DataMagic: Transforming Tabular Data into Data Insight Video

• URL: http://arxiv.org/abs/2606.20388v1
• Date: Thu, 18 Jun 2026 15:45:05 GMT
• Title: DataMagic: Transforming Tabular Data into Data Insight Video
• Abstract summary: Data videos integrate dynamic charts, voice narration, and synchronized animations to communicate data insights as temporal narratives.<n>Existing approaches fall short: static visualization tools lack narrative logic and animation.<n>We demonstrate DataMagic, an end-to-end interactive system that transforms natural language queries into narrative data-insight videos.
• Score: 15.163664003655631
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data videos integrate dynamic charts, voice narration, and synchronized animations to communicate data insights as temporal narratives, making them an effective medium for improving data consumption efficiency in the data management lifecycle. However, producing high-quality data videos requires expertise spanning data analysis, narrative design, and video production. Existing approaches fall short: static visualization tools (e.g., BI dashboards) lack narrative logic and animation; authoring tools require users to pre-prepare visualizations rather than working from raw data; pixel-level video generation models cannot guarantee data fidelity or provenance. We demonstrate DataMagic, an end-to-end interactive system that transforms raw tabular data and natural language queries into narrative data-insight videos. To ensure data fidelity, DataMagic introduces the declarative specification DVSpec, which binds visual and animation elements to underlying data fields through data-driven semantic references. To address the combinatorial explosion of the design space, DataMagic adopts a Generate-then-Orchestrate multi-agent architecture that generates candidate scenes in parallel and then optimizes narrative coherence through global orchestration. Leveraging DVSpec's decoupling of logic and rendering, the system further supports three interaction modes and structured provenance-based data Q&A, transforming one-way videos into explorable interactive data interfaces. Evaluation on 109 real-world samples validates the effectiveness of the DataMagic. Homepage: https://datamagic-home.github.io/

Related papers

• DATAREEL: Automated Data-Driven Video Story Generation with Animations [40.67215506530081]
  We introduce DataReel, a benchmark for automated data-driven video story generation.<n>Each story pairs structured data, a chart visualization, and a narration transcript.<n>We propose a multi-agent framework that decomposes the task into planning, generation, and verification stages.
  arXiv  Detail & Related papers  (2026-04-28T04:56:25Z)
• Lifting Unlabeled Internet-level Data for 3D Scene Understanding [56.35787129098819]
  We demonstrate that carefully designed data engines can leverage web-curated, unlabeled videos to automatically generate training data.<n>We identify and analyze bottlenecks in automated data generation, revealing critical factors that determine the efficiency and effectiveness of learning from unlabeled data.
  arXiv  Detail & Related papers  (2026-04-02T11:26:44Z)
• VDCook:DIY video data cook your MLLMs [3.170179753848826]
  VDCook is a self-evolving video data operating system for researchers and vertical domain teams.<n>It generates in-domain data packages with complete provenance and metadata, along with reproducible Notebooks.
  arXiv  Detail & Related papers  (2026-03-04T10:39:04Z)
• Sparrow: Data-Efficient Video-LLM with Text-to-Image Augmentation [57.34255010956452]
  This work revisits scaling with synthetic data and focuses on developing video-LLMs from a data-centric perspective.<n>We propose a data augmentation method called Sparrow, which synthesizes video-like samples from pure text instruction data.<n>Our proposed method achieves performance comparable to or even superior to that of baselines trained with significantly more samples.
  arXiv  Detail & Related papers  (2024-11-29T18:59:54Z)
• Feature-Action Design Patterns for Storytelling Visualizations with Time Series Data [14.417710088310784]
  We present a method to create storytelling visualization with time series data. Motivated by the need to communicate time series data during the COVID-19 pandemic, we developed a novel computer-assisted method for meta-authoring of stories.
  arXiv  Detail & Related papers  (2024-02-05T15:45:59Z)
• VEATIC: Video-based Emotion and Affect Tracking in Context Dataset [34.77364955121413]
  We introduce a brand new large dataset, the Video-based Emotion and Affect Tracking in Context dataset (VEATIC) VEATIC has 124 video clips from Hollywood movies, documentaries, and home videos with continuous valence and arousal ratings of each frame via real-time annotation. Along with the dataset, we propose a new computer vision task to infer the affect of the selected character via both context and character information in each video frame.
  arXiv  Detail & Related papers  (2023-09-13T06:31:35Z)
• OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation [8.149870655785955]
  OmniDataComposer is an innovative approach for multimodal data fusion and unlimited data generation. It is capable of identifying over 6400 categories of objects, substantially broadening the spectrum of visual information. It amalgamates diverse modalities, promoting reciprocal enhancement among modalities and facilitating cross-modal data correction.
  arXiv  Detail & Related papers  (2023-08-08T08:30:16Z)
• A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wild [72.0226493284814]
  We propose a unified framework for event-based frame that performs deblurring ad-hoc.<n>Our network consistently outperforms previous state-of-the-art methods on frame, single image deblurring, and the joint task of both.
  arXiv  Detail & Related papers  (2023-01-12T18:19:00Z)
• TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments [84.6017003787244]
  This work proposes a synthetic data generation pipeline to address the difficulties and domain-gaps present in simulated datasets. We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation.
  arXiv  Detail & Related papers  (2022-08-16T20:46:08Z)
• HighlightMe: Detecting Highlights from Human-Centric Videos [52.84233165201391]
  We present a domain- and user-preference-agnostic approach to detect highlightable excerpts from human-centric videos. We use an autoencoder network equipped with spatial-temporal graph convolutions to detect human activities and interactions. We observe a 4-12% improvement in the mean average precision of matching the human-annotated highlights over state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-10-05T01:18:15Z)
• Automatic Curation of Large-Scale Datasets for Audio-Visual Representation Learning [62.47593143542552]
  We describe a subset optimization approach for automatic dataset curation. We demonstrate that our approach finds videos with high audio-visual correspondence and show that self-supervised models trained on our data, despite being automatically constructed, achieve similar downstream performances to existing video datasets with similar scales.
  arXiv  Detail & Related papers  (2021-01-26T14:27:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.