

  11. [11]

    Longfei Chen, Shengxin Li, Ziang Li, and Quan Li. 2025. DancingBoard: Stream- lining the Creation of Motion Comics to Enhance Narratives. In Proceedings of the 30th International Conference on Intelligent User Interfaces . ACM, New York, NY, USA, 477–503. doi:10.1145/3708359.3712167

    work page doi:10.1145/3708359.3712167 2025

  12. [12]

    Qing Chen, Wei Shuai, Jiyao Zhang, Zhida Sun, and Nan Cao. 2024. Beyond numbers: Creating analogies to enhance data comprehension and communication with generative AI. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI) . ACM, New York, NY, USA, Article 377, 14 pages. doi:10.1145/3613904.3642480

    work page doi:10.1145/3613904.3642480 2024

  13. [13]

    Herman Chernoff. 1973. The use of faces to represent points in k-dimensional space graphically. J. Amer. Statist. Assoc. 68, 342 (1973), 361–368

    work page 1973

  14. [14]

    Erin Cherry and Celine Latulipe. 2014. Quantifying the creativity support of digital tools through the creativity support index.ACM Transactions on Computer- Human Interaction 21, 4, Article 21 (2014), 25 pages. doi:10.1145/2617588

    work page doi:10.1145/2617588 2014

  15. [15]

    Fanny Chevalier, Nathalie Henry Riche, Catherine Plaisant, Amira Chalbi, and Christophe Hurter. 2016. Animations 25 years later: New roles and opportunities. In Proceedings of the International Conference on Advanced Visual Interfaces (A VI) . ACM, New York, NY, USA, 280–287. doi:10.1145/2909132.2909255

    work page doi:10.1145/2909132.2909255 2016

  16. [16]

    John Joon Young Chung and Eytan Adar. 2023. PromptPaint: Steering text-to- image generation through paint medium-like interactions. In Proceedings of the Symposium on User Interface Software and Technology (UIST) . ACM, New York, NY, USA, Article 6, 17 pages. doi:10.1145/3586183.3606777

    work page doi:10.1145/3586183.3606777 2023

  17. [17]

    Darius Coelho and Klaus Mueller. 2020. Infomages: Embedding data into thematic images. Computer Graphics Forum 39, 3 (2020), 593–606. doi:10.1111/cgf.14004

    work page doi:10.1111/cgf.14004 2020

  18. [18]

    Peitong Duan, Jeremy Warner, Yang Li, and Bjoern Hartmann. 2024. Generating automatic feedback on UI mockups with large language models. InProceedings of the ACM Conference on Human Factors in Computing Systems (CHI) . ACM, New York, NY, USA, Article 6, 20 pages. doi:10.1145/3613904.3642782

    work page doi:10.1145/3613904.3642782 2024

  19. [19]

    Rinon Gal, Yael Vinker, Yuval Alaluf, Amit Bermano, Daniel Cohen-Or, Ariel Shamir, and Gal Chechik. 2024. Breathing life into sketches using text- to-video priors. In Proceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR) . IEEE, Piscataway, NJ, USA, 4325–4336. doi:10.1109/CVPR52733.2024.00414

    work page doi:10.1109/cvpr52733.2024.00414 2024

  20. [20]

    Lin Gao, Leixian Shen, Yuheng Zhao, Jiexiang Lan, Huamin Qu, and Siming Chen. 2025. SceneLoom: Communicating Data with Scene Context. (2025). arXiv:2507.16466 Accepted to IEEE VIS 2025

    work page arXiv 2025

  21. [21]

    Julian Garnier. 2025. anime.js. Retrieved April 1, 2025 from https://animejs.com/

    work page 2025

  22. [22]

    Tong Ge, Bongshin Lee, and Yunhai Wang. 2021. Cast: Authoring data-driven chart animations. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI). ACM, New York, NY, USA, Article 24, 15 pages. doi:10. 1145/3411764.3445452

    work page arXiv 2021

  23. [23]

    Yuwei Guo, Ceyuan Yang, Anyi Rao, Yaohui Wang, Yu Qiao, Dahua Lin, and Bo Dai. 2024. AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning. In Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net, 19 pages. arXiv:2307.04725 https://openreview.net/pdf?id=Fx2SbBgcte

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  24. [24]

    Samuel Huron, Romain Vuillemot, and Jean-Daniel Fekete. 2013. Visual sedimen- tation. IEEE Transactions on Visualization and Computer Graphics 19, 12 (2013), 2446–2455. doi:10.1109/TVCG.2013.227

    work page doi:10.1109/tvcg.2013.227 2013

  25. [25]

    Rive Inc. 2025. Rive. Retrieved April 1, 2025 from https://rive.app/

    work page 2025

  26. [26]

    Rubaiat Habib Kazi, Fanny Chevalier, Tovi Grossman, Shengdong Zhao, and George Fitzmaurice. 2014. Draco: Bringing life to illustrations with kinetic textures. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI). ACM, New York, NY, USA, 351–360. doi:10.1145/2556288.2556987

    work page doi:10.1145/2556288.2556987 2014

  27. [27]

    Tae Soo Kim, DaEun Choi, Yoonseo Choi, and Juho Kim. 2022. Stylette: Styling the web with natural language. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI). ACM, New York, NY, USA, Article 5, 17 pages. doi:10.1145/3491102.3501931

    work page doi:10.1145/3491102.3501931 2022

  28. [29]

    Xingyu Lan, Yang Shi, Yanqiu Wu, Xiaohan Jiao, and Nan Cao. 2021. Kineticharts: Augmenting Affective Expressiveness of Charts in Data Stories with Animation Design. IEEE Transactions on Visualization and Computer Graphics 28, 1 (2021), 933–943. doi:10.1109/TVCG.2021.3114775

    work page doi:10.1109/tvcg.2021.3114775 2021

  29. [30]

    Xingyu Lan, Yanqiu Wu, and Nan Cao. 2023. Affective visualization design: Leveraging the emotional impact of data. IEEE Transactions on Visualization and Computer Graphics 30, 1 (2023), 1–11. doi:10.1109/TVCG.2023.3327385

    work page doi:10.1109/tvcg.2023.3327385 2023

  30. [31]

    Zhengqi Li, Richard Tucker, Noah Snavely, and Aleksander Holynski. 2024. Gen- erative image dynamics. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE, Piscataway, NJ, USA, 24142–24153. doi:10.1109/CVPR52733.2024.02279

    work page doi:10.1109/cvpr52733.2024.02279 2024

  31. [32]

    Can Liu, Yu Zhang, Cong Wu, Chen Li, and Xiaoru Yuan. 2024. A spatial con- straint model for manipulating static visualizations. ACM Transactions on Inter- active Intelligent Systems 14, 2, Article 12 (2024), 29 pages. doi:10.1145/3657642

    work page doi:10.1145/3657642 2024

  32. [33]

    Vivian Liu, Rubaiat Habib Kazi, Li-Yi Wei, Matthew Fisher, Timothy Langlois, Seth Walker, and Lydia Chilton. 2025. LogoMotion: Visually grounded code generation for content-aware animation. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI). ACM, New York, NY, USA, Article 157, 16 pages. doi:10.1145/3706598.3714155

    work page doi:10.1145/3706598.3714155 2025

  33. [34]

    Zichen Liu, Yihao Meng, Hao Ouyang, Yue Yu, Bolin Zhao, Daniel Cohen-Or, and Huamin Qu. 2025. Dynamic typography: Bringing text to life via video diffusion prior. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). arXiv:2404.11614 Just Accepted

    work page arXiv 2025

  34. [35]

    Zhicheng Liu, John Thompson, Alan Wilson, Mira Dontcheva, James Delorey, Sam Grigg, Bernard Kerr, and John Stasko. 2018. Data Illustrator: Augmenting vector design tools with lazy data binding for expressive visualization authoring. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI). ACM, New York, NY, USA, 13 pages. doi:10.1...

    work page doi:10.1145/3173574.3173697 2018

  35. [36]

    Min Lu, Noa Fish, Shuaiqi Wang, Joel Lanir, Daniel Cohen-Or, and Hui Huang

    work page

  36. [38]

    Giorgia Lupi and Stefanie Posavec. 2016. Dear data. Chronicle books

    work page 2016

  37. [39]

    Jiaju Ma and Maneesh Agrawala. 2025. MoVer: Motion verification for motion graphics animations. ACM Transactions on Graphics 44, 4, Article 33 (2025), 17 pages. doi:10.1145/3731209

    work page doi:10.1145/3731209 2025

  38. [40]

    Damien Masson, Sylvain Malacria, Géry Casiez, and Daniel Vogel. 2024. Direct- GPT: A direct manipulation interface to interact with large language models. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI) . ACM, New York, NY, USA, Article 975, 16 pages. doi:10.1145/3613904.3642462

    work page doi:10.1145/3613904.3642462 2024

  39. [41]

    Anna Offenwanger, Matthew Brehmer, Fanny Chevalier, and Theophanis Tsandi- las. 2023. Timesplines: Sketch-based authoring of flexible and idiosyncratic timelines. IEEE Transactions on Visualization and Computer Graphics 30, 1 (2023), 34–44. doi:10.1109/TVCG.2023.3326520

    work page doi:10.1109/tvcg.2023.3326520 2023

  40. [42]

    Anna Offenwanger, Theophanis Tsandilas, and Fanny Chevalier. 2025. DataGar- den: Formalizing personal sketches into structured visualization templates. IEEE Transactions on Visualization and Computer Graphics 31, 1 (2025), 1268–1278. doi:10.1109/TVCG.2024.3456336

    work page doi:10.1109/tvcg.2024.3456336 2025

  41. [43]

    OpenAI. 2025. ChatGPT. Retrieved April 1, 2025 from https://chatgpt.com/

    work page 2025

  42. [44]

    Hana Pokojná, Tobias Isenberg, Stefan Bruckner, Barbora Kozlíková, and Laura Garrison. 2025. The language of infographics: Toward understanding conceptual metaphor use in scientific storytelling. IEEE Transactions on Visualization and Liwenhan Xie, Jiayi Zhou, Anyi Rao, Huamin Qu, and Xinhuan Shu Computer Graphics 31, 1 (2025), 371–381. doi:10.1109/TVCG.2...

    work page doi:10.1109/tvcg.2024.3456327 2025

  43. [46]

    Casey Reas and Ben Fry. 2006. Processing: Programming for the media arts. AI & Society 20, 4 (2006), 526–538. doi:10.1007/s00146-006-0050-9

    work page doi:10.1007/s00146-006-0050-9 2006

  44. [47]

    Donghao Ren, Matthew Brehmer, Bongshin Lee, Tobias Hollerer, and Eun Kyoung Choe. 2017. ChartAccent: Annotation for data-driven storytelling. In Proceedings of the IEEE PacificVis Conference . IEEE, Pitscataway, NJ, USA, 230–239. doi:10. 1109/pacificvis.2017.8031599

    work page arXiv 2017

  45. [48]

    Hugo Romat, Caroline Appert, and Emmanuel Pietriga. 2019. Expressive author- ing of node-link diagrams with Graphies. IEEE Transactions on Visualization and Computer Graphics 27, 4 (2019), 2329–2340. doi:10.1109/TVCG.2019.2950932

    work page doi:10.1109/tvcg.2019.2950932 2019

  46. [49]

    Arvind Satyanarayan, Bongshin Lee, Donghao Ren, Jeffrey Heer, John Stasko, John Thompson, Matthew Brehmer, and Zhicheng Liu. 2019. Critical reflections on visualization authoring systems. IEEE Transactions on Visualization and Computer Graphics 26, 1 (2019), 461–471. doi:10.1109/TVCG.2019.2934281

    work page doi:10.1109/tvcg.2019.2934281 2019

  47. [50]

    Leixian Shen, Haotian Li, Yun Wang, Tianqi Luo, Yuyu Luo, and Huamin Qu

    work page

  48. [52]

    Leixian Shen, Yizhi Zhang, Haidong Zhang, and Yun Wang. 2024. Data Player: Automatic generation of data videos with narration-animation interplay. IEEE Transactions on Visualization and Computer Graphics 30, 1 (2024), 109–119. doi:10. 1109/TVCG.2023.3327197

    work page arXiv 2024

  49. [53]

    Yuancheng Shen, Yue Zhao, Yunhai Wang, Tong Ge, Haoyan Shi, and Bongshin Lee. 2025. Authoring data-driven chart animations. IEEE Transactions on Visual- ization and Computer Graphics 31, 2 (2025), 1613–1630. doi:10.1109/TVCG.2024. 3491504

    work page doi:10.1109/tvcg.2024 2025

  50. [54]

    Danqing Shi, Fuling Sun, Xinyue Xu, Xingyu Lan, David Gotz, and Nan Cao

    work page

  51. [55]

    Computer Graphics Forum 40, 3 (2021), 495–505

    AutoClips: An automatic approach to video generation from data facts. Computer Graphics Forum 40, 3 (2021), 495–505. doi:10.1111/cgf.14324

    work page doi:10.1111/cgf.14324 2021

  52. [56]

    Yang Shi, Tian Gao, Xiaohan Jiao, and Nan Cao. 2023. Understanding design collaboration between designers and artificial intelligence: A systematic literature review. Proceedings of the ACM on Human-Computer Interaction7, CSCW2, Article 368 (2023), 35 pages. doi:10.1145/3610217

    work page doi:10.1145/3610217 2023

  53. [57]

    Yang Shi, Xingyu Lan, Jingwen Li, Zhaorui Li, and Nan Cao. 2021. Communicating with motion: A design space for animated visual narratives in data videos. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI) . ACM, New York, NY, USA, Article 605, 13 pages. doi:10.1145/3411764.3445337

    work page doi:10.1145/3411764.3445337 2021

  54. [58]

    Xinhuan Shu, Aoyu Wu, Junxiu Tang, Benjamin Bach, Yingcai Wu, and Huamin Qu. 2021. What makes a Data-GIF understandable? IEEE Transactions on Visual- ization and Computer Graphics 27, 02 (2021), 1492–1502. doi:10.1109/TVCG.2020. 3030396

    work page doi:10.1109/tvcg.2020 2021

  55. [59]

    Hariharan Subramonyam, Roy Pea, Christopher Lawrence Pondoc, Maneesh Agrawala, and Colleen Seifert. 2024. Bridging the gulf of envisioning: Cognitive design challenges in LLM interfaces. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI) . ACM, New York, NY, USA, Article 1039, 19 pages. doi:10.1145/3613904.3642754

    work page doi:10.1145/3613904.3642754 2024

  56. [60]

    SVGator. 2025. SVGator. Retrieved April 1, 2025 from https://www.svgator.com/

    work page 2025

  57. [61]

    John Thompson, Zhicheng Liu, Wilmot Li, and John Stasko. 2020. Understanding the design space and authoring paradigms for animated data graphics. Computer Graphics Forum 39, 3 (2020), 207–218. doi:10.1111/cgf.13974

    work page doi:10.1111/cgf.13974 2020

  58. [62]

    John Thompson, Zhicheng Liu, and John Stasko. 2021. Data Animator: Authoring expressive animated data graphics. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI) . ACM, New York, NY, USA, Article 15, 18 pages. doi:10.1145/3411764.3445747

    work page doi:10.1145/3411764.3445747 2021

  59. [63]

    Gleb Tkachev, Rene Cutura, Michael Sedlmair, Steffen Frey, and Thomas Ertl

    work page

  60. [64]

    In Extended Abstracts on Human Factors in Computing Systems (CHI EA)

    Metaphorical visualization: Mapping data to familiar concepts. In Extended Abstracts on Human Factors in Computing Systems (CHI EA) . ACM, New York, NY, USA, Article 10, 10 pages. doi:10.1145/3491101.3516393

    work page doi:10.1145/3491101.3516393

  61. [65]

    Tiffany Tseng, Ruijia Cheng, and Jeffrey Nichols. 2024. Keyframer: Empowering animation design using large language models. arXiv:2402.06071

    work page arXiv 2024

  62. [66]

    1983.The visual display of quantitative information

    Edward R Tufte and Peter R Graves-Morris. 1983.The visual display of quantitative information. Graphics press Cheshire, CT

    work page 1983

  63. [67]

    Barbara Tversky, Julie Bauer Morrison, and Mireille Betrancourt. 2002. Anima- tion: Can it facilitate? International Journal of Human-Computer Studies 57, 4 (2002), 247–262. doi:10.1006/ijhc.2002.1017

    work page doi:10.1006/ijhc.2002.1017 2002

  64. [68]

    Jagoda Walny, Christian Frisson, Mieka West, Doris Kosminsky, Søren Knudsen, Sheelagh Carpendale, and Wesley Willett. 2019. Data changes everything: Chal- lenges and opportunities in data visualization design handoff. IEEE Transactions on Visualization and Computer Graphics 26, 1 (2019), 12–22. doi:10.1109/TVCG. 2019.2934538

    work page doi:10.1109/tvcg 2019

  65. [69]

    Yun Wang, Yi Gao, Ray Huang, Weiwei Cui, Haidong Zhang, and Dongmei Zhang. 2021. Animated presentation of static infographics with InfoMotion. Computer Graphics Forum 40, 3 (2021), 507–518. doi:10.1111/cgf.14325

    work page doi:10.1111/cgf.14325 2021

  66. [70]

    Yun Wang, Leixian Shen, Zhengxin You, Xinhuan Shu, Bongshin Lee, John Thompson, Haidong Zhang, and Dongmei Zhang. 2024. WonderFlow: Narration- centric design of animated data videos. IEEE Transactions on Visualization and Computer Graphics (2024), 17 pages. doi:10.1109/TVCG.2024.3411575 Early Access

    work page doi:10.1109/tvcg.2024.3411575 2024

  67. [71]

    Zhenyu Wang and Min Lu. 2025. Image-Space Collage and Packing with Dif- ferentiable Rendering. In Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference (SIGGRAPH) . ACM, New York, NY, USA, Article 172, 11 pages. doi:10.1145/3721238.3730690

    work page doi:10.1145/3721238.3730690 2025

  68. [72]

    Nora S Willett, Wilmot Li, Jovan Popovic, Floraine Berthouzoz, and Adam Finkel- stein. 2017. Secondary motion for performed 2D animation. In Proceedings of the Symposium on User Interface Software and Technology (UIST) . ACM, New York, NY, USA, 97–108. doi:10.1145/3126594.3126641

    work page doi:10.1145/3126594.3126641 2017

  69. [73]

    Greg Woodin, Bodo Winter, and Lace Padilla. 2021. Conceptual metaphor and graphical convention influence the interpretation of line graphs. IEEE Transactions on Visualization and Computer Graphics 28, 2 (2021), 1209–1221. doi:10.1109/TVCG.2021.3088343

    work page doi:10.1109/tvcg.2021.3088343 2021

  70. [74]

    Ronghuan Wu, Wanchao Su, and Jing Liao. 2025. LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization. (2025). arXiv:2505.23740

    work page arXiv 2025

  71. [75]

    Ronghuan Wu, Wanchao Su, Kede Ma, and Jing Liao. 2024. AniClipart: Clipart animation with text-to-video priors. International Journal of Computer Vision (2024), 17 pages. doi:10.1007/s11263-024-02306-1

    work page doi:10.1007/s11263-024-02306-1 2024

  72. [76]

    Haijun Xia, Nathalie Henry Riche, Fanny Chevalier, Bruno De Araujo, and Daniel Wigdor. 2018. DataInk: Direct and creative data-oriented drawing. InProceedings of the ACM Conference on Human Factors in Computing Systems (CHI) . ACM, New York, NY, USA, Article 223, 13 pages. doi:10.1145/3173574.3173797

    work page doi:10.1145/3173574.3173797 2018

  73. [77]

    Shishi Xiao, Suizi Huang, Yue Lin, Yilin Ye, and Wei Zeng. 2023. Let the chart spark: Embedding semantic context into chart with text-to-image generative model. IEEE Transactions on Visualization and Computer Graphics 30, 1 (2023), 284–294. doi:10.1109/TVCG.2023.3326913

    work page doi:10.1109/tvcg.2023.3326913 2023

  74. [78]

    Liwenhan Xie, Yanna Lin, Can Liu, Huamin Qu, and Xinhuan Shu. 2025. DataWink: Reusing and Adapting SVG-based Visualization Examples with Large Multimodal Models. (2025). arXiv:2507.17734 Accepted to IEEE VIS 2025

    work page arXiv 2025

  75. [79]

    Liwenhan Xie, Xinhuan Shu, Jeon Cheol Su, Yun Wang, Siming Chen, and Huamin Qu. 2024. Creating emordle: Animating word cloud for emotion ex- pression. IEEE Transactions on Visualization and Computer Graphics 30, 8 (2024), 5198–5211. doi:10.1109/TVCG.2023.3286392

    work page doi:10.1109/tvcg.2023.3286392 2024

  76. [80]

    Liwenhan Xie, Zhaoyu Zhou, Kerun Yu, Yun Wang, Huamin Qu, and Siming Chen. 2023. Wakey-Wakey: Animate text by mimicking characters in a GIF. In Proceedings of the Symposium on User Interface Software and Technology (UIST) . ACM, New York, NY, USA, Article 98, 14 pages. doi:10.1145/3586183.3606813

    work page doi:10.1145/3586183.3606813 2023

  77. [81]

    Liuhuaying Yang. 2023. Four seasons: How has the world progressed in recent years. Retrieved April 1, 2025 from https://www.go4trees.com/four-seasons/ Interactive Winner of the 2023 World Dataviz Prize

    work page 2023

  78. [82]

    Yiying Yang, Wei Cheng, Sijin Chen, Xianfang Zeng, Fukun Yin, Jiaxu Zhang, Liao Wang, Gang Yu, Xingjun Ma, and Yu-Gang Jiang. 2025. Omnisvg: A unified scalable vector graphics generation model. (2025). arXiv:2504.06263

    work page arXiv 2025

  79. [83]

    Lu Ying, Xinhuan Shu, Dazhen Deng, Yuchen Yang, Tan Tang, Lingyun Yu, and Yingcai Wu. 2022. MetaGlyph: Automatic generation of metaphoric glyph-based visualization. IEEE Transactions on Visualization and Computer Graphics 29, 1 (2022), 331–341. doi:10.1109/TVCG.2022.3209447

    work page doi:10.1109/tvcg.2022.3209447 2022

  80. [84]

    Bao Zhang, Zihan Li, Zhenglei Liu, Huanchen Wang, and Yuxin Ma. 2025. In- tegrating Large Language Models into Text Animation: An Intelligent Editing System with Inline and Chat Interaction. arXiv preprint arXiv:2506.10762 (2025)

    work page arXiv 2025

Showing first 80 references.