CoChat
Sign Up
Cited by 45Data Visualization and AnalyticsDigital Media and Visual ArtComputer Graphics and Visualization Techniques

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Data Player: Automatic Generation of Data Videos with Narration-Animation Interplay

Open access
Shen, Leixian, Zhang, Yizhi, Zhang, Haidong, Wang, Yun·2024·IEEE Transactions on Visualization and Computer Graphics
DOI 10.1109/tvcg.2023.3327197
Open this paper in CoChat — free accountOpen PDF

Abstract

Data visualizations and narratives are often integrated to convey data stories effectively. Among various data storytelling formats, data videos have been garnering increasing attention. These videos provide an intuitive interpretation of data charts while vividly articulating the underlying data insights. However, the production of data videos demands a diverse set of professional skills and considerable manual labor, including understanding narratives, linking visual elements with narration segments, designing and crafting animations, recording audio narrations, and synchronizing audio with visual animations. To simplify this process, our paper introduces a novel method, referred to as Data Player, capable of automatically generating dynamic data videos with narration-animation interplay. This approach lowers the technical barriers associated with creating data videos rich in narration. To enable narration-animation interplay, Data Player constructs references between visualizations and text input. Specifically, it first extracts data into tables from the visualizations. Subsequently, it utilizes large language models to form semantic connections between text and visuals. Finally, Data Player encodes animation design knowledge as computational low-level constraints, allowing for the recommendation of suitable animation presets that align with the audio narration produced by text-to-speech technologies. We assessed Data Player's efficacy through an example gallery, a user study, and expert interviews. The evaluation results demonstrated that Data Player can generate high-quality data videos that are comparable to human-composed ones.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tvcg.2023.3327197

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Pioneering tools applying text-to-image models and LLMs were published in VIS 2023 in Oct. 2023.

    “there were pioneering ones that apply text-to-image models [41] and LLMs [34, 30, 24] published in VIS 2023 in Oct. 2023.”

    From Reflection on Data Storytelling Tools in the Generative AI Era from the Human-AI Collaboration Perspective (2025) · cites this paper as [30]

    The paper’s “4.3.2 Linking by an LLM” section describes Data Player as a tool that uses an LLM to link narration with visual elements, supporting its use as an example of an LLM-based tool. The passages in our copy do not establish that it was published at VIS 2023 in October 2023; searches for that venue and date found no confirming passage. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 66

  1. Chatgpt prompt engineering for developers
  2. Ffmpeg multimedia framework
  3. Gsap animation platform
  4. Microsoft azure text-to-speech service
  5. 10.1145/2702123.2702431 · DOI
  6. 10.1145/3206505.3206552 · DOI
  7. 10.1109/TVCG.2016.2598647 · DOI
  8. 10.1109/TVCG.2018.2865119 · DOI
  9. 10.1145/3544548.3581472 · DOI
  10. 10.1145/3491102.3517485 · DOI
  11. 10.1111/cgf.14560 · DOI
  12. 10.1145/3472749.3474778 · DOI
  13. 10.1145/3379337.3415814 · DOI
  14. 10.1007/BF01320076 · DOI
  15. 10.1145/3242587.3242600 · DOI
  16. 10.1007/978-3-540-78800-3_24 · DOI · Paper page
  17. 10.1145/3411764.3445452 · DOI
  18. 10.1111/cgf.14005 · DOI
  19. 10.1109/TVCG.2007.70539 · DOI
  20. 10.1109/VISUAL.2019.8933695 · DOI
  21. 10.1145/3210825.3210826 · DOI
  22. 10.1145/3242587.3242617 · DOI
  23. 10.1109/TVCG.2020.3030360 · DOI
  24. 10.1109/VIS49827.2021.9623291 · DOI
  25. 10.1145/2556288.2557241 · DOI
  26. 10.1145/3313831.3376443 · DOI
  27. 10.1109/TVCG.2021.3114775 · DOI
  28. 10.1109/TVCG.2021.3114802 · DOI
  29. Li, 2023, Why is AI not a Panacea for Data Workers?, An Interview Study on Human-AI Collaboration in Data Storytelling
  30. 10.1145/3491102.3502048 · DOI
  31. 10.1145/3544548.3581470 · DOI
  32. 10.1109/TVCG.2023.3251344 · DOI
  33. 10.1145/3588942 · DOI
  34. 10.1145/3544548.3581091 · DOI
  35. 10.1111/cgf.13195 · DOI
  36. 10.1145/3172944.3173007 · DOI
  37. 10.1109/TVCG.2018.2865240 · DOI
  38. 10.1109/PACIFICVIS.2017.8031599 · DOI
  39. 10.1145/3544548.3580964 · DOI
  40. 10.1007/978-1-4939-0378-8_15 · DOI
  41. 10.1109/TVCG.2010.179 · DOI · Paper page
  42. 10.1109/iV.2018.00075 · DOI
  43. 10.1145/3584931.3607492 · DOI · Paper page
  44. 10.1109/TVCG.2022.3148007 · DOI
  45. 10.2312/evs.20211061 · DOI
  46. 10.1145/3511808.3557159 · DOI
  47. 10.1007/s41019-022-00195-3 · DOI
  48. 10.1109/TVCG.2023.3238909 · DOI
  49. 10.1111/cgf.14324 · DOI
  50. 10.1145/3411764.3445337 · DOI
  51. 10.1109/TVCG.2018.2865145 · DOI
  52. 10.1145/3411764.3445354 · DOI
  53. 10.1145/3313831.3376593 · DOI
  54. 10.1111/cgf.13974 · DOI
  55. 10.1145/3411764.3445747 · DOI
  56. 10.1006/ijhc.2002.1017 · DOI
  57. 10.1111/cgf.14325 · DOI
  58. 10.1109/TVCG.2022.3209357 · DOI
  59. Wang, 2023, WonderFlow: Narration-Centric Design of Animated Data Videos, 1
  60. 10.1109/TVCG.2021.3099002 · DOI
  61. 10.1145/3491102.3517582 · DOI
  62. 10.1109/TVCG.2023.3286392 · DOI
  63. 10.1145/2642918.2647398 · DOI
  64. 10.1109/TVCG.2022.3209447 · DOI
  65. 10.1111/cgf.13719 · DOI
  66. 10.1109/TVCG.2022.3209369 · DOI

Cited by

Sorted by citations

Metadata

Authors
Shen, L., Zhang, Y., Zhang, H., & Wang, Y.
Affiliations
  • Hong Kong University of Science and Technology (HK)
  • Cornell University (US)
  • Microsoft Research Asia (China) (CN)
ORCID
Venue
IEEE Transactions on Visualization and Computer Graphics
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2024-01
Volume
30
Issue
1
Pages
109-119
ISSN
  • 1077-2626 (ISSN-L)
  • 1941-0506
  • 2160-9306
DOI
10.1109/tvcg.2023.3327197
OpenAlex
W4388286232
Cited by
45
References
3
Citations by year
2026: 12 · 2025: 18 · 2024: 15
FWCI
4.09
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Transactions on Visualization and Computer Graphics (publishedVersion)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by-sa)
  • Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Data Visualization and Analytics
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
Keywords
data storytelling, automatic video generation, text-to-speech, large language models, audio-video synchronization, data visualization

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review