Modality: Video ×Clear filters

Field

Computer Science & AI1

Source

Type

Access

Modality

Image1 Tabular1 Text1 Video1

Method

Optical character recognition1

Format

License

Year

1 dataset

Evidence

strictstandardbroad

Export CSV · JSONL · IDs1–1 shown · 413 ms

Query

{
  "version": "1.0",
  "query": {
    "text": "handwriting OCR",
    "operator": "and",
    "filters": [
      {
        "field": "modality",
        "op": "eq",
        "value": "Video",
        "evidence": null
      }
    ],
    "evidence_policy": "standard"
  },
  "sort": null,
  "page": {
    "size": 25
  }
}

Hugging Face Datasets2026 · Image
VidScribe
VidScribe VidScribe is a diagnostic benchmark for visual text in video generation. It has four tasks: T2V (render text from a prompt), R2V (transfer text identity from a reference image), I2V (keep text intact under motion from a first frame), and V2V (edit localized text in an existing video). Every sample is labeled on 12 factor axes (F1–F12). Release status. This repository hosts the public hal
huggingface.co ↗Computer Science & AI · Image · Tabular · TextSynced 6 d ago
Why it matched · keyword, concept
Keyword
ocr
Concept
OCR
Concept
handwriting recognition